1{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "4146ad264bc41966c53c6c2a", "attempt_id": "82062e437bf8", "run_group_id": "E0_smoke:A0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:34.723314Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 64, "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": 0.007208087481558323, "decode_payload_ms": 0.0, "receiver_prefill_ms": 704.172583995387, "ttft_ms": 111.37787497136742, "decode_ms": 52.97070904634893}, "total_wall_ms": 874.542957986705, "ttft_ms": 111.37787497136742, "input_usage": {"receiver_prompt_tokens": 64}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6598574080, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6221848952, "mlx_cache_bytes": 52763976, "process_rss_bytes": 6598574080}, "peak_prefill_memory": null, "peak_decode_memory": 6221848952, "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.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}2{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "aea3215c06f1768bed89e0e4", "attempt_id": "eb2cf16a0cb8", "run_group_id": "E0_smoke:A0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:35.621639Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 70, "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": 0.007208087481558323, "decode_payload_ms": 0.0, "receiver_prefill_ms": 714.0282499603927, "ttft_ms": 16.376250074245036, "decode_ms": 20.608124905265868}, "total_wall_ms": 751.6555410111323, "ttft_ms": 16.376250074245036, "input_usage": {"receiver_prompt_tokens": 70}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6599262208, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6243951240, "mlx_cache_bytes": 117497160, "process_rss_bytes": 6599262208}, "peak_prefill_memory": null, "peak_decode_memory": 6243951240, "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.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}3{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "19cb26d87f4f6c06f22133ab", "attempt_id": "f2ace8e95ee4", "run_group_id": "E0_smoke:A0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:36.394852Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 70, "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": 0.007208087481558323, "decode_payload_ms": 0.0, "receiver_prefill_ms": 37.55691600963473, "ttft_ms": 13.19108298048377, "decode_ms": 21.748042083345354}, "total_wall_ms": 73.1698750751093, "ttft_ms": 13.19108298048377, "input_usage": {"receiver_prompt_tokens": 70}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6599311360, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6243951240, "mlx_cache_bytes": 117497160, "process_rss_bytes": 6599311360}, "peak_prefill_memory": null, "peak_decode_memory": 6243951240, "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.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}4{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "55040e08a970feabf0c8dfb0", "attempt_id": "d1f4af490c6e", "run_group_id": "E0_smoke:A0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:36.488122Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 67, "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": 0.007208087481558323, "decode_payload_ms": 0.0, "receiver_prefill_ms": 33.89208402950317, "ttft_ms": 13.485999894328415, "decode_ms": 13.414166984148324}, "total_wall_ms": 61.261874972842634, "ttft_ms": 13.485999894328415, "input_usage": {"receiver_prompt_tokens": 67}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6599344128, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6245671560, "mlx_cache_bytes": 162520392, "process_rss_bytes": 6599344128}, "peak_prefill_memory": null, "peak_decode_memory": 6245671560, "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.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}5{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "b5a907e579d3ba6be2a73c6e", "attempt_id": "8a37232cf18e", "run_group_id": "E0_smoke:A1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:36.569588Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2045, "message_tokens": 1971, "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": 0.013124896213412285, "decode_payload_ms": 0.0, "receiver_prefill_ms": 268.84245907422155, "ttft_ms": 40.27962498366833, "decode_ms": 220.9290829487145}, "total_wall_ms": 533.2459580386057, "ttft_ms": 40.27962498366833, "input_usage": {"receiver_prompt_tokens": 2045}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6599606272, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7061651504, "mlx_cache_bytes": 1144192312, "process_rss_bytes": 6599606272}, "peak_prefill_memory": null, "peak_decode_memory": 