spb/wp30_uqo

Public
11commits
1branches
0releases
171.6 MBon disk
maindefault branch
4 days agolast push
358.3 KB · 115 lines
1{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "1acce7293fdf27d3784c6e81", "attempt_id": "3a91072adb5b", "run_group_id": "E0_smoke_llama:A0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:10.997570Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425501000}, "weight_precision": "bf16", "method_id": "A0", "implementation_fidelity": "custom", "compression_config": {"realized": {"note": "receiver gets no source context"}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 0, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 86, "message_tokens": 0, "message_utf8_bytes": 0, "cache_tensor_bytes": null, "serialized_payload_bytes": 0, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.006209011189639568, "decode_payload_ms": 0.0, "receiver_prefill_ms": 104.80358300264925, "ttft_ms": 38.55491697322577, "decode_ms": 42.36904205754399}, "total_wall_ms": 194.91720804944634, "ttft_ms": 38.55491697322577, "input_usage": {"receiver_prompt_tokens": 86}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6927237120, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6512662392, "mlx_cache_bytes": 88274304, "process_rss_bytes": 6927237120}, "peak_prefill_memory": null, "peak_decode_memory": 6512662392, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b764cdc0eab7137467211272fa539f1260d1bf2e71bcf6ff3bdc960f5c16aa14"}2{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "7e57ab223f53fe54106b58be", "attempt_id": "783d0cb42803", "run_group_id": "E0_smoke_llama:A0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:11.222377Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A0", "implementation_fidelity": "custom", "compression_config": {"realized": {"note": "receiver gets no source context"}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 0, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 91, "message_tokens": 0, "message_utf8_bytes": 0, "cache_tensor_bytes": null, "serialized_payload_bytes": 0, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.006209011189639568, "decode_payload_ms": 0.0, "receiver_prefill_ms": 49.940416938625276, "ttft_ms": 32.91054104920477, "decode_ms": 55.94099999871105}, "total_wall_ms": 139.85866599250585, "ttft_ms": 32.91054104920477, "input_usage": {"receiver_prompt_tokens": 91}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6927417344, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6516209100, "mlx_cache_bytes": 151221992, "process_rss_bytes": 6927417344}, "peak_prefill_memory": null, "peak_decode_memory": 6516209100, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Unknown.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "9cf9f50925b2a7803c73826a305235d4215dc428721c731072a9f2c0f5d6ae5a"}3{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "80eba4737155699c0a7c69f8", "attempt_id": "ef9db7ee8bcb", "run_group_id": "E0_smoke_llama:A0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:11.386669Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A0", "implementation_fidelity": "custom", "compression_config": {"realized": {"note": "receiver gets no source context"}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 0, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 91, "message_tokens": 0, "message_utf8_bytes": 0, "cache_tensor_bytes": null, "serialized_payload_bytes": 0, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.006209011189639568, "decode_payload_ms": 0.0, "receiver_prefill_ms": 60.74287497904152, "ttft_ms": 34.07541697379202, "decode_ms": 90.18166700843722}, "total_wall_ms": 185.84875005763024, "ttft_ms": 34.07541697379202, "input_usage": {"receiver_prompt_tokens": 91}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6927433728, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6516209100, "mlx_cache_bytes": 151221992, "process_rss_bytes": 6927433728}, "peak_prefill_memory": null, "peak_decode_memory": 6516209100, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Unknown.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "9cf9f50925b2a7803c73826a305235d4215dc428721c731072a9f2c0f5d6ae5a"}4{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "0f310404290cf683416256cc", "attempt_id": "55ce2bb3b2ca", "run_group_id": "E0_smoke_llama:A0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:11.596095Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A0", "implementation_fidelity": "custom", "compression_config": {"realized": {"note": "receiver gets no source context"}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 0, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 88, "message_tokens": 0, "message_utf8_bytes": 0, "cache_tensor_bytes": null, "serialized_payload_bytes": 0, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.006209011189639568, "decode_payload_ms": 0.0, "receiver_prefill_ms": 53.37033304385841, "ttft_ms": 35.44983407482505, "decode_ms": 62.86750000435859}, "total_wall_ms": 152.5538330897689, "ttft_ms": 35.44983407482505, "input_usage": {"receiver_prompt_tokens": 88}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6927450112, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6519993804, "mlx_cache_bytes": 177665768, "process_rss_bytes": 6927450112}, "peak_prefill_memory": null, "peak_decode_memory": 6519993804, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Unknown.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "9cf9f50925b2a7803c73826a305235d4215dc428721c731072a9f2c0f5d6ae5a"}5{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "a06eb15f6c19a57624f42a03", "attempt_id": "8204848563f0", "run_group_id": "E0_smoke_llama:A1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:11.774406Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A1", "implementation_fidelity": "custom", "compression_config": {}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1862, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 7280, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.011915923096239567, "decode_payload_ms": 0.0, "receiver_prefill_ms": 444.0474580042064, "ttft_ms": 114.788957987912, "decode_ms": 270.48599999397993}, "total_wall_ms": 832.6459999661893, "ttft_ms": 114.788957987912, "input_usage": {"receiver_prompt_tokens": 1862}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6927777792, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7120900424, "mlx_cache_bytes": 884249596, "process_rss_bytes": 6927777792}, "peak_prefill_memory": null, "peak_decode_memory": 7120900424, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}6{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "b1d7b1cce8d3a973f5a29a1a", "attempt_id": "6bbc100b1afa", "run_group_id": "E0_smoke_llama:A1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:12.629456Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A1", "implementation_fidelity": "custom", "compression_config": {}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1867, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 7280, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.011915923096239567, "decode_payload_ms": 0.0, "receiver_prefill_ms": 495.7376670790836, "ttft_ms": 44.04479102231562, "decode_ms": 340.5430830316618}, "total_wall_ms": 884.0085410047323, "ttft_ms": 44.04479102231562, "input_usage": {"receiver_prompt_tokens": 1867}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6695288832, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7122260316, "mlx_cache_bytes": 1354510628, "process_rss_bytes": 6695288832}, "peak_prefill_memory": null, "peak_decode_memory": 7122260316, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}7{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "0d0757aa5d272f5e5f06f1f4", "attempt_id": "b5a52cd8b5e1", "run_group_id": "E0_smoke_llama:A1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:13.535016Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A1", "implementation_fidelity": "custom", "compression_config": {}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1867, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 7280, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.011915923096239567, "decode_payload_ms": 0.0, "receiver_prefill_ms": 451.73691597301513, "ttft_ms": 37.32558398041874, "decode_ms": 178.22666699066758}, "total_wall_ms": 670.3590000979602, "ttft_ms": 37.32558398041874, "input_usage": {"receiver_prompt_tokens": 1867}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6641074176, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7122260316, "mlx_cache_bytes": 1354510628, "process_rss_bytes": 6641074176}, "peak_prefill_memory": null, "peak_decode_memory": 7122260316, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}8{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d29228b6041b9db070f72d7c", "attempt_id": "b70bcb139367", "run_group_id": "E0_smoke_llama:A1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:14.229625Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A1", "implementation_fidelity": "custom", "compression_config": {}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1864, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 7280, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.011915923096239567, "decode_payload_ms": 0.0, "receiver_prefill_ms": 440.22891600616276, "ttft_ms": 39.44133303593844, "decode_ms": 205.141541082412}, "total_wall_ms": 687.8513750853017, "ttft_ms": 39.44133303593844, "input_usage": {"receiver_prompt_tokens": 1864}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6551306240, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7159222632, "mlx_cache_bytes": 1594913060, "process_rss_bytes": 6551306240}, "peak_prefill_memory": null, "peak_decode_memory": 7159222632, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}9{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "4c3a0a4bad55488d3a6874e2", "attempt_id": "3170a08d5ad8", "run_group_id": "E0_smoke_llama:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:14.941063Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1766}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 617, "message_tokens": 516, "message_utf8_bytes": 1940, "cache_tensor_bytes": null, "serialized_payload_bytes": 1940, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.5928338980302215, "decode_payload_ms": 0.0, "receiver_prefill_ms": 177.61712498031557, "ttft_ms": 45.229541952721775, "decode_ms": 52.08924994803965}, "total_wall_ms": 276.7296659294516, "ttft_ms": 45.229541952721775, "input_usage": {"receiver_prompt_tokens": 617}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6554402816, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6867467768, "mlx_cache_bytes": 2050112196, "process_rss_bytes": 6554402816}, "peak_prefill_memory": null, "peak_decode_memory": 6867467768, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "83c1970dac87ef7396a52d14a2764a080806f090cf3b37207beb09b20af11f42", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}10{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d422269a403ca89ddb2d4079", "attempt_id": "0521e5fc82fd", "run_group_id": "E0_smoke_llama:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:15.236832Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1766}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 622, "message_tokens": 516, "message_utf8_bytes": 1940, "cache_tensor_bytes": null, "serialized_payload_bytes": 1940, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.5928338980302215, "decode_payload_ms": 0.0, "receiver_prefill_ms": 125.95404102467, "ttft_ms": 37.89616597350687, "decode_ms": 391.38012495823205}, "total_wall_ms": 556.9134170655161, "ttft_ms": 37.89616597350687, "input_usage": {"receiver_prompt_tokens": 622}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6554009600, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6878428684, "mlx_cache_bytes": 2363245688, "process_rss_bytes": 6554009600}, "peak_prefill_memory": null, "peak_decode_memory": 6878428684, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "83c1970dac87ef7396a52d14a2764a080806f090cf3b37207beb09b20af11f42", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}11{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d1de1204b1dde86818bd5184", "attempt_id": "38fb4366138f", "run_group_id": "E0_smoke_llama:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:15.818841Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1766}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 622, "message_tokens": 516, "message_utf8_bytes": 1940, "cache_tensor_bytes": null, "serialized_payload_bytes": 1940, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.5928338980302215, "decode_payload_ms": 0.0, "receiver_prefill_ms": 168.85512496810406, "ttft_ms": 48.81137504708022, "decode_ms": 38.724916987121105}, "total_wall_ms": 258.002792019397, "ttft_ms": 48.81137504708022, "input_usage": {"receiver_prompt_tokens": 622}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6554058752, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6882262540, "mlx_cache_bytes": 2363245688, "process_rss_bytes": 6554058752}, "peak_prefill_memory": null, "peak_decode_memory": 6882262540, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "83c1970dac87ef7396a52d14a2764a080806f090cf3b37207beb09b20af11f42", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}12{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "a97ce48716cccfffb0df7d46", "attempt_id": "8aff5e407615", "run_group_id": "E0_smoke_llama:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:16.096513Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1766}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 619, "message_tokens": 516, "message_utf8_bytes": 1940, "cache_tensor_bytes": null, "serialized_payload_bytes": 1940, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.5928338980302215, "decode_payload_ms": 0.0, "receiver_prefill_ms": 154.10387504380196, "ttft_ms": 35.48179194331169, "decode_ms": 60.69491698872298}, "total_wall_ms": 251.7090420005843, "ttft_ms": 35.48179194331169, "input_usage": {"receiver_prompt_tokens": 619}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6554173440, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6900022796, "mlx_cache_bytes": 2602517624, "process_rss_bytes": 6554173440}, "peak_prefill_memory": null, "peak_decode_memory": 6900022796, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "83c1970dac87ef7396a52d14a2764a080806f090cf3b37207beb09b20af11f42", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}13{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "65b2e0d942958d4955094a38", "attempt_id": "168a1109b45c", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:16.370902Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 509, "n_sentences": 18}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 606, "message_tokens": 509, "message_utf8_bytes": 1536, "cache_tensor_bytes": null, "serialized_payload_bytes": 1536, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.271499950438738, "decode_payload_ms": 0.0, "receiver_prefill_ms": 174.26633299328387, "ttft_ms": 25.856332969851792, "decode_ms": 169.48837495874614}, "total_wall_ms": 371.1075000464916, "ttft_ms": 25.856332969851792, "input_usage": {"receiver_prompt_tokens": 606}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6556090368, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6861684216, "mlx_cache_bytes": 2940961912, "process_rss_bytes": 6556090368}, "peak_prefill_memory": null, "peak_decode_memory": 6861684216, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Haruki Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "0ca1d3fed207a8962d88341b7fb1b07da00df9d8e507d786a2e99c06b18d0a62", "output_hash": "55a01495263476a6da84eabe2c22899f74b3909040b9d9d4fe8a8b6431ff9e18"}14{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "2a898ab433c5394686322580", "attempt_id": "2dbaac58758b", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:16.760564Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 509, "n_sentences": 18}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 611, "message_tokens": 509, "message_utf8_bytes": 1536, "cache_tensor_bytes": null, "serialized_payload_bytes": 1536, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.271499950438738, "decode_payload_ms": 0.0, "receiver_prefill_ms": 140.41587500832975, "ttft_ms": 38.561749970540404, "decode_ms": 40.86958395782858}, "total_wall_ms": 221.20654198806733, "ttft_ms": 38.561749970540404, "input_usage": {"receiver_prompt_tokens": 611}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6556106752, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6864387576, "mlx_cache_bytes": 3282191480, "process_rss_bytes": 6556106752}, "peak_prefill_memory": null, "peak_decode_memory": 6864387576, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "0ca1d3fed207a8962d88341b7fb1b07da00df9d8e507d786a2e99c06b18d0a62", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}15{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "ec7b2a9fe84bf0e283f64e2a", "attempt_id": "4c277500c5b6", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:17.001906Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 509, "n_sentences": 18}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 611, "message_tokens": 509, "message_utf8_bytes": 1536, "cache_tensor_bytes": null, "serialized_payload_bytes": 1536, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.271499950438738, "decode_payload_ms": 0.0, "receiver_prefill_ms": 169.2981249652803, "ttft_ms": 23.593208054080606, "decode_ms": 54.50175004079938}, "total_wall_ms": 248.86029202025384, "ttft_ms": 23.593208054080606, "input_usage": {"receiver_prompt_tokens": 611}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6557040640, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6864387576, "mlx_cache_bytes": 3282191480, "process_rss_bytes": 6557040640}, "peak_prefill_memory": null, "peak_decode_memory": 6864387576, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "0ca1d3fed207a8962d88341b7fb1b07da00df9d8e507d786a2e99c06b18d0a62", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}16{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "0c1493bd8cd834eeb7aa0785", "attempt_id": "9169bdcba916", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:17.272578Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 509, "n_sentences": 18}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 608, "message_tokens": 509, "message_utf8_bytes": 1536, "cache_tensor_bytes": null, "serialized_payload_bytes": 1536, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.271499950438738, "decode_payload_ms": 0.0, "receiver_prefill_ms": 180.0412500742823, "ttft_ms": 43.045250000432134, "decode_ms": 190.88037498295307}, "total_wall_ms": 415.3167080366984, "ttft_ms": 43.045250000432134, "input_usage": {"receiver_prompt_tokens": 608}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6557106176, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6893698552, "mlx_cache_bytes": 3438888056, "process_rss_bytes": 6557106176}, "peak_prefill_memory": null, "peak_decode_memory": 6893698552, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "0ca1d3fed207a8962d88341b7fb1b07da00df9d8e507d786a2e99c06b18d0a62", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}17{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e9f693f84c29d8efb40e2291", "attempt_id": "79119d577b43", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:17.707911Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 511, "n_sentences": 28}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 608, "message_tokens": 511, "message_utf8_bytes": 1555, "cache_tensor_bytes": null, "serialized_payload_bytes": 1555, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.141499960795045, "decode_payload_ms": 0.0, "receiver_prefill_ms": 137.3269580071792, "ttft_ms": 42.00733406469226, "decode_ms": 276.81891701649874}, "total_wall_ms": 458.59983400441706, "ttft_ms": 42.00733406469226, "input_usage": {"receiver_prompt_tokens": 608}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6557253632, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6901202424, "mlx_cache_bytes": 3438888056, "process_rss_bytes": 6557253632}, "peak_prefill_memory": null, "peak_decode_memory": 6901202424, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "0ff405ac03e5a10e14d572266d362d361b4219fa184f9be3bb806057879fd9ac", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}18{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "72b77475732181169f7e78f8", "attempt_id": "1910237ecabe", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:18.186661Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 508, "n_sentences": 29}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 610, "message_tokens": 508, "message_utf8_bytes": 1715, "cache_tensor_bytes": null, "serialized_payload_bytes": 1715, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.1243750341236591, "decode_payload_ms": 0.0, "receiver_prefill_ms": 195.8667910657823, "ttft_ms": 23.60216702800244, "decode_ms": 335.8849590877071}, "total_wall_ms": 557.7511669835076, "ttft_ms": 23.60216702800244, "input_usage": {"receiver_prompt_tokens": 610}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6557384704, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6864387576, "mlx_cache_bytes": 3438888056, "process_rss_bytes": 6557384704}, "peak_prefill_memory": null, "peak_decode_memory": 6864387576, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2a8e20793db30181404c83877c2fa0ce0e9f4ce155842796b2e9a4db57e4d166", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}19{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "3aa7131806a41f29a7e7635a", "attempt_id": "e3374140fba2", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:18.766348Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 512, "n_sentences": 29}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 614, "message_tokens": 512, "message_utf8_bytes": 1561, "cache_tensor_bytes": null, "serialized_payload_bytes": 1561, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.0653340723365545, "decode_payload_ms": 0.0, "receiver_prefill_ms": 152.72070898208767, "ttft_ms": 38.70024997740984, "decode_ms": 168.77012501936406}, "total_wall_ms": 362.51762497704476, "ttft_ms": 38.70024997740984, "input_usage": {"receiver_prompt_tokens": 614}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6557630464, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6897040888, "mlx_cache_bytes": 3597091960, "process_rss_bytes": 6557630464}, "peak_prefill_memory": null, "peak_decode_memory": 6897040888, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "a53881c8306c0d00c837f52a61f488dcff8e4df7502a72cc68c383b3156842b8", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}20{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "2623ac986d4ae09b6f38cb6b", "attempt_id": "c118ee4ca756", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:19.148562Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 511, "n_sentences": 22}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 606, "message_tokens": 507, "message_utf8_bytes": 1893, "cache_tensor_bytes": null, "serialized_payload_bytes": 1893, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.0557500645518303, "decode_payload_ms": 0.0, "receiver_prefill_ms": 140.03133296500891, "ttft_ms": 41.58537497278303, "decode_ms": 201.92399993538857}, "total_wall_ms": 386.04374998249114, "ttft_ms": 41.58537497278303, "input_usage": {"receiver_prompt_tokens": 606}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6558023680, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6861684216, "mlx_cache_bytes": 3597091960, "process_rss_bytes": 6558023680}, "peak_prefill_memory": null, "peak_decode_memory": 6861684216, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "22d6a96c1f0de138d69e1c361d6afdd8664290d33341c244479d5699bb0376d5", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}21{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c297d644a762a42131883b7d", "attempt_id": "bad721ed6bbf", "run_group_id": "E0_smoke_llama:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:36.584206Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 612, "message_tokens": 512, "message_utf8_bytes": 1595, "cache_tensor_bytes": null, "serialized_payload_bytes": 1595, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 17029.7132920241, "decode_payload_ms": 0.0, "receiver_prefill_ms": 224.51616707257926, "ttft_ms": 51.759208901785314, "decode_ms": 58.00508300308138}, "total_wall_ms": 335.8493749983609, "ttft_ms": 51.759208901785314, "input_usage": {"receiver_prompt_tokens": 612, "sender_input_tokens": 1900, "sender_output_tokens": 512, "sender_prefill_ms": 444.6433329721913, "sender_ttft_ms": 42.203875025734305, "sender_decode_ms": 16540.646250010468}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6561136640, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6903856632, "mlx_cache_bytes": 4814004772, "process_rss_bytes": 6561136640}, "peak_prefill_memory": null, "peak_decode_memory": 6903856632, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2670c7b1d77f11e98aea66022431c5d5cd7ede827d457184e5ccd1710c1c584e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}22{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "af5ca197d146c72042e02b45", "attempt_id": "d46502500ded", "run_group_id": "E0_smoke_llama:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:36.941363Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 617, "message_tokens": 512, "message_utf8_bytes": 1595, "cache_tensor_bytes": null, "serialized_payload_bytes": 1595, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 17029.7132920241, "decode_payload_ms": 0.0, "receiver_prefill_ms": 149.41387507133186, "ttft_ms": 42.637665988877416, "decode_ms": 313.3010419551283}, "total_wall_ms": 506.7510830704123, "ttft_ms": 42.637665988877416, "input_usage": {"receiver_prompt_tokens": 617, "sender_input_tokens": 1900, "sender_output_tokens": 512, "sender_prefill_ms": 444.6433329721913, "sender_ttft_ms": 42.203875025734305, "sender_decode_ms": 16540.646250010468}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6561169408, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6867467768, "mlx_cache_bytes": 4814004772, "process_rss_bytes": 6561169408}, "peak_prefill_memory": null, "peak_decode_memory": 6867467768, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 916-F, Fermont", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.28571428571428575}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2670c7b1d77f11e98aea66022431c5d5cd7ede827d457184e5ccd1710c1c584e", "output_hash": "90f0dea38d92a987240fd60c09e83237873c207c6079538eed9a620045be71c5"}23{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "55c02754131bfc6f507a1cf8", "attempt_id": "fe9605bbc93f", "run_group_id": "E0_smoke_llama:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:37.466533Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 617, "message_tokens": 512, "message_utf8_bytes": 1595, "cache_tensor_bytes": null, "serialized_payload_bytes": 1595, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 17029.7132920241, "decode_payload_ms": 0.0, "receiver_prefill_ms": 199.5497919851914, "ttft_ms": 48.74649993143976, "decode_ms": 90.31466708984226}, "total_wall_ms": 339.81412497814745, "ttft_ms": 48.74649993143976, "input_usage": {"receiver_prompt_tokens": 617, "sender_input_tokens": 1900, "sender_output_tokens": 512, "sender_prefill_ms": 444.6433329721913, "sender_ttft_ms": 42.203875025734305, "sender_decode_ms": 16540.646250010468}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6561185792, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6867467768, "mlx_cache_bytes": 4814004772, "process_rss_bytes": 6561185792}, "peak_prefill_memory": null, "peak_decode_memory": 6867467768, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "68.6281", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2670c7b1d77f11e98aea66022431c5d5cd7ede827d457184e5ccd1710c1c584e", "output_hash": "dcf770b51da1816894e8b51a64ce9116a511525b5b251eab5e28faebddc3df9f"}24{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "7cd74952809d0bb6cd5c0200", "attempt_id": "b25eefb17888", "run_group_id": "E0_smoke_llama:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:37.825977Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 614, "message_tokens": 512, "message_utf8_bytes": 1595, "cache_tensor_bytes": null, "serialized_payload_bytes": 1595, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 17029.7132920241, "decode_payload_ms": 0.0, "receiver_prefill_ms": 189.33529197238386, "ttft_ms": 44.18208298739046, "decode_ms": 195.17187506426126}, "total_wall_ms": 430.00350007787347, "ttft_ms": 44.18208298739046, "input_usage": {"receiver_prompt_tokens": 614, "sender_input_tokens": 1900, "sender_output_tokens": 512, "sender_prefill_ms": 444.6433329721913, "sender_ttft_ms": 42.203875025734305, "sender_decode_ms": 16540.646250010468}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6561218560, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6904610296, "mlx_cache_bytes": 4814004772, "process_rss_bytes": 6561218560}, "peak_prefill_memory": null, "peak_decode_memory": 6904610296, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2670c7b1d77f11e98aea66022431c5d5cd7ede827d457184e5ccd1710c1c584e", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}25{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "411f61984792a78bf25b5893", "attempt_id": "54a3e7485b18", "run_group_id": "E0_smoke_llama:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:57.740971Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 443, "message_tokens": 331, "message_utf8_bytes": 922, "cache_tensor_bytes": null, "serialized_payload_bytes": 922, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 19464.825083035976, "decode_payload_ms": 0.0, "receiver_prefill_ms": 130.85904193576425, "ttft_ms": 37.889541941694915, "decode_ms": 35.92687495984137}, "total_wall_ms": 206.39716705773026, "ttft_ms": 37.889541941694915, "input_usage": {"receiver_prompt_tokens": 443, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 487.87766601890326, "sender_ttft_ms": 50.601374940015376, "sender_decode_ms": 18924.01612503454}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6562988032, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6738705496, "mlx_cache_bytes": 5622825032, "process_rss_bytes": 6562988032}, "peak_prefill_memory": null, "peak_decode_memory": 6738705496, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e137340f68268b678688cd455e9b3cd6eb172e1f73407cc86ea551d8a3db9112", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}26{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "3cc9446b3ad102c3baf6af25", "attempt_id": "e9c37c9c8d05", "run_group_id": "E0_smoke_llama:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:57.969766Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 448, "message_tokens": 331, "message_utf8_bytes": 922, "cache_tensor_bytes": null, "serialized_payload_bytes": 922, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 19464.825083035976, "decode_payload_ms": 0.0, "receiver_prefill_ms": 144.1592500777915, "ttft_ms": 20.462832995690405, "decode_ms": 41.42437502741814}, "total_wall_ms": 207.5935839675367, "ttft_ms": 20.462832995690405, "input_usage": {"receiver_prompt_tokens": 448, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 487.87766601890326, "sender_ttft_ms": 50.601374940015376, "sender_decode_ms": 18924.01612503454}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6563053568, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6741605464, "mlx_cache_bytes": 5873107016, "process_rss_bytes": 6563053568}, "peak_prefill_memory": null, "peak_decode_memory": 6741605464, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e137340f68268b678688cd455e9b3cd6eb172e1f73407cc86ea551d8a3db9112", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}27{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c27ce71f958b1a8eab837012", "attempt_id": "34724b1a5730", "run_group_id": "E0_smoke_llama:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:58.201511Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 448, "message_tokens": 331, "message_utf8_bytes": 922, "cache_tensor_bytes": null, "serialized_payload_bytes": 922, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 19464.825083035976, "decode_payload_ms": 0.0, "receiver_prefill_ms": 170.96658307127655, "ttft_ms": 44.05787494033575, "decode_ms": 87.86874997895211}, "total_wall_ms": 304.1407499695197, "ttft_ms": 44.05787494033575, "input_usage": {"receiver_prompt_tokens": 448, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 487.87766601890326, "sender_ttft_ms": 50.601374940015376, "sender_decode_ms": 18924.01612503454}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6563119104, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6741605464, "mlx_cache_bytes": 5873107016, "process_rss_bytes": 6563119104}, "peak_prefill_memory": null, "peak_decode_memory": 6741605464, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "58.0820", "evidence_artifact": {"n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e137340f68268b678688cd455e9b3cd6eb172e1f73407cc86ea551d8a3db9112", "output_hash": "b38eb8a0b5e545425ac83b4aa75ce5fda3dec19e0fb0d34757f1276e1e89f55b"}28{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "04038b21771c154b41a48952", "attempt_id": "c059118314e3", "run_group_id": "E0_smoke_llama:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:43:58.528210Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 445, "message_tokens": 331, "message_utf8_bytes": 922, "cache_tensor_bytes": null, "serialized_payload_bytes": 922, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 19464.825083035976, "decode_payload_ms": 0.0, "receiver_prefill_ms": 147.983834031038, "ttft_ms": 45.002790982834995, "decode_ms": 24.279332952573895}, "total_wall_ms": 218.7393750064075, "ttft_ms": 45.002790982834995, "input_usage": {"receiver_prompt_tokens": 445, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 487.87766601890326, "sender_ttft_ms": 50.601374940015376, "sender_decode_ms": 18924.01612503454}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6563135488, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6762527832, "mlx_cache_bytes": 6031409224, "process_rss_bytes": 6563135488}, "peak_prefill_memory": null, "peak_decode_memory": 6762527832, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e137340f68268b678688cd455e9b3cd6eb172e1f73407cc86ea551d8a3db9112", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}29{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "84a6deed072a53ee196c6aee", "attempt_id": "3ee33f336d99", "run_group_id": "E0_smoke_llama:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:19.121617Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A6", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "max_fetch_bytes": 2000, "max_lookups": 6, "realized": {"n_refs": 9}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 918, "message_tokens": 821, "message_utf8_bytes": 816, "cache_tensor_bytes": null, "serialized_payload_bytes": 816, "side_information_bytes": 0, "fetched_bytes": 1496, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20351.395833073184, "decode_payload_ms": 0.0, "receiver_prefill_ms": 220.54516593925655, "ttft_ms": 24.7326249955222, "decode_ms": 286.289207986556}, "total_wall_ms": 533.5963340476155, "ttft_ms": 24.7326249955222, "input_usage": {"receiver_prompt_tokens": 918, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 592.018208000809, "sender_ttft_ms": 40.81787494942546, "sender_decode_ms": 19716.19079192169}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6564102144, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6962990168, "mlx_cache_bytes": 6599819336, "process_rss_bytes": 6564102144}, "peak_prefill_memory": null, "peak_decode_memory": 6962990168, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1496, "retrieved_refs": 6}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "20e51e9edfce0f1f7bbb42564f4a801681629d693f39bdfd2f0fa18174b9872c", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}30{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "9ae727a39e3113fae8cdea21", "attempt_id": "5576328117db", "run_group_id": "E0_smoke_llama:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:19.675066Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A6", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "max_fetch_bytes": 2000, "max_lookups": 6, "realized": {"n_refs": 9}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 927, "message_tokens": 825, "message_utf8_bytes": 816, "cache_tensor_bytes": null, "serialized_payload_bytes": 816, "side_information_bytes": 0, "fetched_bytes": 1498, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20351.395833073184, "decode_payload_ms": 0.0, "receiver_prefill_ms": 253.4893749980256, "ttft_ms": 33.21612498257309, "decode_ms": 33.41083403211087}, "total_wall_ms": 321.7156248865649, "ttft_ms": 33.21612498257309, "input_usage": {"receiver_prompt_tokens": 927, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 592.018208000809, "sender_ttft_ms": 40.81787494942546, "sender_decode_ms": 19716.19079192169}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6564380672, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6967446616, "mlx_cache_bytes": 7055458376, "process_rss_bytes": 6564380672}, "peak_prefill_memory": null, "peak_decode_memory": 6967446616, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1498, "retrieved_refs": 6}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "dd58c6723f7a488b688a9800bd53ab4c41b6262ba448a078f439a766616620c8", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}31{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "55543c366c72ffdbbd39c8af", "attempt_id": "66686a257fbb", "run_group_id": "E0_smoke_llama:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:20.017815Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A6", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "max_fetch_bytes": 2000, "max_lookups": 6, "realized": {"n_refs": 9}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 911, "message_tokens": 809, "message_utf8_bytes": 816, "cache_tensor_bytes": null, "serialized_payload_bytes": 816, "side_information_bytes": 0, "fetched_bytes": 1498, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20351.395833073184, "decode_payload_ms": 0.0, "receiver_prefill_ms": 246.01679190527648, "ttft_ms": 32.576250028796494, "decode_ms": 151.59720892552286}, "total_wall_ms": 432.2824589908123, "ttft_ms": 32.576250028796494, "input_usage": {"receiver_prompt_tokens": 911, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 592.018208000809, "sender_ttft_ms": 40.81787494942546, "sender_decode_ms": 19716.19079192169}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6564429824, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6964415564, "mlx_cache_bytes": 7480819784, "process_rss_bytes": 6564429824}, "peak_prefill_memory": null, "peak_decode_memory": 6964415564, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1498, "retrieved_refs": 6}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e1819d55abb157660a30ec7e8741d5ff9892523ece3b510e1752a6800ca62402", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}32{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "99d6c56f377436971f9e4433", "attempt_id": "d7f4cc777047", "run_group_id": "E0_smoke_llama:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:20.470661Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A6", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "max_fetch_bytes": 2000, "max_lookups": 6, "realized": {"n_refs": 9}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 924, "message_tokens": 825, "message_utf8_bytes": 816, "cache_tensor_bytes": null, "serialized_payload_bytes": 816, "side_information_bytes": 0, "fetched_bytes": 1498, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20351.395833073184, "decode_payload_ms": 0.0, "receiver_prefill_ms": 