7061651504, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}6{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c3b51441b577e5cf867a711f", "attempt_id": "899cf42e0e05", "run_group_id": "E0_smoke:A1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:37.123667Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2051, "message_tokens": 1971, "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": 0.013124896213412285, "decode_payload_ms": 0.0, "receiver_prefill_ms": 660.5961669702083, "ttft_ms": 19.695666036568582, "decode_ms": 177.584792021662}, "total_wall_ms": 861.3416670123115, "ttft_ms": 19.695666036568582, "input_usage": {"receiver_prompt_tokens": 2051}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6600179712, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7054786612, "mlx_cache_bytes": 1950271808, "process_rss_bytes": 6600179712}, "peak_prefill_memory": null, "peak_decode_memory": 7054786612, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}7{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "768e16d34f259a76a877fe66", "attempt_id": "56658b192495", "run_group_id": "E0_smoke:A1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:38.004317Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2051, "message_tokens": 1971, "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": 0.013124896213412285, "decode_payload_ms": 0.0, "receiver_prefill_ms": 270.62474994454533, "ttft_ms": 13.784875045530498, "decode_ms": 137.02083297539502}, "total_wall_ms": 424.99795800540596, "ttft_ms": 13.784875045530498, "input_usage": {"receiver_prompt_tokens": 2051}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6600196096, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7054786612, "mlx_cache_bytes": 1950271808, "process_rss_bytes": 6600196096}, "peak_prefill_memory": null, "peak_decode_memory": 7054786612, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}8{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "bf2332e5ea92995e70a698fa", "attempt_id": "b65f009d2226", "run_group_id": "E0_smoke:A1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:38.450459Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2048, "message_tokens": 1971, "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": 0.013124896213412285, "decode_payload_ms": 0.0, "receiver_prefill_ms": 270.55058302357793, "ttft_ms": 16.825958038680255, "decode_ms": 115.82745797932148}, "total_wall_ms": 406.5157499862835, "ttft_ms": 16.825958038680255, "input_usage": {"receiver_prompt_tokens": 2048}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6600228864, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7063175232, "mlx_cache_bytes": 1950271808, "process_rss_bytes": 6600228864}, "peak_prefill_memory": null, "peak_decode_memory": 7063175232, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}9{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "680a1696a501a9abbd246fe8", "attempt_id": "7116fac29eef", "run_group_id": "E0_smoke:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:38.879959Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1971}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 595, "message_tokens": 516, "message_utf8_bytes": 1775, "cache_tensor_bytes": null, "serialized_payload_bytes": 1775, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.7649579094722867, "decode_payload_ms": 0.0, "receiver_prefill_ms": 98.40858390089124, "ttft_ms": 14.796082978136837, "decode_ms": 28.082999982871115}, "total_wall_ms": 142.88441697135568, "ttft_ms": 14.796082978136837, "input_usage": {"receiver_prompt_tokens": 595}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6600474624, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6566965336, "mlx_cache_bytes": 2345519424, "process_rss_bytes": 6600474624}, "peak_prefill_memory": null, "peak_decode_memory": 6566965336, "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.log", "payload_hash": "d2f5c011b1bc04cde05fd53e8eda8cce4f41dc708c77ba1e0b49bd3fb47d3958", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}10{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "7d73c49fb6ea7ba015627e4f", "attempt_id": "c1a192f5a6d1", "run_group_id": "E0_smoke:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:39.046782Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1971}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 601, "message_tokens": 516, "message_utf8_bytes": 1775, "cache_tensor_bytes": null, "serialized_payload_bytes": 1775, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.7649579094722867, "decode_payload_ms": 0.0, "receiver_prefill_ms": 96.09833301510662, "ttft_ms": 21.742249955423176, "decode_ms": 187.9519580397755}, "total_wall_ms": 307.20599996857345, "ttft_ms": 21.742249955423176, "input_usage": {"receiver_prompt_tokens": 601}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6600540160, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6567653464, "mlx_cache_bytes": 2695874880, "process_rss_bytes": 