265.9725840203464, "ttft_ms": 36.55616601463407, "decode_ms": 28.996124980039895}, "total_wall_ms": 333.160417038016, "ttft_ms": 36.55616601463407, "input_usage": {"receiver_prompt_tokens": 924, "sender_input_tokens": 1930, "sender_output_tokens": 512, "sender_prefill_ms": 592.018208000809, "sender_ttft_ms": 40.81787494942546, "sender_decode_ms": 19716.19079192169}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6564495360, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7001082968, "mlx_cache_bytes": 7677526088, "process_rss_bytes": 6564495360}, "peak_prefill_memory": null, "peak_decode_memory": 7001082968, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1498, "retrieved_refs": 6}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "dd58c6723f7a488b688a9800bd53ab4c41b6262ba448a078f439a766616620c8", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}33{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "7b6538619254e7b397e82909", "attempt_id": "499765337f31", "run_group_id": "E0_smoke_llama:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:20.830950Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 3.5135135135135136}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1862, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 2072, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 7.439083070494235, "decode_payload_ms": 0.5127090262249112, "receiver_prefill_ms": 498.52987495251, "ttft_ms": 36.994458991102874, "decode_ms": 260.9179160790518}, "total_wall_ms": 800.1195830293, "ttft_ms": 36.994458991102874, "input_usage": {"receiver_prompt_tokens": 1862}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6569115648, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7120900424, "mlx_cache_bytes": 7677526088, "process_rss_bytes": 6569115648}, "peak_prefill_memory": null, "peak_decode_memory": 7120900424, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}34{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "93b4d8e4431a75f0233ad746", "attempt_id": "545588961097", "run_group_id": "E0_smoke_llama:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:21.651547Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 3.5135135135135136}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1867, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 2072, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 7.439083070494235, "decode_payload_ms": 0.5127090262249112, "receiver_prefill_ms": 509.5061670290306, "ttft_ms": 49.28991699125618, "decode_ms": 315.8052080543712}, "total_wall_ms": 877.6191669749096, "ttft_ms": 49.28991699125618, "input_usage": {"receiver_prompt_tokens": 1867}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6569164800, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7122260316, "mlx_cache_bytes": 7677526088, "process_rss_bytes": 6569164800}, "peak_prefill_memory": null, "peak_decode_memory": 7122260316, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}35{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "88d68cf77d7e11beadc7266c", "attempt_id": "2645dbd8e95d", "run_group_id": "E0_smoke_llama:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:22.553539Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 3.5135135135135136}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1867, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 2072, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 7.439083070494235, "decode_payload_ms": 0.5127090262249112, "receiver_prefill_ms": 450.3524579340592, "ttft_ms": 31.306082964874804, "decode_ms": 152.0601250231266}, "total_wall_ms": 636.4715420641005, "ttft_ms": 31.306082964874804, "input_usage": {"receiver_prompt_tokens": 1867}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6569181184, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7122260316, "mlx_cache_bytes": 7677526088, "process_rss_bytes": 6569181184}, "peak_prefill_memory": null, "peak_decode_memory": 7122260316, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}36{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e2b2bcfa03ca62ad479ecb48", "attempt_id": "f2ba1f71926d", "run_group_id": "E0_smoke_llama:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:23.209456Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 3.5135135135135136}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 1864, "message_tokens": 1766, "message_utf8_bytes": 7280, "cache_tensor_bytes": null, "serialized_payload_bytes": 2072, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 7.439083070494235, "decode_payload_ms": 0.5127090262249112, "receiver_prefill_ms": 491.95970804430544, "ttft_ms": 44.978291960433125, "decode_ms": 222.31799992732704}, "total_wall_ms": 762.6348329940811, "ttft_ms": 44.978291960433125, "input_usage": {"receiver_prompt_tokens": 1864}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6569197568, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7179080028, "mlx_cache_bytes": 7677526088, "process_rss_bytes": 6569197568}, "peak_prefill_memory": null, "peak_decode_memory": 7179080028, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}37{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "cc589ec7a25b40c391448878", "attempt_id": "8d1266ebf492", "run_group_id": "E0_smoke_llama:B0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:24.515315Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870660104}, "weight_precision": "bf16", "method_id": "B0", "implementation_fidelity": "custom", "compression_config": {"realized": {}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433294, "side_information_bytes": 13006, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 522.5020839134231, "doc_prefill_ms": 437.422874965705, "compress_ms": 10.527916951104999, "serialize_ms": 70.8771669305861, "load_ms": 6.305875023826957, "receiver_prefill_ms": 0.0, "query_prefill_ms": 72.47437501791865, "ttft_ms": 72.47437501791865, "decode_ms": 261.442834045738}, "total_wall_ms": 341.9492499670014, "ttft_ms": 72.47437501791865, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6991708160, "backend_memory": {"mlx_active_bytes": 7085356040, "mlx_peak_bytes": 7148451120, "mlx_cache_bytes": 8003223625, "process_rss_bytes": 6991708160}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7148451120, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "fa7deb82387df79ba9c62b52861e9729c29f9571c7ce3cc4593b01366fba1eb9", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}38{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "be00ef5059d78d7afef9989a", "attempt_id": "54c814cd5911", "run_group_id": "E0_smoke_llama:B0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:24.879707Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870660104}, "weight_precision": "bf16", "method_id": "B0", "implementation_fidelity": "custom", "compression_config": {"realized": {}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433294, "side_information_bytes": 13006, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 522.5020839134231, "doc_prefill_ms": 437.422874965705, "compress_ms": 10.527916951104999, "serialize_ms": 70.8771669305861, "load_ms": 5.109624937176704, "receiver_prefill_ms": 0.0, "query_prefill_ms": 77.48341606929898, "ttft_ms": 77.48341606929898, "decode_ms": 384.95275005698204}, "total_wall_ms": 469.2965829744935, "ttft_ms": 77.48341606929898, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6991921152, "backend_memory": {"mlx_active_bytes": 7086273544, "mlx_peak_bytes": 7152973104, "mlx_cache_bytes": 8294957129, "process_rss_bytes": 6991921152}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7152973104, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "fa7deb82387df79ba9c62b52861e9729c29f9571c7ce3cc4593b01366fba1eb9", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}39{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "5dbb517dc1e39027d47ce53d", "attempt_id": "67c316ecb86b", "run_group_id": "E0_smoke_llama:B0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:25.371676Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870660104}, "weight_precision": "bf16", "method_id": "B0", "implementation_fidelity": "custom", "compression_config": {"realized": {}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433294, "side_information_bytes": 13006, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 522.5020839134231, "doc_prefill_ms": 437.422874965705, "compress_ms": 10.527916951104999, "serialize_ms": 70.8771669305861, "load_ms": 4.740834003314376, "receiver_prefill_ms": 0.0, "query_prefill_ms": 61.675542034208775, "ttft_ms": 61.675542034208775, "decode_ms": 163.4873750153929}, "total_wall_ms": 231.41041700728238, "ttft_ms": 61.675542034208775, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6991953920, "backend_memory": {"mlx_active_bytes": 7085356040, "mlx_peak_bytes": 7152973104, "mlx_cache_bytes": 8295874633, "process_rss_bytes": 6991953920}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7152973104, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "fa7deb82387df79ba9c62b52861e9729c29f9571c7ce3cc4593b01366fba1eb9", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}40{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e30c2d93f6504db52f420ff5", "attempt_id": "201b24eb535f", "run_group_id": "E0_smoke_llama:B0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:25.623900Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870660104}, "weight_precision": "bf16", "method_id": "B0", "implementation_fidelity": "custom", "compression_config": {"realized": {}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433294, "side_information_bytes": 13006, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 522.5020839134231, "doc_prefill_ms": 437.422874965705, "compress_ms": 10.527916951104999, "serialize_ms": 70.8771669305861, "load_ms": 8.166083018295467, "receiver_prefill_ms": 0.0, "query_prefill_ms": 58.05266601964831, "ttft_ms": 58.05266601964831, "decode_ms": 214.86158296465874}, "total_wall_ms": 282.6327499933541, "ttft_ms": 58.05266601964831, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6992019456, "backend_memory": {"mlx_active_bytes": 7085356040, "mlx_peak_bytes": 7152416048, "mlx_cache_bytes": 8315551817, "process_rss_bytes": 6992019456}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7152416048, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "fa7deb82387df79ba9c62b52861e9729c29f9571c7ce3cc4593b01366fba1eb9", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}41{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "3bdce55ca1c203e6cb369146", "attempt_id": "cfdd9fae6058", "run_group_id": "E0_smoke_llama:B1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:25.999220Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870496264}, "weight_precision": "bf16", "method_id": "B1", "implementation_fidelity": "custom", "compression_config": {"realized": {"serialize_roundtrip": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": "63d490dc6cecd04f", "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433322, "side_information_bytes": 13034, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.577791986987, "doc_prefill_ms": 437.422874965705, "compress_ms": 5.062707932665944, "serialize_ms": 67.35641695559025, "load_ms": 38.35595794953406, "receiver_prefill_ms": 0.0, "query_prefill_ms": 61.90962495747954, "ttft_ms": 61.90962495747954, "decode_ms": 312.5291250180453}, "total_wall_ms": 414.4973329966888, "ttft_ms": 61.90962495747954, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 7202373632, "backend_memory": {"mlx_active_bytes": 7085192200, "mlx_peak_bytes": 7148139824, "mlx_cache_bytes": 8315715657, "process_rss_bytes": 7202373632}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7148139824, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c36a83ab14f375c59623a755718dc5b0bdfcef7c346cb20d001ff25b80cf6a92", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}42{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "da49bbe0ee1937a1d6cea01b", "attempt_id": "262b74cca3b0", "run_group_id": "E0_smoke_llama:B1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:26.434479Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870496264}, "weight_precision": "bf16", "method_id": "B1", "implementation_fidelity": "custom", "compression_config": {"realized": {"serialize_roundtrip": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": "63d490dc6cecd04f", "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433322, "side_information_bytes": 13034, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.577791986987, "doc_prefill_ms": 437.422874965705, "compress_ms": 5.062707932665944, "serialize_ms": 67.35641695559025, "load_ms": 27.08279201760888, "receiver_prefill_ms": 0.0, "query_prefill_ms": 36.74579202197492, "ttft_ms": 36.74579202197492, "decode_ms": 428.5999160492793}, "total_wall_ms": 493.9215829363093, "ttft_ms": 36.74579202197492, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 7202406400, "backend_memory": {"mlx_active_bytes": 7086109704, "mlx_peak_bytes": 7152809264, "mlx_cache_bytes": 8314798153, "process_rss_bytes": 7202406400}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7152809264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c36a83ab14f375c59623a755718dc5b0bdfcef7c346cb20d001ff25b80cf6a92", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}43{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "16b714f92a451743570b3b31", "attempt_id": "cf8fc0d51247", "run_group_id": "E0_smoke_llama:B1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:26.948504Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870496264}, "weight_precision": "bf16", "method_id": "B1", "implementation_fidelity": "custom", "compression_config": {"realized": {"serialize_roundtrip": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": "63d490dc6cecd04f", "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433322, "side_information_bytes": 13034, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.577791986987, "doc_prefill_ms": 437.422874965705, "compress_ms": 5.062707932665944, "serialize_ms": 67.35641695559025, "load_ms": 26.593707967549562, "receiver_prefill_ms": 0.0, "query_prefill_ms": 71.3852500775829, "ttft_ms": 71.3852500775829, "decode_ms": 116.4509579539299}, "total_wall_ms": 215.88545804843307, "ttft_ms": 71.3852500775829, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 7202455552, "backend_memory": {"mlx_active_bytes": 7085192200, "mlx_peak_bytes": 7152809264, "mlx_cache_bytes": 8315715657, "process_rss_bytes": 7202455552}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7152809264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c36a83ab14f375c59623a755718dc5b0bdfcef7c346cb20d001ff25b80cf6a92", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}44{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "3ab2375116fc39604b6bb3dd", "attempt_id": "0e62b672bf28", "run_group_id": "E0_smoke_llama:B1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:27.184808Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6870496264}, "weight_precision": "bf16", "method_id": "B1", "implementation_fidelity": "custom", "compression_config": {"realized": {"serialize_roundtrip": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": "63d490dc6cecd04f", "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 209420288, "serialized_payload_bytes": 209433322, "side_information_bytes": 13034, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.577791986987, "doc_prefill_ms": 437.422874965705, "compress_ms": 5.062707932665944, "serialize_ms": 67.35641695559025, "load_ms": 29.1128340177238, "receiver_prefill_ms": 0.0, "query_prefill_ms": 56.22645898256451, "ttft_ms": 56.22645898256451, "decode_ms": 231.56520805787295}, "total_wall_ms": 318.4051669668406, "ttft_ms": 56.22645898256451, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 7202471936, "backend_memory": {"mlx_active_bytes": 7085192200, "mlx_peak_bytes": 7152219440, "mlx_cache_bytes": 8315715657, "process_rss_bytes": 7202471936}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 7152219440, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c36a83ab14f375c59623a755718dc5b0bdfcef7c346cb20d001ff25b80cf6a92", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}45{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "99a3adca6917879f925d6786", "attempt_id": "a920ac2a6176", "run_group_id": "E0_smoke_llama:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:27.586430Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6773814280}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 8, "realized": {"bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 111254528, "serialized_payload_bytes": 111281646, "side_information_bytes": 27118, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 61.96125003043562, "doc_prefill_ms": 437.422874965705, "compress_ms": 30.956957954913378, "serialize_ms": 30.65370803233236, "load_ms": 13.677041977643967, "receiver_prefill_ms": 0.0, "query_prefill_ms": 217.12250006385148, "ttft_ms": 217.12250006385148, "decode_ms": 343.93254097085446}, "total_wall_ms": 576.2448329478502, "ttft_ms": 217.12250006385148, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 7316357120, "backend_memory": {"mlx_active_bytes": 6888567816, "mlx_peak_bytes": 6964742096, "mlx_cache_bytes": 8847362761, "process_rss_bytes": 7316357120}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6964742096, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c81fb07470693068b7485351f664d38e900f7f96b9ec080e540dd33f44152a99", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}46{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "8145f501bf31191588311a59", "attempt_id": "d17cb71f1d20", "run_group_id": "E0_smoke_llama:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:28.184216Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6773814280}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 8, "realized": {"bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 111254528, "serialized_payload_bytes": 111281646, "side_information_bytes": 27118, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 61.96125003043562, "doc_prefill_ms": 437.422874965705, "compress_ms": 30.956957954913378, "serialize_ms": 30.65370803233236, "load_ms": 3.7757500540465117, "receiver_prefill_ms": 0.0, "query_prefill_ms": 60.53770799189806, "ttft_ms": 60.53770799189806, "decode_ms": 339.0390001004562}, "total_wall_ms": 405.1002920605242, "ttft_ms": 60.53770799189806, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 7316570112, "backend_memory": {"mlx_active_bytes": 6889485320, "mlx_peak_bytes": 6971168592, "mlx_cache_bytes": 9017721641, "process_rss_bytes": 7316570112}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6971168592, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c81fb07470693068b7485351f664d38e900f7f96b9ec080e540dd33f44152a99", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}47{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "9e09d4a66b95560c536e4bb6", "attempt_id": "3398867c7cff", "run_group_id": "E0_smoke_llama:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:28.612313Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6773814280}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 8, "realized": {"bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 111254528, "serialized_payload_bytes": 111281646, "side_information_bytes": 27118, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 61.96125003043562, "doc_prefill_ms": 437.422874965705, "compress_ms": 30.956957954913378, "serialize_ms": 30.65370803233236, "load_ms": 7.927541038952768, "receiver_prefill_ms": 0.0, "query_prefill_ms": 89.23725003842264, "ttft_ms": 89.23725003842264, "decode_ms": 179.2399160331115}, "total_wall_ms": 278.06874993257225, "ttft_ms": 89.23725003842264, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 7316586496, "backend_memory": {"mlx_active_bytes": 6888502280, "mlx_peak_bytes": 6971171536, "mlx_cache_bytes": 9018704681, "process_rss_bytes": 7316586496}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6971171536, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c81fb07470693068b7485351f664d38e900f7f96b9ec080e540dd33f44152a99", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}48{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c936609e91653935523c0908", "attempt_id": "43b1cfa6952a", "run_group_id": "E0_smoke_llama:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:28.911150Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6773814280}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 8, "realized": {"bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 111254528, "serialized_payload_bytes": 111281646, "side_information_bytes": 27118, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 61.96125003043562, "doc_prefill_ms": 437.422874965705, "compress_ms": 30.956957954913378, "serialize_ms": 30.65370803233236, "load_ms": 4.78758302051574, "receiver_prefill_ms": 0.0, "query_prefill_ms": 39.28579203784466, "ttft_ms": 39.28579203784466, "decode_ms": 184.25929197110236}, "total_wall_ms": 230.09091592393816, "ttft_ms": 39.28579203784466, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 7316586496, "backend_memory": {"mlx_active_bytes": 6888567816, "mlx_peak_bytes": 6971415216, "mlx_cache_bytes": 9045216425, "process_rss_bytes": 7316586496}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6971415216, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c81fb07470693068b7485351f664d38e900f7f96b9ec080e540dd33f44152a99", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}49{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "7d6acf26fc79182f5dbb1ed8", "attempt_id": "15136fb321a2", "run_group_id": "E0_smoke_llama:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:29.244120Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6720943112}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 4, "realized": {"bits": 4}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 58899456, "serialized_payload_bytes": 58926513, "side_information_bytes": 27057, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 79.94737499393523, "doc_prefill_ms": 437.422874965705, "compress_ms": 51.74345790874213, "serialize_ms": 27.822209056466818, "load_ms": 3.18250001873821, "receiver_prefill_ms": 0.0, "query_prefill_ms": 185.57591596618295, "ttft_ms": 185.57591596618295, "decode_ms": 295.966292032972}, "total_wall_ms": 486.3574579358101, "ttft_ms": 185.57591596618295, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 7371276288, "backend_memory": {"mlx_active_bytes": 6782612488, "mlx_peak_bytes": 6847246256, "mlx_cache_bytes": 9327865001, "process_rss_bytes": 7371276288}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6847246256, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4180fb98d26b8f9bc2c30120aea76b31662b7d5e9c4b045f5c9627ed7b0df3a6", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}50{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c564af55b1354e855d13ebb5", "attempt_id": "d0c64cba8a9d", "run_group_id": "E0_smoke_llama:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:29.752314Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6720943112}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 4, "realized": {"bits": 4}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 58899456, "serialized_payload_bytes": 58926513, "side_information_bytes": 27057, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 79.94737499393523, "doc_prefill_ms": 437.422874965705, "compress_ms": 51.74345790874213, "serialize_ms": 27.822209056466818, "load_ms": 2.182958065532148, "receiver_prefill_ms": 0.0, "query_prefill_ms": 63.19291703402996, "ttft_ms": 63.19291703402996, "decode_ms": 353.3098748885095}, "total_wall_ms": 420.24579201824963, "ttft_ms": 63.19291703402996, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 7371325440, "backend_memory": {"mlx_active_bytes": 6782645256, "mlx_peak_bytes": 6854042320, "mlx_cache_bytes": 9327832233, "process_rss_bytes": 7371325440}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6854042320, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4180fb98d26b8f9bc2c30120aea76b31662b7d5e9c4b045f5c9627ed7b0df3a6", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}51{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "5f2dc6cc5e94630f30047acf", "attempt_id": "ef05ade2e72f", "run_group_id": "E0_smoke_llama:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:30.194955Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6720943112}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 4, "realized": {"bits": 4}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 58899456, "serialized_payload_bytes": 58926513, "side_information_bytes": 27057, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 79.94737499393523, "doc_prefill_ms": 437.422874965705, "compress_ms": 51.74345790874213, "serialize_ms": 27.822209056466818, "load_ms": 1.280625001527369, "receiver_prefill_ms": 0.0, "query_prefill_ms": 42.38108394201845, "ttft_ms": 42.38108394201845, "decode_ms": 163.35366701241583}, "total_wall_ms": 208.8556250091642, "ttft_ms": 42.38108394201845, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 7371358208, "backend_memory": {"mlx_active_bytes": 6782579720, "mlx_peak_bytes": 6854042320, "mlx_cache_bytes": 9327897769, "process_rss_bytes": 7371358208}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6854042320, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4180fb98d26b8f9bc2c30120aea76b31662b7d5e9c4b045f5c9627ed7b0df3a6", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}52{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "72933f8a71427c88fc872a97", "attempt_id": "4f258f174b74", "run_group_id": "E0_smoke_llama:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:30.427208Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6720943112}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 4, "realized": {"bits": 4}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 58899456, "serialized_payload_bytes": 58926513, "side_information_bytes": 27057, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 79.94737499393523, "doc_prefill_ms": 437.422874965705, "compress_ms": 51.74345790874213, "serialize_ms": 27.822209056466818, "load_ms": 2.032542019151151, "receiver_prefill_ms": 0.0, "query_prefill_ms": 54.19116606935859, "ttft_ms": 54.19116606935859, "decode_ms": 194.77229204494506}, "total_wall_ms": 252.6729580713436, "ttft_ms": 54.19116606935859, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 7371374592, "backend_memory": {"mlx_active_bytes": 6782579720, "mlx_peak_bytes": 6853991280, "mlx_cache_bytes": 9328159913, "process_rss_bytes": 7371374592}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6853991280, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4180fb98d26b8f9bc2c30120aea76b31662b7d5e9c4b045f5c9627ed7b0df3a6", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}53{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "4a990a3bbc163af0254f4da9", "attempt_id": "decdff1d7a8a", "run_group_id": "E0_smoke_llama:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:30.835010Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 56.43370805773884}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310610, "side_information_bytes": 12882, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 132.07170902751386, "doc_prefill_ms": 437.422874965705, "compress_ms": 56.50170799344778, "serialize_ms": 75.29904192779213, "load_ms": 0.7832079427316785, "receiver_prefill_ms": 0.0, "query_prefill_ms": 48.5515829641372, "ttft_ms": 48.5515829641372, "decode_ms": 492.50808299984783}, "total_wall_ms": 543.5889170039445, "ttft_ms": 48.5515829641372, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 12}, "provider_cached_usage": null, "process_memory": 7392919552, "backend_memory": {"mlx_active_bytes": 6772061192, "mlx_peak_bytes": 6811006264, "mlx_cache_bytes": 9428331689, "process_rss_bytes": 7392919552}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6811006264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "There is no Torsel-5 in the text.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4bede118afa323ca6bb797abb36c340ea9d9edcd57e651802639f006b0fd8a3f", "output_hash": "9692259f44dd18dd1cdbacd4f40fc5c86163138fa40a692cba37d5829d9efdae"}54{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "edb167c9d4a110a48c5571db", "attempt_id": "9bd754b97ad0", "run_group_id": "E0_smoke_llama:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:31.403191Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 56.43370805773884}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310610, "side_information_bytes": 12882, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 132.07170902751386, "doc_prefill_ms": 437.422874965705, "compress_ms": 56.50170799344778, "serialize_ms": 75.29904192779213, "load_ms": 4.029666073620319, "receiver_prefill_ms": 0.0, "query_prefill_ms": 59.984708088450134, "ttft_ms": 59.984708088450134, "decode_ms": 240.85499998182058}, "total_wall_ms": 306.52774998452514, "ttft_ms": 59.984708088450134, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 7392854016, "backend_memory": {"mlx_active_bytes": 6772323336, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 9444846761, "process_rss_bytes": 7392854016}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4bede118afa323ca6bb797abb36c340ea9d9edcd57e651802639f006b0fd8a3f", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}55{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "fd54709862c7fe9cda0b03ce", "attempt_id": "ae351568c289", "run_group_id": "E0_smoke_llama:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:31.732096Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 56.43370805773884}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310610, "side_information_bytes": 12882, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 132.07170902751386, "doc_prefill_ms": 437.422874965705, "compress_ms": 56.50170799344778, "serialize_ms": 75.29904192779213, "load_ms": 1.343625015579164, "receiver_prefill_ms": 0.0, "query_prefill_ms": 50.66633294336498, "ttft_ms": 50.66633294336498, "decode_ms": 127.93991691432893}, "total_wall_ms": 181.72441702336073, "ttft_ms": 50.66633294336498, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 7392903168, "backend_memory": {"mlx_active_bytes": 6772192264, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 9444977833, "process_rss_bytes": 7392903168}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Not available.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4bede118afa323ca6bb797abb36c340ea9d9edcd57e651802639f006b0fd8a3f", "output_hash": "469147b9096ca76595ba03d6e8e849959829de7be9f36bbb9e437b35a34af4c5"}56{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "f0e55404bf4c08124bf59b7e", "attempt_id": "5e01a4805fd3", "run_group_id": "E0_smoke_llama:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:31.936141Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 56.43370805773884}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310610, "side_information_bytes": 12882, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 132.07170902751386, "doc_prefill_ms": 437.422874965705, "compress_ms": 56.50170799344778, "serialize_ms": 75.29904192779213, "load_ms": 1.520541962236166, "receiver_prefill_ms": 0.0, "query_prefill_ms": 31.29674994852394, "ttft_ms": 31.29674994852394, "decode_ms": 252.26949993520975}, "total_wall_ms": 286.5531659917906, "ttft_ms": 31.29674994852394, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 7392477184, "backend_memory": {"mlx_active_bytes": 6772192264, "mlx_peak_bytes": 6815839544, "mlx_cache_bytes": 9444977833, "process_rss_bytes": 7392477184}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6815839544, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "AC-59L-3161", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "4bede118afa323ca6bb797abb36c340ea9d9edcd57e651802639f006b0fd8a3f", "output_hash": "ad64332dcd39755f6897a634ba23cec1a004826ea0ea9dabd0093a9c2ec190b0"}57{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "52c48b9797ca5c06552b1531", "attempt_id": "6091f1f0713c", "run_group_id": "E0_smoke_llama:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:32.302798Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 9.820375009439886}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310605, "side_information_bytes": 12877, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 60.8185000019148, "doc_prefill_ms": 437.422874965705, "compress_ms": 9.860167047008872, "serialize_ms": 50.75112509075552, "load_ms": 1.3935830211266875, "receiver_prefill_ms": 0.0, "query_prefill_ms": 57.18616594094783, "ttft_ms": 57.18616594094783, "decode_ms": 1790.9953750204295}, "total_wall_ms": 1851.3322500512004, "ttft_ms": 57.18616594094783, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 7445053440, "backend_memory": {"mlx_active_bytes": 6775993352, "mlx_peak_bytes": 6811006264, "mlx_cache_bytes": 9754963113, "process_rss_bytes": 7445053440}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6811006264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "}\n\n}\n\n}\n\n}\n\n}\n\n}\n\n}\n\n}\n\n\n\n\n\n\n\n\n\n\n\n}\n\n\n\n}\n\n\n\n}\n\n}\n\n}\n\n}\n\n}\n\n}\n\n}\n\n\n\n}\n\n\n\n}\n\n\n\n}\n\n\n\n}\n\n}\n\n}\n\n\n\n//}\n\n//////////////////////", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "00809d6606d7fc50c17f04bd8a4a3707958f32db62bac946b1c32fc3e676b47f", "output_hash": "ccccfe0de485e198bddd0417f4df11b4b4717882fdaf107fd56e690b6fa5f10b"}58{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "24076303fc2fee00bc3a854e", "attempt_id": "a133016fcd07", "run_group_id": "E0_smoke_llama:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:34.175581Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 9.820375009439886}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310605, "side_information_bytes": 12877, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 60.8185000019148, "doc_prefill_ms": 437.422874965705, "compress_ms": 9.860167047008872, "serialize_ms": 50.75112509075552, "load_ms": 3.364000003784895, "receiver_prefill_ms": 0.0, "query_prefill_ms": 44.80479098856449, "ttft_ms": 44.80479098856449, "decode_ms": 1871.8788340920582}, "total_wall_ms": 1922.2292910562828, "ttft_ms": 44.80479098856449, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 7445102592, "backend_memory": {"mlx_active_bytes": 6775993352, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 9754963113, "process_rss_bytes": 7445102592}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "}\n\n}\n\n}\n\n}\n\n\n\n}\n\n\n\n}\n\n\n\n}\n\n\n\n}\n\n}\n\n}\n\n}\n\n\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "00809d6606d7fc50c17f04bd8a4a3707958f32db62bac946b1c32fc3e676b47f", "output_hash": "8a98bf1cdbfff3febaa313db2ee830212976ff44521e87d9f91743b75c411c7c"}59{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "f481d30b9909473a1d70d9a6", "attempt_id": "dc9da1b7970d", "run_group_id": "E0_smoke_llama:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:36.118241Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 9.820375009439886}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310605, "side_information_bytes": 12877, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 60.8185000019148, "doc_prefill_ms": 437.422874965705, "compress_ms": 9.860167047008872, "serialize_ms": 50.75112509075552, "load_ms": 2.0380420610308647, "receiver_prefill_ms": 0.0, "query_prefill_ms": 19.68616701196879, "ttft_ms": 19.68616701196879, "decode_ms": 1811.1777500016615}, "total_wall_ms": 1834.7261250019073, "ttft_ms": 19.68616701196879, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 7445102592, "backend_memory": {"mlx_active_bytes": 6775993352, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 9754963113, "process_rss_bytes": 7445102592}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "}\n\n}\n\n}\n\n//////////////////////////////////////////////////////////////////////////////////////////", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "00809d6606d7fc50c17f04bd8a4a3707958f32db62bac946b1c32fc3e676b47f", "output_hash": "9c1c85d0af791dd782b2fc598b4c2453d6625d60ad58bacf00b9ab5c4e254186"}60{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c0bd23fcdf788f4e76591000", "attempt_id": "6bc2cb9bbadf", "run_group_id": "E0_smoke_llama:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:37.975107Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 1826, "keep": 456, "compress_ms": 9.820375009439886}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310605, "side_information_bytes": 12877, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 60.8185000019148, "doc_prefill_ms": 437.422874965705, "compress_ms": 9.860167047008872, "serialize_ms": 50.75112509075552, "load_ms": 5.221916944719851, "receiver_prefill_ms": 0.0, "query_prefill_ms": 48.19733300246298, "ttft_ms": 48.19733300246298, "decode_ms": 1727.6302080135792}, "total_wall_ms": 1782.6562089612707, "ttft_ms": 48.19733300246298, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6908248064, "backend_memory": {"mlx_active_bytes": 6775993352, "mlx_peak_bytes": 6815839544, "mlx_cache_bytes": 9754963113, "process_rss_bytes": 6908248064}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6815839544, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "}\n\n}\n\n}\n\n//////////////////////////////////////////////////////////////////////////////////////////", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 0.