6600540160}, "peak_prefill_memory": null, "peak_decode_memory": 6567653464, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Lot 61-C in Schefferville", "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.log", "payload_hash": "d2f5c011b1bc04cde05fd53e8eda8cce4f41dc708c77ba1e0b49bd3fb47d3958", "output_hash": "3491362e6ed6bb557ea2c25e29286d6fdbd0a0a36995d38446eddfd8450e097c"}11{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "610ae196b469cb2b3d8c27c1", "attempt_id": "ee38ce288b68", "run_group_id": "E0_smoke:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:39.376514Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1971}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 601, "message_tokens": 516, "message_utf8_bytes": 1775, "cache_tensor_bytes": null, "serialized_payload_bytes": 1775, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.7649579094722867, "decode_payload_ms": 0.0, "receiver_prefill_ms": 105.36962503101677, "ttft_ms": 16.225583967752755, "decode_ms": 25.455374969169497}, "total_wall_ms": 148.63470802083611, "ttft_ms": 16.225583967752755, "input_usage": {"receiver_prompt_tokens": 601}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6600556544, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6567653464, "mlx_cache_bytes": 2695874880, "process_rss_bytes": 6600556544}, "peak_prefill_memory": null, "peak_decode_memory": 6567653464, "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.log", "payload_hash": "d2f5c011b1bc04cde05fd53e8eda8cce4f41dc708c77ba1e0b49bd3fb47d3958", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}12{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "17e7e463c5868b352e0a43d6", "attempt_id": "b1a1be404836", "run_group_id": "E0_smoke:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:39.546022Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1971}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 598, "message_tokens": 516, "message_utf8_bytes": 1775, "cache_tensor_bytes": null, "serialized_payload_bytes": 1775, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.7649579094722867, "decode_payload_ms": 0.0, "receiver_prefill_ms": 95.2667499659583, "ttft_ms": 23.73883395921439, "decode_ms": 22.320416988804936}, "total_wall_ms": 142.76070904452354, "ttft_ms": 23.73883395921439, "input_usage": {"receiver_prompt_tokens": 598}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6600654848, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6568931416, "mlx_cache_bytes": 2941831488, "process_rss_bytes": 6600654848}, "peak_prefill_memory": null, "peak_decode_memory": 6568931416, "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.log", "payload_hash": "d2f5c011b1bc04cde05fd53e8eda8cce4f41dc708c77ba1e0b49bd3fb47d3958", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}13{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "4e1e37e59f7beee987b1ca29", "attempt_id": "ff5f09c23dec", "run_group_id": "E0_smoke:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:39.712474Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 508, "n_sentences": 14}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 583, "message_tokens": 508, "message_utf8_bytes": 1231, "cache_tensor_bytes": null, "serialized_payload_bytes": 1231, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.582667046226561, "decode_payload_ms": 0.0, "receiver_prefill_ms": 92.41145791020244, "ttft_ms": 21.56287501566112, "decode_ms": 15.641708974726498}, "total_wall_ms": 130.70283306296915, "ttft_ms": 21.56287501566112, "input_usage": {"receiver_prompt_tokens": 583}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6600769536, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6559592536, "mlx_cache_bytes": 3296414016, "process_rss_bytes": 6600769536}, "peak_prefill_memory": null, "peak_decode_memory": 6559592536, "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.log", "payload_hash": "386755a6041624133cae3e906274e1dbaa1ac732378d43f385e9581f5c9aba44", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}14{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "12de52603bea6e9934f5b230", "attempt_id": "71f4c1fad7f1", "run_group_id": "E0_smoke:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:39.862544Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 508, "n_sentences": 14}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 589, "message_tokens": 508, "message_utf8_bytes": 1231, "cache_tensor_bytes": null, "serialized_payload_bytes": 1231, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.582667046226561, "decode_payload_ms": 0.0, "receiver_prefill_ms": 93.39258295949548, "ttft_ms": 23.743500001728535, "decode_ms": 20.554958027787507}, "total_wall_ms": 139.25754197407514, "ttft_ms": 23.743500001728535, "input_usage": {"receiver_prompt_tokens": 