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "00809d6606d7fc50c17f04bd8a4a3707958f32db62bac946b1c32fc3e676b47f", "output_hash": "9c1c85d0af791dd782b2fc598b4c2453d6625d60ad58bacf00b9ab5c4e254186"}61{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c9bb5f57c39cd9b828c7092a", "attempt_id": "e9dc8ce0e20e", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:39.778208Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 36, "compress_ms": 223.24320790357888}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 245.0225839857012, "doc_prefill_ms": 437.422874965705, "compress_ms": 224.6504999930039, "serialize_ms": 20.149499992839992, "load_ms": 2.4289999855682254, "receiver_prefill_ms": 0.0, "query_prefill_ms": 38.21954189334065, "ttft_ms": 38.21954189334065, "decode_ms": 227.5533340871334}, "total_wall_ms": 515.092583023943, "ttft_ms": 38.21954189334065, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6921027584, "backend_memory": {"mlx_active_bytes": 6772061192, "mlx_peak_bytes": 6811006264, "mlx_cache_bytes": 10017287337, "process_rss_bytes": 6921027584}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6811006264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}62{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "ed4dca7d54c8d06691e35017", "attempt_id": "7f0d9603a35d", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:40.314694Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 41, "compress_ms": 162.85679198335856}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 192.2094589099288, "doc_prefill_ms": 437.422874965705, "compress_ms": 164.35245797038078, "serialize_ms": 27.638208004646003, "load_ms": 2.581541077233851, "receiver_prefill_ms": 0.0, "query_prefill_ms": 46.956875012256205, "ttft_ms": 46.956875012256205, "decode_ms": 314.66949998866767}, "total_wall_ms": 558.5637079784647, "ttft_ms": 46.956875012256205, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6911475712, "backend_memory": {"mlx_active_bytes": 6772323336, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 10036014249, "process_rss_bytes": 6911475712}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}63{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "55d7c75cb9ebbc123fa690f9", "attempt_id": "957cb1da168c", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:40.897428Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 41, "compress_ms": 147.52570795826614}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 162.3099580174312, "doc_prefill_ms": 437.422874965705, "compress_ms": 149.2385419551283, "serialize_ms": 12.80104205943644, "load_ms": 1.1120840208604932, "receiver_prefill_ms": 0.0, "query_prefill_ms": 41.776582947932184, "ttft_ms": 41.776582947932184, "decode_ms": 141.10079209785908}, "total_wall_ms": 348.03975000977516, "ttft_ms": 41.776582947932184, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6913359872, "backend_memory": {"mlx_active_bytes": 6772192264, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 10036145321, "process_rss_bytes": 6913359872}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}64{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e477b9a1d55a7ccb17c67451", "attempt_id": "4ae83690bd30", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:41.267533Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 38, "compress_ms": 129.34766698163003}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 146.5985419927165, "doc_prefill_ms": 437.422874965705, "compress_ms": 130.98404195625335, "serialize_ms": 15.367292100563645, "load_ms": 2.997333067469299, "receiver_prefill_ms": 0.0, "query_prefill_ms": 51.74429202452302, "ttft_ms": 51.74429202452302, "decode_ms": 221.70766699127853}, "total_wall_ms": 425.10620795655996, "ttft_ms": 51.74429202452302, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6915211264, "backend_memory": {"mlx_active_bytes": 6772061192, "mlx_peak_bytes": 6815839544, "mlx_cache_bytes": 10043419817, "process_rss_bytes": 6915211264}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6815839544, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}65{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "b46d4fcd3e2cacc4f4171eda", "attempt_id": "4d532bb7e02d", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:41.858815Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "blind", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 19, "compress_ms": 130.59799990151078}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 142.4080830765888, "doc_prefill_ms": 437.422874965705, "compress_ms": 130.77891699504107, "serialize_ms": 11.471665930002928, "load_ms": 0.9596669115126133, "receiver_prefill_ms": 0.0, "query_prefill_ms": 27.27637509815395, "ttft_ms": 27.27637509815395, "decode_ms": 24.090874940156937}, "total_wall_ms": 54.03216590639204, "ttft_ms": 27.27637509815395, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6917292032, "backend_memory": {"mlx_active_bytes": 6770488328, "mlx_peak_bytes": 6811006264, "mlx_cache_bytes": 10065439989, "process_rss_bytes": 6917292032}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6811006264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}66{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d97a8ce2c81cfb32ae8dc73a", "attempt_id": "745244fed267", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:41.934154Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "blind", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 19, "compress_ms": 130.59799990151078}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 142.4080830765888, "doc_prefill_ms": 437.422874965705, "compress_ms": 130.77891699504107, "serialize_ms": 11.471665930002928, "load_ms": 1.297999988310039, "receiver_prefill_ms": 0.0, "query_prefill_ms": 52.7221669908613, "ttft_ms": 52.7221669908613, "decode_ms": 41.93408403079957}, "total_wall_ms": 97.69941691774875, "ttft_ms": 52.7221669908613, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6917292032, "backend_memory": {"mlx_active_bytes": 6772061192, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 10063867125, "process_rss_bytes": 6917292032}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}67{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "1899008e558dfaa91056372a", "attempt_id": "5a1814d043d3", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:42.050982Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "blind", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 19, "compress_ms": 130.59799990151078}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 142.4080830765888, "doc_prefill_ms": 437.422874965705, "compress_ms": 130.77891699504107, "serialize_ms": 11.471665930002928, "load_ms": 1.8834170186892152, "receiver_prefill_ms": 0.0, "query_prefill_ms": 44.49391597881913, "ttft_ms": 44.49391597881913, "decode_ms": 37.344375043176115}, "total_wall_ms": 85.45716595835984, "ttft_ms": 44.49391597881913, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6917292032, "backend_memory": {"mlx_active_bytes": 6772061192, "mlx_peak_bytes": 6817002808, "mlx_cache_bytes": 10063867125, "process_rss_bytes": 6917292032}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6817002808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}68{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "8bf08c1d45fa158cabe9c701", "attempt_id": "e50e364f8914", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:42.158671Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "blind", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 19, "compress_ms": 130.59799990151078}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310651, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 142.4080830765888, "doc_prefill_ms": 437.422874965705, "compress_ms": 130.77891699504107, "serialize_ms": 11.471665930002928, "load_ms": 2.5057089515030384, "receiver_prefill_ms": 0.0, "query_prefill_ms": 35.62441701069474, "ttft_ms": 35.62441701069474, "decode_ms": 42.37329191528261}, "total_wall_ms": 82.29766692966223, "ttft_ms": 35.62441701069474, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6917292032, "backend_memory": {"mlx_active_bytes": 6770488328, "mlx_peak_bytes": 6815839544, "mlx_cache_bytes": 10065439989, "process_rss_bytes": 6917292032}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6815839544, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "5fb14777456d937b3f49bcee3ce7cc4906bf362fefc39cb2f8070a5576ea10ca", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}69{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "6644725e8322781a5ad9d3f9", "attempt_id": "1dbb2113f66c", "run_group_id": "E0_smoke_llama:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:42.263727Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "pyramid", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 36, "compress_ms": 155.98812501411885}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310621, "side_information_bytes": 12893, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 179.18008391279727, "doc_prefill_ms": 437.422874965705, "compress_ms": 157.55825000815094, "serialize_ms": 21.383208106271923, "load_ms": 3.9268749533221126, "receiver_prefill_ms": 0.0, "query_prefill_ms": 872.3779579158872, "ttft_ms": 872.3779579158872, "decode_ms": 265.98583289887756}, "total_wall_ms": 1323.2823330909014, "ttft_ms": 872.3779579158872, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6851657728, "backend_memory": {"mlx_active_bytes": 6771045384, "mlx_peak_bytes": 6839888636, "mlx_cache_bytes": 10584059665, "process_rss_bytes": 6851657728}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6839888636, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-14H-1182", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2b623b234e50bb45b3d64ddb4e5fc624d2e8d987140d846139a2f1fc5933cbce", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}70{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "bbc8aae14960288c98be5b42", "attempt_id": "1dc7fe1a4905", "run_group_id": "E0_smoke_llama:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:43.609212Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "pyramid", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 41, "compress_ms": 154.456916032359}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310619, "side_information_bytes": 12891, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 177.84450005274266, "doc_prefill_ms": 437.422874965705, "compress_ms": 156.14125004503876, "serialize_ms": 21.469792001880705, "load_ms": 1.3804170303046703, "receiver_prefill_ms": 0.0, "query_prefill_ms": 938.1341250846162, "ttft_ms": 938.1341250846162, "decode_ms": 359.9463750142604}, "total_wall_ms": 1478.9378329878673, "ttft_ms": 938.1341250846162, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6911180800, "backend_memory": {"mlx_active_bytes": 6771897352, "mlx_peak_bytes": 6844136300, "mlx_cache_bytes": 10614410077, "process_rss_bytes": 6911180800}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6844136300, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "848149b18f72edc487ee684ea55641b98ac2d675e22c288ffa0f3a81f652f67e", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}71{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "5f17d37ee4da2fa8a0c22e08", "attempt_id": "1b3d099d25e4", "run_group_id": "E0_smoke_llama:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:45.112131Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "pyramid", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 41, "compress_ms": 129.18295804411173}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310621, "side_information_bytes": 12893, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 145.54508298169822, "doc_prefill_ms": 437.422874965705, "compress_ms": 130.7377500925213, "serialize_ms": 14.53899999614805, "load_ms": 1.1376250768080354, "receiver_prefill_ms": 0.0, "query_prefill_ms": 1037.930167047307, "ttft_ms": 1037.930167047307, "decode_ms": 149.28004110697657}, "total_wall_ms": 1335.5639590881765, "ttft_ms": 1037.930167047307, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6947028992, "backend_memory": {"mlx_active_bytes": 6771274760, "mlx_peak_bytes": 6844136300, "mlx_cache_bytes": 10615032669, "process_rss_bytes": 6947028992}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6844136300, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2b623b234e50bb45b3d64ddb4e5fc624d2e8d987140d846139a2f1fc5933cbce", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}72{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "fc3835ebfc431e41ae846d63", "attempt_id": "9f4834358d02", "run_group_id": "E0_smoke_llama:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:46.471228Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "pyramid", "keep_frac": 0.25, "T": 1826, "keep": 456, "window_tokens": 38, "compress_ms": 139.58499999716878}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 52297728, "serialized_payload_bytes": 52310621, "side_information_bytes": 12893, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 156.92758397199214, "doc_prefill_ms": 437.422874965705, "compress_ms": 141.24699996318668, "serialize_ms": 15.446165925823152, "load_ms": 1.5408750623464584, "receiver_prefill_ms": 0.0, "query_prefill_ms": 883.123290957883, "ttft_ms": 883.123290957883, "decode_ms": 175.33191700931638}, "total_wall_ms": 1218.847917043604, "ttft_ms": 883.123290957883, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6989185024, "backend_memory": {"mlx_active_bytes": 6771012616, "mlx_peak_bytes": 6841477948, "mlx_cache_bytes": 10621881181, "process_rss_bytes": 6989185024}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6841477948, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2b623b234e50bb45b3d64ddb4e5fc624d2e8d987140d846139a2f1fc5933cbce", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}73{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "8effa93c0f06a54d68593ab3", "attempt_id": "b758fe81f510", "run_group_id": "E0_smoke_llama:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:47.848242Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q00_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6717502472}, "weight_precision": "bf16", "method_id": "B9", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.5, "bits": 8, "realized": {"policy": "sink_recent", "keep_frac": 0.5, "T": 1826, "keep": 913, "compress_ms": 49.07041706610471, "bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 36, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 55627264, "serialized_payload_bytes": 55654040, "side_information_bytes": 26776, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 135.99824998527765, "doc_prefill_ms": 437.422874965705, "compress_ms": 104.20516703743488, "serialize_ms": 31.361375004053116, "load_ms": 3.6407920997589827, "receiver_prefill_ms": 0.0, "query_prefill_ms": 36.66383307427168, "ttft_ms": 36.66383307427168, "decode_ms": 99.13308289833367}, "total_wall_ms": 141.15158305503428, "ttft_ms": 36.66383307427168, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 36}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 7049773056, "backend_memory": {"mlx_active_bytes": 6776222728, "mlx_peak_bytes": 6840512432, "mlx_cache_bytes": 10683583325, "process_rss_bytes": 7049773056}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6840512432, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Not found.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 0.0, "abstained": 1.0, "f1": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "f8fd9dcee318c26cba28b4b502c6b7cf62df7ec624ef536a87cffed1f586c739", "output_hash": "0802559db1375af3ff5caabba71acea1d6299f1a7fc64b6a5024f19cbd33b72f"}74{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d4eb8890a5e642f7ab6000aa", "attempt_id": "d61c0956fdb3", "run_group_id": "E0_smoke_llama:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:48.013724Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q01_single_fact", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6717502472}, "weight_precision": "bf16", "method_id": "B9", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.5, "bits": 8, "realized": {"policy": "sink_recent", "keep_frac": 0.5, "T": 1826, "keep": 913, "compress_ms": 49.07041706610471, "bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 55627264, "serialized_payload_bytes": 55654040, "side_information_bytes": 26776, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 135.99824998527765, "doc_prefill_ms": 437.422874965705, "compress_ms": 104.20516703743488, "serialize_ms": 31.361375004053116, "load_ms": 3.137958934530616, "receiver_prefill_ms": 0.0, "query_prefill_ms": 52.22874996252358, "ttft_ms": 52.22874996252358, "decode_ms": 385.93683403450996}, "total_wall_ms": 442.7836670074612, "ttft_ms": 52.22874996252358, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 7049789440, "backend_memory": {"mlx_active_bytes": 6778057736, "mlx_peak_bytes": 6836265264, "mlx_cache_bytes": 10681748317, "process_rss_bytes": 7049789440}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6836265264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C, Schefferville.", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.8571428571428571}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "f8fd9dcee318c26cba28b4b502c6b7cf62df7ec624ef536a87cffed1f586c739", "output_hash": "5280344bb130ba2ce68331d4c5deadfa47c813ecd5c007f5616e1ff44aa0daea"}75{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "2d065ff453763a5f4c3731f7", "attempt_id": "999a8ae40b7c", "run_group_id": "E0_smoke_llama:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:48.479776Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q02_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6717502472}, "weight_precision": "bf16", "method_id": "B9", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.5, "bits": 8, "realized": {"policy": "sink_recent", "keep_frac": 0.5, "T": 1826, "keep": 913, "compress_ms": 49.07041706610471, "bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 41, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 55627264, "serialized_payload_bytes": 55654040, "side_information_bytes": 26776, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 135.99824998527765, "doc_prefill_ms": 437.422874965705, "compress_ms": 104.20516703743488, "serialize_ms": 31.361375004053116, "load_ms": 6.236125016584992, "receiver_prefill_ms": 0.0, "query_prefill_ms": 53.27745899558067, "ttft_ms": 53.27745899558067, "decode_ms": 147.6881660055369}, "total_wall_ms": 208.8929999154061, "ttft_ms": 53.27745899558067, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 41}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 7049805824, "backend_memory": {"mlx_active_bytes": 6776222728, "mlx_peak_bytes": 6836265264, "mlx_cache_bytes": 10683583325, "process_rss_bytes": 7049805824}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6836265264, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "78.0424", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "f8fd9dcee318c26cba28b4b502c6b7cf62df7ec624ef536a87cffed1f586c739", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}76{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "0ed88b91f50021037e7b63fa", "attempt_id": "10349d5e5002", "run_group_id": "E0_smoke_llama:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:48.711103Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q03_exact_copy", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6717502472}, "weight_precision": "bf16", "method_id": "B9", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.5, "bits": 8, "realized": {"policy": "sink_recent", "keep_frac": 0.5, "T": 1826, "keep": 913, "compress_ms": 49.07041706610471, "bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 4, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1766, "source_tokens_receiver": 1766, "query_tokens": 38, "message_tokens": 1826, "message_utf8_bytes": 7280, "cache_tensor_bytes": 55627264, "serialized_payload_bytes": 55654040, "side_information_bytes": 26776, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 135.99824998527765, "doc_prefill_ms": 437.422874965705, "compress_ms": 104.20516703743488, "serialize_ms": 31.361375004053116, "load_ms": 2.9613750521093607, "receiver_prefill_ms": 0.0, "query_prefill_ms": 31.615874962881207, "ttft_ms": 31.615874962881207, "decode_ms": 254.29916696157306}, "total_wall_ms": 290.79958400689065, "ttft_ms": 31.615874962881207, "input_usage": {"receiver_prefix_tokens": 1826, "dense_cache_bytes": 209420288, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 7049822208, "backend_memory": {"mlx_active_bytes": 6776222728, "mlx_peak_bytes": 6837017456, "mlx_cache_bytes": 10683583325, "process_rss_bytes": 7049822208}, "peak_prefill_memory": 7112184136, "peak_decode_memory": 6837017456, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Wilhelmina Rousseau", "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "f8fd9dcee318c26cba28b4b502c6b7cf62df7ec624ef536a87cffed1f586c739", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}77{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d9b75cee222d17ea15050553", "attempt_id": "670fbabb21dc", "run_group_id": "E0_smoke_llama:A0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:49.621118Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A0", "implementation_fidelity": "custom", "compression_config": {"realized": {"note": "receiver gets no source context"}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 0, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 95, "message_tokens": 0, "message_utf8_bytes": 0, "cache_tensor_bytes": null, "serialized_payload_bytes": 0, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.00925001222640276, "decode_payload_ms": 0.0, "receiver_prefill_ms": 63.3784169331193, "ttft_ms": 51.294708042405546, "decode_ms": 1745.2523339306936}, "total_wall_ms": 1860.6292499462143, "ttft_ms": 51.294708042405546, "input_usage": {"receiver_prompt_tokens": 95}, "output_usage": {"output_tokens": 47}, "provider_cached_usage": null, "process_memory": 6802898944, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6519191004, "mlx_cache_bytes": 388432592, "process_rss_bytes": 6802898944}, "peak_prefill_memory": null, "peak_decode_memory": 6519191004, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    if rows < 0:\n        return \"Invalid number of rows\"\n    elif rows == 0:\n        return 0\n    else:\n        return rows * 100\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "TypeError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "06087c1270f1bbd4d0fcf8573af49de69f8e400a5022dd76dbda1cb50c96ba93"}78{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d78132a69217e36ae518ef36", "attempt_id": "60b3015340ec", "run_group_id": "E0_smoke_llama:A1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:51.527146Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A1", "implementation_fidelity": "custom", "compression_config": {}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 1898, "message_tokens": 1793, "message_utf8_bytes": 7944, "cache_tensor_bytes": null, "serialized_payload_bytes": 7944, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.01525005791336298, "decode_payload_ms": 0.0, "receiver_prefill_ms": 470.90358298737556, "ttft_ms": 45.215333928354084, "decode_ms": 4239.911125041544}, "total_wall_ms": 4759.3687500339, "ttft_ms": 45.215333928354084, "input_usage": {"receiver_prompt_tokens": 1898}, "output_usage": {"output_tokens": 109}, "provider_cached_usage": null, "process_memory": 6803439616, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7130223064, "mlx_cache_bytes": 869458036, "process_rss_bytes": 6803439616}, "peak_prefill_memory": null, "peak_decode_memory": 7130223064, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] == 'Sud' or r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        revenue = r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n        total += revenue\n    tax = total * 0.09975\n    total += tax\n    return round(total, 2)", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "output_hash": "6a5767437ed79776be33a6ac25bf033ba327c6bfa72d04299e74247d9629c624"}79{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e08997cc2feb77c2c937b94a", "attempt_id": "edd940dbeb54", "run_group_id": "E0_smoke_llama:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:44:56.333998Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1793}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 625, "message_tokens": 515, "message_utf8_bytes": 2185, "cache_tensor_bytes": null, "serialized_payload_bytes": 2185, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.051000017672777, "decode_payload_ms": 0.0, "receiver_prefill_ms": 181.25262495595962, "ttft_ms": 51.436083973385394, "decode_ms": 3500.617416924797}, "total_wall_ms": 3734.8810830153525, "ttft_ms": 51.436083973385394, "input_usage": {"receiver_prompt_tokens": 625}, "output_usage": {"output_tokens": 95}, "provider_cached_usage": null, "process_memory": 6804488192, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6872104472, "mlx_cache_bytes": 1329424948, "process_rss_bytes": 6804488192}, "peak_prefill_memory": null, "peak_decode_memory": 6872104472, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    rows = [row for row in rows if row['region'] != 'Sud' and row['returned'] == False and row['units'] >= 2]\n    revenue = sum(row['units'] * row['unit_price'] * (1 - row['discount_pct'] / 100) for row in rows)\n    revenue *= 1.09975\n    return round(revenue, 2)\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "2413b1319a63f1b6cd0f54d110715d18bcdb9bb119470d5b741d8c0d7ebff49c", "output_hash": "d6ad48d19daa4028fb032076e444c54864be0c65981308d25e8463d4e1012ab9"}80{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "ddf8979de181cebec5f1827f", "attempt_id": "1c2fdfbd9e2b", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:45:00.118142Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 501, "n_sentences": 6}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 604, "message_tokens": 498, "message_utf8_bytes": 1553, "cache_tensor_bytes": null, "serialized_payload_bytes": 1553, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.8467919435352087, "decode_payload_ms": 0.0, "receiver_prefill_ms": 181.44291604403406, "ttft_ms": 17.23441598005593, "decode_ms": 3289.129166980274}, "total_wall_ms": 3489.383792039007, "ttft_ms": 17.23441598005593, "input_usage": {"receiver_prompt_tokens": 604}, "output_usage": {"output_tokens": 93}, "provider_cached_usage": null, "process_memory": 6804537344, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6860832280, "mlx_cache_bytes": 1689692724, "process_rss_bytes": 6804537344}, "peak_prefill_memory": null, "peak_decode_memory": 6860832280, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total = 0\n    for r in rows:\n        if not r['returned'] and r['region'] != 'Sud' and r['units'] >= 2:\n            total += r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n    return round(total * (1 + 0.09975), 2)\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "48e30493b93ebcda2339038b160af9a3c10308d66882e2c52b74d425d38bc3ec", "output_hash": "0c7889ee8e7cfd64c00351584d70e550d93bdc704007cedf1a26ae62d0807c38"}81{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d7584634c71bf21e0d6eecd1", "attempt_id": "70b30cfac8e5", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:45:03.652108Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 512, "n_sentences": 25}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 618, "message_tokens": 512, "message_utf8_bytes": 2405, "cache_tensor_bytes": null, "serialized_payload_bytes": 2405, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.066208933480084, "decode_payload_ms": 0.0, "receiver_prefill_ms": 154.62425001896918, "ttft_ms": 39.64283294044435, "decode_ms": 3531.6903749480844}, "total_wall_ms": 3728.690249961801, "ttft_ms": 39.64283294044435, "input_usage": {"receiver_prompt_tokens": 618}, "output_usage": {"output_tokens": 98}, "provider_cached_usage": null, "process_memory": 6804602880, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6868844056, "mlx_cache_bytes": 2035198516, "process_rss_bytes": 6804602880}, "peak_prefill_memory": null, "peak_decode_memory": 6868844056, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total_revenue = 0\n    for r in rows:\n        if r['region'] != 'Sud' and r['units'] >= 2:\n            revenue = r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100)\n            total_revenue += revenue\n    tax = total_revenue * 0.09975\n    return round(total_revenue + tax, 2)", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "1b918631e0fb86c8eeb18ec2fd014d346b49af210fb4d83a68e05ad9997e0880", "output_hash": "386afcb0ebee66414bfab34fc6c287fa4764e3c3d58a941f153b33b00abcdd81"}82{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "1da1f33c7f89ce4370a99fc6", "attempt_id": "be4c357385b8", "run_group_id": "E0_smoke_llama:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:45:27.648986Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 622, "message_tokens": 512, "message_utf8_bytes": 1692, "cache_tensor_bytes": null, "serialized_payload_bytes": 1692, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20225.024625076912, "decode_payload_ms": 0.0, "receiver_prefill_ms": 150.09825001470745, "ttft_ms": 49.69558399170637, "decode_ms": 3554.733332945034}, "total_wall_ms": 3756.172207999043, "ttft_ms": 49.69558399170637, "input_usage": {"receiver_prompt_tokens": 622, "sender_input_tokens": 1927, "sender_output_tokens": 512, "sender_prefill_ms": 470.2747920528054, "sender_ttft_ms": 45.99579190835357, "sender_decode_ms": 19706.098709022626}, "output_usage": {"output_tokens": 96}, "provider_cached_usage": null, "process_memory": 6805078016, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6902070808, "mlx_cache_bytes": 3238791244, "process_rss_bytes": 6805078016}, "peak_prefill_memory": null, "peak_decode_memory": 6902070808, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total_revenue = sum(\n        (row['units'] * row['unit_price'] * (1 - row['discount_pct'] / 100)) \n        for row in rows if not row['returned'] and row['region'] != 'Sud'\n    )\n    total_revenue *= 1.09975  # Apply 9.975% tax\n    return round(total_revenue, 2)\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.8, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "ce216383da3fca3914a369e3532324ff4046ab2dfdd40ea6c9eb2f590604f161", "output_hash": "2f4e3ebeefa8303d0e566703fe6dc53c934833e5434ecb87e0da10191df67a70"}83{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "6ac733142fc67d77e042f09a", "attempt_id": "c339466219ca", "run_group_id": "E0_smoke_llama:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:45:51.782152Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 5, "unresolved_quotes": 0, "parse_ok": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 526, "message_tokens": 405, "message_utf8_bytes": 1333, "cache_tensor_bytes": null, "serialized_payload_bytes": 1333, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20329.91862494964, "decode_payload_ms": 0.0, "receiver_prefill_ms": 156.54124994762242, "ttft_ms": 29.017125023528934, "decode_ms": 2839.151250082068}, "total_wall_ms": 3026.1665829457343, "ttft_ms": 29.017125023528934, "input_usage": {"receiver_prompt_tokens": 526, "sender_input_tokens": 1957, "sender_output_tokens": 512, "sender_prefill_ms": 517.0142910210416, "sender_ttft_ms": 44.45845796726644, "sender_decode_ms": 19765.974750043824}, "output_usage": {"output_tokens": 78}, "provider_cached_usage": null, "process_memory": 6805225472, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6815022616, "mlx_cache_bytes": 4044957404, "process_rss_bytes": 6805225472}, "peak_prefill_memory": null, "peak_decode_memory": 6815022616, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        total += r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n    return round(total, 2)", "evidence_artifact": {"n_facts": 5, "unresolved_quotes": 0, "parse_ok": true}, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "f05cb6c2f9bf2f73fb1dcd0e0639f005f621b57c0475151370086fbe11e43e46", "output_hash": "20782f8c8645c8bef359993e2e9d5715b1b1a2f52039b25419491a0f11425629"}84{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "87cd1fcac8bca76f19512355", "attempt_id": "f11e12cb7f24", "run_group_id": "E0_smoke_llama:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:14.870978Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A6", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "max_fetch_bytes": 2000, "max_lookups": 6, "realized": {"n_refs": 5}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 646, "message_tokens": 540, "message_utf8_bytes": 432, "cache_tensor_bytes": null, "serialized_payload_bytes": 432, "side_information_bytes": 0, "fetched_bytes": 1265, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 20015.72812499944, "decode_payload_ms": 0.0, "receiver_prefill_ms": 220.63470794819295, "ttft_ms": 38.1325000198558, "decode_ms": 2624.743292108178}, "total_wall_ms": 2885.4318329831585, "ttft_ms": 38.1325000198558, "input_usage": {"receiver_prompt_tokens": 646, "sender_input_tokens": 1957, "sender_output_tokens": 512, "sender_prefill_ms": 533.8998339138925, "sender_ttft_ms": 45.12329096905887, "sender_decode_ms": 19434.01129206177}, "output_usage": {"output_tokens": 73}, "provider_cached_usage": null, "process_memory": 6805356544, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6884572780, "mlx_cache_bytes": 4429656304, "process_rss_bytes": 6805356544}, "peak_prefill_memory": null, "peak_decode_memory": 6884572780, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['returned'] or r['region'] == 'Sud' or r['units'] < 2:\n            continue\n        total += r['units'] * r['unit_price'] * (1 - r['discount_pct'])\n    return total", "evidence_artifact": {"lookups": 5, "fetched_bytes": 1265, "retrieved_refs": 5}, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "60edc4dbc168ed8b9a202ed54bacfb9f509e83f39b892b5d729d21f65d514068", "output_hash": "11e6c0f73669642380a1848864610e25be94ddbc954c1891d8be076ad8de2943"}85{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "612cacc00b9ad234007dcb5f", "attempt_id": "477199f5cbef", "run_group_id": "E0_smoke_llama:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:17.807723Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 6.139103554868624}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 1898, "message_tokens": 1793, "message_utf8_bytes": 7944, "cache_tensor_bytes": null, "serialized_payload_bytes": 1294, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.10441604536026716, "decode_payload_ms": 0.018208986148238182, "receiver_prefill_ms": 511.64245803374797, "ttft_ms": 22.179667023010552, "decode_ms": 4115.618415991776}, "total_wall_ms": 4653.617207892239, "ttft_ms": 22.179667023010552, "input_usage": {"receiver_prompt_tokens": 1898}, "output_usage": {"output_tokens": 109}, "provider_cached_usage": null, "process_memory": 6805389312, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7130223064, "mlx_cache_bytes": 4429656304, "process_rss_bytes": 6805389312}, "peak_prefill_memory": null, "peak_decode_memory": 7130223064, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] == 'Sud' or r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        revenue = r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n        total += revenue\n    tax = total * 0.09975\n    total += tax\n    return round(total, 2)", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "output_hash": "6a5767437ed79776be33a6ac25bf033ba327c6bfa72d04299e74247d9629c624"}86{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "0d74956e2bab90a3256d5dd2", "attempt_id": "463267041c39", "run_group_id": "E0_smoke_llama:B0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:23.058543Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6873412616}, "weight_precision": "bf16", "method_id": "B0", "implementation_fidelity": "custom", "compression_config": {"realized": {}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 212516864, "serialized_payload_bytes": 212529870, "side_information_bytes": 13006, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 547.9008340043947, "doc_prefill_ms": 491.1570419790223, "compress_ms": 5.470708012580872, "serialize_ms": 47.444583964534104, "load_ms": 4.824541974812746, "receiver_prefill_ms": 0.0, "query_prefill_ms": 73.48570798058063, "ttft_ms": 73.48570798058063, "decode_ms": 4921.614417107776}, "total_wall_ms": 5001.988791045733, "ttft_ms": 73.48570798058063, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 109}, "provider_cached_usage": null, "process_memory": 6697304064, "backend_memory": {"mlx_active_bytes": 7103706120, "mlx_peak_bytes": 7162344676, "mlx_cache_bytes": 7737651801, "process_rss_bytes": 6697304064}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 7162344676, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] == 'Sud' or r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        revenue = r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n        total += revenue\n    tax = total * 0.09975\n    total += tax\n    return round(total, 2)", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "522bffe332074bcb796f108c4005f47eec780836ba66d0efb9b603d20188ccef", "output_hash": "6a5767437ed79776be33a6ac25bf033ba327c6bfa72d04299e74247d9629c624"}87{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "74d9df9a04f363079fbb80ec", "attempt_id": "e3be8f7bcc14", "run_group_id": "E0_smoke_llama:B1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:28.490509Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6873248776}, "weight_precision": "bf16", "method_id": "B1", "implementation_fidelity": "custom", "compression_config": {"realized": {"serialize_roundtrip": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": "acd4936815db7cad", "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 212516864, "serialized_payload_bytes": 212529898, "side_information_bytes": 13034, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 373.191750026308, "doc_prefill_ms": 491.1570419790223, "compress_ms": 224.6105830417946, "serialize_ms": 148.3124999795109, "load_ms": 52.63670801650733, "receiver_prefill_ms": 0.0, "query_prefill_ms": 69.78820904623717, "ttft_ms": 69.78820904623717, "decode_ms": 4938.05329198949}, "total_wall_ms": 5062.4504160368815, "ttft_ms": 69.78820904623717, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 109}, "provider_cached_usage": null, "process_memory": 7312818176, "backend_memory": {"mlx_active_bytes": 7103542280, "mlx_peak_bytes": 7162180836, "mlx_cache_bytes": 7737815641, "process_rss_bytes": 7312818176}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 7162180836, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] == 'Sud' or r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        revenue = r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n        total += revenue\n    tax = total * 0.09975\n    total += tax\n    return round(total, 2)", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "6c67a21bc7e0c6e1c50b732378ea78ab585671684a96ad5d43a4f97a0218becf", "output_hash": "6a5767437ed79776be33a6ac25bf033ba327c6bfa72d04299e74247d9629c624"}88{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "0ebc2d3b95b910b895dba16b", "attempt_id": "edb994f3389f", "run_group_id": "E0_smoke_llama:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:33.691256Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6774158344}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 8, "realized": {"bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 112899584, "serialized_payload_bytes": 112926716, "side_information_bytes": 27132, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 89.32725002523512, "doc_prefill_ms": 491.1570419790223, "compress_ms": 38.98474993184209, "serialize_ms": 50.01079197973013, "load_ms": 6.6009999718517065, "receiver_prefill_ms": 0.0, "query_prefill_ms": 59.833958046510816, "ttft_ms": 59.833958046510816, "decode_ms": 4563.0839159712195}, "total_wall_ms": 4631.997165968642, "ttft_ms": 59.833958046510816, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 109}, "provider_cached_usage": null, "process_memory": 6839533568, "backend_memory": {"mlx_active_bytes": 6897103880, "mlx_peak_bytes": 6978903204, "mlx_cache_bytes": 9336604729, "process_rss_bytes": 6839533568}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6978903204, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] == 'Sud' or r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        revenue = r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n        total += revenue\n    tax = total * 0.09975\n    total += tax\n    return round(total, 2)", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e7a89df0990ce3437929cd0e918adccbe4bf4185ee218535531bb40e7ff755a6", "output_hash": "6a5767437ed79776be33a6ac25bf033ba327c6bfa72d04299e74247d9629c624"}89{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "2e3064455744be4e77fe8483", "attempt_id": "c03ae7602083", "run_group_id": "E0_smoke_llama:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:38.493748Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6720943112}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 4, "realized": {"bits": 4}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 59770368, "serialized_payload_bytes": 59797425, "side_information_bytes": 27057, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 122.98837502021343, "doc_prefill_ms": 491.1570419790223, "compress_ms": 90.87250009179115, "serialize_ms": 31.734207994304597, "load_ms": 4.436874995008111, "receiver_prefill_ms": 0.0, "query_prefill_ms": 45.52912502549589, "ttft_ms": 45.52912502549589, "decode_ms": 4216.681290999986}, "total_wall_ms": 4269.118999945931, "ttft_ms": 45.52912502549589, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 108}, "provider_cached_usage": null, "process_memory": 6784548864, "backend_memory": {"mlx_active_bytes": 6786085896, "mlx_peak_bytes": 6859957796, "mlx_cache_bytes": 9791039545, "process_rss_bytes": 6784548864}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6859957796, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] == 'Sud' or r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        total += r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n    tax = total * 0.09975\n    total += tax\n    return round(total, 2)\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 1.0, "pass_rate": 1.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "a2b102a2f28b534d74058a7540f8b4289c47979a55e3bc77a025b8b925612e15", "output_hash": "b9fa353e4e3364bf240cf377ea132be87c593ad7da514a543129c39d1b5e887a"}90{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "efb3addedafe4789379451f0", "attempt_id": "a52d9e1663a8", "run_group_id": "E0_smoke_llama:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:42.906098Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 1853, "keep": 463, "compress_ms": 54.579207906499505}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 53100544, "serialized_payload_bytes": 53113427, "side_information_bytes": 12883, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 88.03220803383738, "doc_prefill_ms": 491.1570419790223, "compress_ms": 54.63979090563953, "serialize_ms": 33.18020899314433, "load_ms": 2.2533750161528587, "receiver_prefill_ms": 0.0, "query_prefill_ms": 37.718416075222194, "ttft_ms": 37.718416075222194, "decode_ms": 3739.06579206232}, "total_wall_ms": 3782.042583101429, "ttft_ms": 37.718416075222194, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 100}, "provider_cached_usage": null, "process_memory": 6756958208, "backend_memory": {"mlx_active_bytes": 6783333384, "mlx_peak_bytes": 6819935468, "mlx_cache_bytes": 10784106553, "process_rss_bytes": 6756958208}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6819935468, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total_revenue = 0\n    total_cost = 0\n    for row in rows:\n        if row['revenue'] is not None and row['cost'] is not None:\n            total_revenue += row['revenue']\n            total_cost += row['cost']\n    if total_revenue > 0 and total_cost > 0:\n        return total_revenue - total_cost\n    else:\n        return 0\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "KeyError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "1fb443d7753647899bdc487cfa5d58121408e20220200eca14b96b0da3dfe5db", "output_hash": "2c3ad5303d8d1f45396dfca7af62ca9ec49b63f96cdb18c9eca1e0e6dc18ce23"}91{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "9dd21bff5ab11791cb50d7a5", "attempt_id": "5423139c786b", "run_group_id": "E0_smoke_llama:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:46.848905Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 1853, "keep": 463, "compress_ms": 67.42537498939782}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 53100544, "serialized_payload_bytes": 53113421, "side_information_bytes": 12877, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 112.62058292049915, "doc_prefill_ms": 491.1570419790223, "compress_ms": 67.4783339491114, "serialize_ms": 44.90229196380824, "load_ms": 1.1183340102434158, "receiver_prefill_ms": 0.0, "query_prefill_ms": 42.3420409206301, "ttft_ms": 42.3420409206301, "decode_ms": 11749.81549999211}, "total_wall_ms": 11798.366833943874, "ttft_ms": 42.3420409206301, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 320}, "provider_cached_usage": null, "process_memory": 6758465536, "backend_memory": {"mlx_active_bytes": 6809023496, "mlx_peak_bytes": 6833395092, "mlx_cache_bytes": 13406824505, "process_rss_bytes": 6758465536}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6833395092, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "��������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "exec:SyntaxError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "d9510e09d0ca8eb3b75b9730b22636fac2776b0f1df7ae8a095c1d0f3b1b855b", "output_hash": "96a784ac557a03befea2a2bf3c2c86086644fca8c3acf17e4a7eb949027d72ef"}92{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e43d7b02322007475f60a2f7", "attempt_id": "c1a0f1b8e31b", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:46:58.701555Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1853, "keep": 463, "window_tokens": 45, "compress_ms": 248.77916695550084}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 53100544, "serialized_payload_bytes": 53113467, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 278.2090000109747, "doc_prefill_ms": 491.1570419790223, "compress_ms": 251.14658300299197, "serialize_ms": 26.764166075736284, "load_ms": 11.841917061246932, "receiver_prefill_ms": 0.0, "query_prefill_ms": 59.18933392968029, "ttft_ms": 59.18933392968029, "decode_ms": 2920.7867920631543}, "total_wall_ms": 3273.8528749905527, "ttft_ms": 59.18933392968029, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 79}, "provider_cached_usage": null, "process_memory": 6846595072, "backend_memory": {"mlx_active_bytes": 6781498376, "mlx_peak_bytes": 6819935468, "mlx_cache_bytes": 13700950177, "process_rss_bytes": 6846595072}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6819935468, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] != 'Sud':\n            if r['units'] >= 2:\n                total += r['units'] * (r['revenue'] / 100.0) * 0.09\n    return round(total, 2)\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "KeyError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "344418aab1ee0e165ccb40fdaea3ae28b2491712429aad0877b2b70e2671f9e4", "output_hash": "8b9932740a653d50bb9a06974b348eac63c0262c73f7ab3adf800acb851a30ab"}93{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "b20154cd293d097bae3a92a0", "attempt_id": "9a6f4f817e57", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:02.238812Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6713603080}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "blind", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 1853, "keep": 463, "window_tokens": 19, "compress_ms": 187.52808298449963}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 53100544, "serialized_payload_bytes": 53113467, "side_information_bytes": 12923, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 208.3799170795828, "doc_prefill_ms": 491.1570419790223, "compress_ms": 187.91816697921604, "serialize_ms": 20.24979202542454, "load_ms": 2.7195829898118973, "receiver_prefill_ms": 0.0, "query_prefill_ms": 34.48229201603681, "ttft_ms": 34.48229201603681, "decode_ms": 4416.312083951198}, "total_wall_ms": 4461.860541952774, "ttft_ms": 34.48229201603681, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 121}, "provider_cached_usage": null, "process_memory": 6904283136, "backend_memory": {"mlx_active_bytes": 6786085896, "mlx_peak_bytes": 6819935468, "mlx_cache_bytes": 13716859117, "process_rss_bytes": 6904283136}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6819935468, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n    total = 0\n    for row in rows:\n        if row['region'] != 'Nord' and row['region'] != 'Sud':\n            if not row['returned']:\n                if row['shipped_days'] < 7:\n                    total += round((row['revenue'] - row['tax']) * 0.9, 2)\n                else:\n                    total += round((row['revenue'] - row['tax']), 2)\n            else:\n                total += round(row['revenue'], 2)\n    return total", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "KeyError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "344418aab1ee0e165ccb40fdaea3ae28b2491712429aad0877b2b70e2671f9e4", "output_hash": "cf7408abaf3fe928a524f5803f95e73959c0d9bcbfa9c73f0704bc5451e2d084"}94{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e82238acdb8214dd547b6279", "attempt_id": "bd85d54b6619", "run_group_id": "E0_smoke_llama:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:06.754008Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6660387848}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "pyramid", "keep_frac": 0.25, "T": 1853, "keep": 463, "window_tokens": 45, "compress_ms": 133.0997080076486}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 53100544, "serialized_payload_bytes": 53113430, "side_information_bytes": 12886, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 158.15033309627324, "doc_prefill_ms": 491.1570419790223, "compress_ms": 134.8713330226019, "serialize_ms": 23.0540829943493, "load_ms": 8.13025003299117, "receiver_prefill_ms": 0.0, "query_prefill_ms": 1112.2218330856413, "ttft_ms": 1112.2218330856413, "decode_ms": 11907.870208960958}, "total_wall_ms": 13189.942457946017, "ttft_ms": 1112.2218330856413, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 320}, "provider_cached_usage": null, "process_memory": 6585827328, "backend_memory": {"mlx_active_bytes": 6809187336, "mlx_peak_bytes": 6850172160, "mlx_cache_bytes": 14307397873, "process_rss_bytes": 6585827328}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6850172160, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] != 'South' and r['region'] != 'South East':\n            if r['region'] != 'South' and r['region'] != 'South East' and r['region'] != 'South West':\n                if r['region'] != 'South' and r['region'] != 'South East' and r['region'] != 'South West' and r['region'] != 'South West':\n                    if r['region'] != 'South' and r['region'] != 'South East' and r['region'] != 'South West' and r['region'] != 'South West' and r['region'] != 'South East':\n                        if r['region'] != 'South' and r['region'] != 'South East' and r['region'] != 'South West' and r['region'] != 'South West' and r['region'] != 'South East' and r['region'] != 'South West':\n                            if r['region'] != 'South' and r['region'] != 'South East' and r['region'] != 'South West' and r['region'] != 'South West' and r['region'] != 'South East' and r['region'] != 'South West' and r['region'] != 'South East':\n                                if r['region'] != 'South' and r['region'] != 'South East' and r['region'] != '", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "exec:SyntaxError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "ea03e9d2020e968c315b0fad6087e5c357cc8a44908d6c2fd52e276c88655e8b", "output_hash": "6b997410a720d0cf9c319e5fbf09df9bb348c7fa1c510c5166bedb92e152c749"}95{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "8b9af9604a2dcd74186091cb", "attempt_id": "bbf489b5d01b", "run_group_id": "E0_smoke_llama:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:20.183489Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "c8bf1a72f33c0fc6f87af8c3029f12cbff489bcb95ae36398cd522af1811a74f", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6717502472}, "weight_precision": "bf16", "method_id": "B9", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.5, "bits": 8, "realized": {"policy": "sink_recent", "keep_frac": 0.5, "T": 1853, "keep": 926, "compress_ms": 81.46916702389717, "bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 1793, "source_tokens_receiver": 1793, "query_tokens": 45, "message_tokens": 1853, "message_utf8_bytes": 7944, "cache_tensor_bytes": 56419328, "serialized_payload_bytes": 56446110, "side_information_bytes": 26782, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 181.39470904134214, "doc_prefill_ms": 491.1570419790223, "compress_ms": 127.8945830417797, "serialize_ms": 53.03558299783617, "load_ms": 3.911250038072467, "receiver_prefill_ms": 0.0, "query_prefill_ms": 59.55883290152997, "ttft_ms": 59.55883290152997, "decode_ms": 3817.130250041373}, "total_wall_ms": 3883.2200409378856, "ttft_ms": 59.55883290152997, "input_usage": {"receiver_prefix_tokens": 1853, "dense_cache_bytes": 212516864, "query_tokens": 45}, "output_usage": {"output_tokens": 96}, "provider_cached_usage": null, "process_memory": 6647808000, "backend_memory": {"mlx_active_bytes": 6786315272, "mlx_peak_bytes": 6845637732, "mlx_cache_bytes": 14337102065, "process_rss_bytes": 6647808000}, "peak_prefill_memory": 7118885336, "peak_decode_memory": 6845637732, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "```python\ndef net_revenue(rows):\n    total = 0.0\n    for r in rows:\n        if r['region'] != 'North America':\n            continue\n        if r['returned']:\n            continue\n        if r['units'] < 2:\n            continue\n        total += r['units'] * r['unit_price'] * (1 - r['discount_pct'] / 100.0)\n    return round(total, 2)\n```", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": null}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "854e85585cd5598ae69453b12fdffc0e8851d877afbd9e6047416972c1c33dd1", "output_hash": "55874831713d841ac59fbffaa1fb9d32a2ded0513cbc33751bbbec2c460f9881"}96{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "44c9f24bdb157946f705579d", "attempt_id": "1167560c78f2", "run_group_id": "E0_smoke_llama:A0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:24.953633Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A0", "implementation_fidelity": "custom", "compression_config": {"realized": {"note": "receiver gets no source context"}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 0, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 82, "message_tokens": 0, "message_utf8_bytes": 0, "cache_tensor_bytes": null, "serialized_payload_bytes": 0, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.022249994799494743, "decode_payload_ms": 0.0, "receiver_prefill_ms": 64.43300005048513, "ttft_ms": 39.59012497216463, "decode_ms": 90.72749991901219}, "total_wall_ms": 195.6150830956176, "ttft_ms": 39.59012497216463, "input_usage": {"receiver_prompt_tokens": 82}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6661668864, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6510474664, "mlx_cache_bytes": 379634332, "process_rss_bytes": 6661668864}, "peak_prefill_memory": null, "peak_decode_memory": 6510474664, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Unknown.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "9cf9f50925b2a7803c73826a305235d4215dc428721c731072a9f2c0f5d6ae5a"}97{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "77089f1b85d697b839c288d5", "attempt_id": "0f1eb80e125d", "run_group_id": "E0_smoke_llama:A1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:25.199886Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A1", "implementation_fidelity": "custom", "compression_config": {}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 3257, "message_tokens": 3165, "message_utf8_bytes": 15217, "cache_tensor_bytes": null, "serialized_payload_bytes": 15217, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.013249926269054413, "decode_payload_ms": 0.0, "receiver_prefill_ms": 926.2564160162583, "ttft_ms": 46.42666596919298, "decode_ms": 396.2914999574423}, "total_wall_ms": 1375.4641669802368, "ttft_ms": 46.42666596919298, "input_usage": {"receiver_prompt_tokens": 3257}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6662848512, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7252325440, "mlx_cache_bytes": 1671217820, "process_rss_bytes": 6662848512}, "peak_prefill_memory": null, "peak_decode_memory": 7252325440, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}98{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d69c345c47e7d7fba1448da5", "attempt_id": "3e503b976551", "run_group_id": "E0_smoke_llama:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:26.604964Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 3165}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 613, "message_tokens": 516, "message_utf8_bytes": 2753, "cache_tensor_bytes": null, "serialized_payload_bytes": 2753, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 4.279125016182661, "decode_payload_ms": 0.0, "receiver_prefill_ms": 159.79537495877594, "ttft_ms": 39.40404194872826, "decode_ms": 145.06600005552173}, "total_wall_ms": 346.0776249412447, "ttft_ms": 39.40404194872826, "input_usage": {"receiver_prompt_tokens": 613}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6664994816, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6865649128, "mlx_cache_bytes": 2124532780, "process_rss_bytes": 6664994816}, "peak_prefill_memory": null, "peak_decode_memory": 6865649128, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Face recognition approach.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "b4ebdc3f71e0de8c27d74d12c7425f1cc913cf419027bf0aa9d66ba8e1fb4ef4", "output_hash": "c91ced75830c795910278259ba26b352cb3b2bb8bcb4ece33a579acee947dd98"}99{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "885c9fa0620152363db82124", "attempt_id": "3a29092e34ab", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:26.979472Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 502, "n_sentences": 13}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 595, "message_tokens": 502, "message_utf8_bytes": 2268, "cache_tensor_bytes": null, "serialized_payload_bytes": 2268, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 4.544583964161575, "decode_payload_ms": 0.0, "receiver_prefill_ms": 175.96541601233184, "ttft_ms": 17.405707971192896, "decode_ms": 79.07637499738485}, "total_wall_ms": 274.16608296334743, "ttft_ms": 17.405707971192896, "input_usage": {"receiver_prompt_tokens": 595}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 6665322496, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6855114216, "mlx_cache_bytes": 2478935084, "process_rss_bytes": 6665322496}, "peak_prefill_memory": null, "peak_decode_memory": 6855114216, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "179bd6082f22e64b2bb3b7a0fb33d014d40dd0c0a2527b41e66dc1a8cb97a1b6", "output_hash": "65cb98a4671af923622f6d04b76c9ce50b86b153894574e55a962cb4f727b91f"}100{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "e9f57946fcf42b900e80e15d", "attempt_id": "1e532de867fd", "run_group_id": "E0_smoke_llama:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:27.278586Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 500, "n_sentences": 23}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 594, "message_tokens": 501, "message_utf8_bytes": 2495, "cache_tensor_bytes": null, "serialized_payload_bytes": 2495, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.601582975126803, "decode_payload_ms": 0.0, "receiver_prefill_ms": 174.43599994294345, "ttft_ms": 37.115958984941244, "decode_ms": 280.2286660298705}, "total_wall_ms": 494.99341601040214, "ttft_ms": 37.115958984941244, "input_usage": {"receiver_prompt_tokens": 594}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6665338880, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6855114216, "mlx_cache_bytes": 2478935084, "process_rss_bytes": 6665338880}, "peak_prefill_memory": null, "peak_decode_memory": 6855114216, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.4615384615384615, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "785023803d7f2c38c80debcdc8309ffa1c94e3c99227c52a36e7e66d830d2d9e", "output_hash": "62be2a82b9b81284ad4ad3e5bf7aa56d7866450a753eeed5461895891c88b2e9"}101{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "d65b20dcb306c0140c6cbee5", "attempt_id": "9a679b545f77", "run_group_id": "E0_smoke_llama:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:47:49.999549Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 609, "message_tokens": 512, "message_utf8_bytes": 2544, "cache_tensor_bytes": null, "serialized_payload_bytes": 2544, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 22201.99812494684, "decode_payload_ms": 0.0, "receiver_prefill_ms": 163.27533405274153, "ttft_ms": 33.47712499089539, "decode_ms": 271.6693750116974}, "total_wall_ms": 470.18758300691843, "ttft_ms": 33.47712499089539, "input_usage": {"receiver_prompt_tokens": 609, "sender_input_tokens": 3299, "sender_output_tokens": 512, "sender_prefill_ms": 847.9583340231329, "sender_ttft_ms": 43.58004208188504, "sender_decode_ms": 21307.24516592454}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6666305536, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6863125992, "mlx_cache_bytes": 4080176172, "process_rss_bytes": 6666305536}, "peak_prefill_memory": null, "peak_decode_memory": 6863125992, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.4615384615384615, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "a92a3840adade198f1f17e7bef7cf09fa2fc2a50f1fe33c73523c5400c06ace4", "output_hash": "62be2a82b9b81284ad4ad3e5bf7aa56d7866450a753eeed5461895891c88b2e9"}102{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "6bda13bb6dac6b19c1f79a9b", "attempt_id": "7752cbe610ee", "run_group_id": "E0_smoke_llama:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:12.350377Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 488, "message_tokens": 380, "message_utf8_bytes": 1257, "cache_tensor_bytes": null, "serialized_payload_bytes": 1257, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 21855.362500064075, "decode_payload_ms": 0.0, "receiver_prefill_ms": 165.4428340261802, "ttft_ms": 23.285583942197263, "decode_ms": 217.3186249565333}, "total_wall_ms": 407.3195829987526, "ttft_ms": 23.285583942197263, "input_usage": {"receiver_prompt_tokens": 488, "sender_input_tokens": 3329, "sender_output_tokens": 512, "sender_prefill_ms": 949.9937500804663, "sender_ttft_ms": 55.828875047154725, "sender_decode_ms": 20846.271000104025}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6667468800, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6764788824, "mlx_cache_bytes": 4628761644, "process_rss_bytes": 6667468800}, "peak_prefill_memory": null, "peak_decode_memory": 6764788824, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Ghost-VLAD model", "evidence_artifact": {"n_facts": 9, "unresolved_quotes": 0, "parse_ok": true}, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "8872c1ee69cdc942cca378c38034ceb53ada658177b2b563192861748b58062e", "output_hash": "158b135e4f20814888b9161908fdd8705a04091174ac37b666dd11ae3cc5a4a7"}103{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "93d51aaa500866412d07fe2f", "attempt_id": "d97b679051fc", "run_group_id": "E0_smoke_llama:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:34.927724Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A6", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "max_fetch_bytes": 2000, "max_lookups": 6, "realized": {"n_refs": 9}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 858, "message_tokens": 765, "message_utf8_bytes": 830, "cache_tensor_bytes": null, "serialized_payload_bytes": 830, "side_information_bytes": 0, "fetched_bytes": 1660, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 22146.301458007656, "decode_payload_ms": 0.0, "receiver_prefill_ms": 227.50466701108962, "ttft_ms": 43.446708004921675, "decode_ms": 36.40404099132866}, "total_wall_ms": 309.42874995525926, "ttft_ms": 43.446708004921675, "input_usage": {"receiver_prompt_tokens": 858, "sender_input_tokens": 3329, "sender_output_tokens": 512, "sender_prefill_ms": 905.3275000769645, "sender_ttft_ms": 68.31662508193403, "sender_decode_ms": 21169.65887497645}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6667829248, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 6933646424, "mlx_cache_bytes": 5173365804, "process_rss_bytes": 6667829248}, "peak_prefill_memory": null, "peak_decode_memory": 6933646424, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1660, "retrieved_refs": 6}, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "93bbce05a459c3fb41371ce4ff355223722554545cc4dac340f74b2cd6065f19", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}104{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "c1a6e4b7f5c4a44097a4f3f4", "attempt_id": "9c9d37ae535b", "run_group_id": "E0_smoke_llama:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:35.260676Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6425506824}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 2.8798258894776683}}, "question_access": "none", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 3257, "message_tokens": 3165, "message_utf8_bytes": 15217, "cache_tensor_bytes": null, "serialized_payload_bytes": 5284, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.15029101632535458, "decode_payload_ms": 0.028749927878379822, "receiver_prefill_ms": 884.1438330709934, "ttft_ms": 55.560875101946294, "decode_ms": 462.33312506228685}, "total_wall_ms": 1407.4600409949198, "ttft_ms": 55.560875101946294, "input_usage": {"receiver_prompt_tokens": 3257}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6668009472, "backend_memory": {"mlx_active_bytes": 6425506824, "mlx_peak_bytes": 7252325440, "mlx_cache_bytes": 5173365804, "process_rss_bytes": 6668009472}, "peak_prefill_memory": null, "peak_decode_memory": 7252325440, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}105{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "abd8f72d5ebf8d2a9042c92c", "attempt_id": "f44c40de4bc9", "run_group_id": "E0_smoke_llama:B0", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:37.563174Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 7177860104}, "weight_precision": "bf16", "method_id": "B0", "implementation_fidelity": "custom", "compression_config": {"realized": {}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 369868800, "serialized_payload_bytes": 369881830, "side_information_bytes": 13030, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 872.6028749952093, "doc_prefill_ms": 768.3387080905959, "compress_ms": 8.387916954234242, "serialize_ms": 90.83100000862032, "load_ms": 7.476166938431561, "receiver_prefill_ms": 0.0, "query_prefill_ms": 65.79979206435382, "ttft_ms": 65.79979206435382, "decode_ms": 491.8956670444459}, "total_wall_ms": 567.7750420290977, "ttft_ms": 65.79979206435382, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 7408992256, "backend_memory": {"mlx_active_bytes": 7553119240, "mlx_peak_bytes": 7646950584, "mlx_cache_bytes": 6101340461, "process_rss_bytes": 7408992256}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7646950584, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "8ee5cf8383bacbbd8af5e34008644b55e21053faeefa305d0b6c29ed3b5977a7", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}106{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "fde7a2e940724dc99dfc4dcd", "attempt_id": "41e64241eecd", "run_group_id": "E0_smoke_llama:B1", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:38.273477Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 7177860104}, "weight_precision": "bf16", "method_id": "B1", "implementation_fidelity": "custom", "compression_config": {"realized": {"serialize_roundtrip": true}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": "95737b617c283ebf", "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 369868800, "serialized_payload_bytes": 369881858, "side_information_bytes": 13058, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 117.73079202976078, "doc_prefill_ms": 768.3387080905959, "compress_ms": 7.5602500000968575, "serialize_ms": 109.97679200954735, "load_ms": 49.44625007919967, "receiver_prefill_ms": 0.0, "query_prefill_ms": 58.2056250423193, "ttft_ms": 58.2056250423193, "decode_ms": 428.46745892893523}, "total_wall_ms": 538.6375420494005, "ttft_ms": 58.2056250423193, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 7779844096, "backend_memory": {"mlx_active_bytes": 7553119240, "mlx_peak_bytes": 7646950584, "mlx_cache_bytes": 6101340461, "process_rss_bytes": 7779844096}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7646950584, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "06d4d3fe4804f01b770c9587580d9b01847dda9cbf57b892fc812328806ca6c5", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}107{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "b9564e291f64162d9ab2f97e", "attempt_id": "d5b9da4adb6f", "run_group_id": "E0_smoke_llama:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:38.939579Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 7005369352}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 8, "realized": {"bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 196492800, "serialized_payload_bytes": 196520056, "side_information_bytes": 27256, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 103.859500028193, "doc_prefill_ms": 768.3387080905959, "compress_ms": 52.26229201070964, "serialize_ms": 51.22220900375396, "load_ms": 6.104291067458689, "receiver_prefill_ms": 0.0, "query_prefill_ms": 175.92745902948081, "ttft_ms": 175.92745902948081, "decode_ms": 421.5575830312446}, "total_wall_ms": 606.0640841023996, "ttft_ms": 175.92745902948081, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 7977893888, "backend_memory": {"mlx_active_bytes": 7206302728, "mlx_peak_bytes": 7295243472, "mlx_cache_bytes": 7318172845, "process_rss_bytes": 7977893888}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7295243472, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "917cb67928b6971fc0158a2501ad4fe2a4db28dc15dec6a692c9b208d7a1f029", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}108{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "2061cab6ef742a32c401c02b", "attempt_id": "e0985f83fa6c", "run_group_id": "E0_smoke_llama:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:39.662899Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6912701448}, "weight_precision": "bf16", "method_id": "B2", "implementation_fidelity": "custom", "compression_config": {"bits": 4, "realized": {"bits": 4}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 104025600, "serialized_payload_bytes": 104052706, "side_information_bytes": 27106, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 91.90604102332145, "doc_prefill_ms": 768.3387080905959, "compress_ms": 50.19495799206197, "serialize_ms": 41.365165961906314, "load_ms": 4.855667008087039, "receiver_prefill_ms": 0.0, "query_prefill_ms": 145.75187501031905, "ttft_ms": 145.75187501031905, "decode_ms": 435.59229106176645}, "total_wall_ms": 588.821041979827, "ttft_ms": 145.75187501031905, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 8187625472, "backend_memory": {"mlx_active_bytes": 7020049416, "mlx_peak_bytes": 7101129960, "mlx_cache_bytes": 7934092589, "process_rss_bytes": 8187625472}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7101129960, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "089268d279957f99a33245ea777c87a7dfb5186fb242114d885d00081725b7d2", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}109{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "4d3758fd158d22e9937a76e5", "attempt_id": "d588d2ad483d", "run_group_id": "E0_smoke_llama:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:40.340883Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6899856392}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 3225, "keep": 806, "compress_ms": 27.757166884839535}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 92438528, "serialized_payload_bytes": 92451421, "side_information_bytes": 12893, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 64.23241703305393, "doc_prefill_ms": 768.3387080905959, "compress_ms": 27.796707930974662, "serialize_ms": 36.2354579847306, "load_ms": 1.9377500284463167, "receiver_prefill_ms": 0.0, "query_prefill_ms": 35.60299996752292, "ttft_ms": 35.60299996752292, "decode_ms": 138.23416701052338}, "total_wall_ms": 179.83395792543888, "ttft_ms": 35.60299996752292, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 8184594432, "backend_memory": {"mlx_active_bytes": 6997111816, "mlx_peak_bytes": 7041660088, "mlx_cache_bytes": 8174708013, "process_rss_bytes": 8184594432}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7041660088, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Face recognition technique", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "cfd45f7f52bfb277d73e198d2a330de3371aa41aec2f77f0731c89ea088e7299", "output_hash": "adc705b949def2e4833f11eabfdb5cc131f5c7801bcaf695f325f05dadc1903f"}110{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "3c1b141113418107b8e9cf68", "attempt_id": "84d644ccfa36", "run_group_id": "E0_smoke_llama:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:40.618881Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6899856392}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 3225, "keep": 806, "compress_ms": 29.710708069615066}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 92438528, "serialized_payload_bytes": 92451416, "side_information_bytes": 12888, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 71.83591590728611, "doc_prefill_ms": 768.3387080905959, "compress_ms": 29.746290994808078, "serialize_ms": 41.88670904841274, "load_ms": 3.7346669705584645, "receiver_prefill_ms": 0.0, "query_prefill_ms": 49.082000041380525, "ttft_ms": 49.082000041380525, "decode_ms": 202.58479204494506}, "total_wall_ms": 257.95587501488626, "ttft_ms": 49.082000041380525, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 8278245376, "backend_memory": {"mlx_active_bytes": 6997111816, "mlx_peak_bytes": 7041660088, "mlx_cache_bytes": 8199021869, "process_rss_bytes": 8278245376}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7041660088, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Extension of NetVLAD", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.4615384615384615, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "bfc5aad5ad47b143ff2ae900af44295c81902b72194b44a72a356052e358fbfb", "output_hash": "8f140fbbbd872bb79f452c7a3e155d08de9d9b3df5f5ad753e80b4846eb8431c"}111{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "ef70aa1aacd6d3a3581298dd", "attempt_id": "c83874a71bb5", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:40.903176Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6807188488}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 3225, "keep": 806, "window_tokens": 32, "compress_ms": 166.13045800477266}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 92438528, "serialized_payload_bytes": 92451461, "side_information_bytes": 12933, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 196.04720908682793, "doc_prefill_ms": 768.3387080905959, "compress_ms": 168.97325008176267, "serialize_ms": 26.782125001773238, "load_ms": 1.180332968942821, "receiver_prefill_ms": 0.0, "query_prefill_ms": 59.43370796740055, "ttft_ms": 59.43370796740055, "decode_ms": 406.5587919903919}, "total_wall_ms": 666.2564580328763, "ttft_ms": 59.43370796740055, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 8287830016, "backend_memory": {"mlx_active_bytes": 6997111816, "mlx_peak_bytes": 7041660088, "mlx_cache_bytes": 8623891861, "process_rss_bytes": 8287830016}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7041660088, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of NetVLAD for face recognition.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.37499999999999994, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "abd1bbad98ec9628f9d26690ae31cf6986bf28f92f185dd733e97b813a4d72f5", "output_hash": "9816a4414797f3bf80cbc9ca7be903c241ad826f66b9aad1df5d1829dbe8b0b9"}112{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "3ad4f21970c0d4d1b502d40a", "attempt_id": "8d6d9f43c4d7", "run_group_id": "E0_smoke_llama:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:41.752781Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6899856392}, "weight_precision": "bf16", "method_id": "B5", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "blind", "realized": {"policy": "attention", "keep_frac": 0.25, "T": 3225, "keep": 806, "window_tokens": 19, "compress_ms": 137.13216700125486}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 92438528, "serialized_payload_bytes": 92451461, "side_information_bytes": 12933, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 158.06108398828655, "doc_prefill_ms": 768.3387080905959, "compress_ms": 137.29495892766863, "serialize_ms": 20.584333105944097, "load_ms": 1.8588330131024122, "receiver_prefill_ms": 0.0, "query_prefill_ms": 47.956917085684836, "ttft_ms": 47.956917085684836, "decode_ms": 247.80429096426815}, "total_wall_ms": 300.38979195524007, "ttft_ms": 47.956917085684836, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 8287911936, "backend_memory": {"mlx_active_bytes": 6997111816, "mlx_peak_bytes": 7041660088, "mlx_cache_bytes": 8646894997, "process_rss_bytes": 8287911936}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7041660088, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Ghost-VLAD pooling method.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "abd1bbad98ec9628f9d26690ae31cf6986bf28f92f185dd733e97b813a4d72f5", "output_hash": "bb4768fc890447a743a28d413f4b9165fc5b5887a6b9e7f30a3648c31602aa4e"}113{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "172f04f7b6a5ab7ec4d24438", "attempt_id": "db4912d84e35", "run_group_id": "E0_smoke_llama:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:42.082088Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6807188488}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware", "realized": {"policy": "pyramid", "keep_frac": 0.25, "T": 3225, "keep": 806, "window_tokens": 32, "compress_ms": 164.159334031865}}, "question_access": "aware", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 92438528, "serialized_payload_bytes": 92451489, "side_information_bytes": 12961, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 193.5198330320418, "doc_prefill_ms": 768.3387080905959, "compress_ms": 166.54054203536361, "serialize_ms": 26.766416965983808, "load_ms": 11.041625053621829, "receiver_prefill_ms": 0.0, "query_prefill_ms": 1063.2581249810755, "ttft_ms": 1063.2581249810755, "decode_ms": 370.9792080335319}, "total_wall_ms": 1642.524458002299, "ttft_ms": 1063.2581249810755, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 7598637056, "backend_memory": {"mlx_active_bytes": 6997996552, "mlx_peak_bytes": 7121915044, "mlx_cache_bytes": 10613161933, "process_rss_bytes": 7598637056}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7121915044, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of the NetVLAD approach.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.4285714285714285, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "c839577fd550993df17a39b7857d9ea072aa21bed74cdcc84d8e1230292586f1", "output_hash": "35066d4391427300133fbec39fa550f39d33b0cf8700f5300bcb8b4c8f852d68"}114{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke_llama", "trial_id": "8cddeb96fd95a16ceee43ed2", "attempt_id": "d9a564f246f6", "run_group_id": "E0_smoke_llama:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "c97f7990508e79bc75587da79eb05cc9fc689fb427f68881c11b47633ac78b50", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:48:43.936211Z", "task_family": "public_qasper", "document_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "document_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "question_id": "q00", "split": "dev", "cluster_id": "lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084", "sender_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"sender": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763", "receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6907196424}, "weight_precision": "bf16", "method_id": "B9", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.5, "bits": 8, "realized": {"policy": "sink_recent", "keep_frac": 0.5, "T": 3225, "keep": 1612, "compress_ms": 68.63458303268999, "bits": 8}}, "question_access": "blind", "topology": "single_handoff", "handoff_index": 1, "reuse_count": 1, "cache_hit": true, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": 3165, "source_tokens_receiver": 3165, "query_tokens": 32, "message_tokens": 3225, "message_utf8_bytes": 15217, "cache_tensor_bytes": 98215936, "serialized_payload_bytes": 98243143, "side_information_bytes": 27207, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 183.25416697189212, "doc_prefill_ms": 768.3387080905959, "compress_ms": 120.4705840209499, "serialize_ms": 62.467875075526536, "load_ms": 8.85850004851818, "receiver_prefill_ms": 0.0, "query_prefill_ms": 59.84200001694262, "ttft_ms": 59.84200001694262, "decode_ms": 125.22991700097919}, "total_wall_ms": 196.51483302004635, "ttft_ms": 59.84200001694262, "input_usage": {"receiver_prefix_tokens": 3225, "dense_cache_bytes": 369868800, "query_tokens": 32}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 7699415040, "backend_memory": {"mlx_active_bytes": 7009039368, "mlx_peak_bytes": 7073338576, "mlx_cache_bytes": 10619427069, "process_rss_bytes": 7699415040}, "peak_prefill_memory": 7242626112, "peak_decode_memory": 7073338576, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Face recognition technique", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.0, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke_llama.log", "payload_hash": "74c04b99846bb7fc6b88c66a3c6d2a9cba3987192872977c7c90b213d45ae0f0", "output_hash": "adc705b949def2e4833f11eabfdb5cc131f5c7801bcaf695f325f05dadc1903f"}115