589}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6600835072, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6563131480, "mlx_cache_bytes": 3639789888, "process_rss_bytes": 6600835072}, "peak_prefill_memory": null, "peak_decode_memory": 6563131480, "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.log", "payload_hash": "386755a6041624133cae3e906274e1dbaa1ac732378d43f385e9581f5c9aba44", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}15{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a5db44064cdbeec9c2302287", "attempt_id": "6e66fa4e2bab", "run_group_id": "E0_smoke:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:40.022475Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 508, "n_sentences": 14}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 589, "message_tokens": 508, "message_utf8_bytes": 1231, "cache_tensor_bytes": null, "serialized_payload_bytes": 1231, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.582667046226561, "decode_payload_ms": 0.0, "receiver_prefill_ms": 92.00699999928474, "ttft_ms": 21.959374891594052, "decode_ms": 176.00433400366455}, "total_wall_ms": 291.4037499576807, "ttft_ms": 21.959374891594052, "input_usage": {"receiver_prompt_tokens": 589}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6600835072, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6563131480, "mlx_cache_bytes": 3639789888, "process_rss_bytes": 6600835072}, "peak_prefill_memory": null, "peak_decode_memory": 6563131480, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "6,068,030", "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.log", "payload_hash": "386755a6041624133cae3e906274e1dbaa1ac732378d43f385e9581f5c9aba44", "output_hash": "d1643b9a5cdbde943cffa17e0bd2ea3a63bd11939d2b80e5c53fe3f1d39a8e26"}16{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "042990c4fab2319bcaa2df57", "attempt_id": "6f2aeaacc7b7", "run_group_id": "E0_smoke:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:40.333810Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 508, "n_sentences": 14}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 586, "message_tokens": 508, "message_utf8_bytes": 1231, "cache_tensor_bytes": null, "serialized_payload_bytes": 1231, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.582667046226561, "decode_payload_ms": 0.0, "receiver_prefill_ms": 88.77624990418553, "ttft_ms": 21.344291046261787, "decode_ms": 102.45566698722541}, "total_wall_ms": 213.67987501434982, "ttft_ms": 21.344291046261787, "input_usage": {"receiver_prompt_tokens": 586}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6600851456, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6561951832, "mlx_cache_bytes": 3880831296, "process_rss_bytes": 6600851456}, "peak_prefill_memory": null, "peak_decode_memory": 6561951832, "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.log", "payload_hash": "386755a6041624133cae3e906274e1dbaa1ac732378d43f385e9581f5c9aba44", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}17{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "8c5856e58a4069eedbaf6563", "attempt_id": "c4a0944c90e1", "run_group_id": "E0_smoke:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:40.568489Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 24}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 587, "message_tokens": 512, "message_utf8_bytes": 1358, "cache_tensor_bytes": null, "serialized_payload_bytes": 1358, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.1340419296175241, "decode_payload_ms": 0.0, "receiver_prefill_ms": 89.60275002755225, "ttft_ms": 20.019917050376534, "decode_ms": 194.40183392725885}, "total_wall_ms": 306.6186250653118, "ttft_ms": 20.019917050376534, "input_usage": {"receiver_prompt_tokens": 587}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6600900608, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6562246744, "mlx_cache_bytes": 4122167616, "process_rss_bytes": 6600900608}, "peak_prefill_memory": null, "peak_decode_memory": 6562246744, "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.log", "payload_hash": "9c6f1d7683c25b99905915cd50af46f8624d0e046d60064afa1f8536d2053414", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}18{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "d2d4bfa6f46817c4a6046d3b", "attempt_id": "3a3af24c7c55", "run_group_id": "E0_smoke:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:40.895456Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 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": 1971, "source_tokens_receiver": 1971, "query_tokens": 589, "message_tokens": 508, "message_utf8_bytes": 1477, "cache_tensor_bytes": null, "serialized_payload_bytes": 1477, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.0682919528335333, "decode_payload_ms": 0.0, "receiver_prefill_ms": 80.28387499507517, "ttft_ms": 20.092083024792373, "decode_ms": 186.3948330283165}, "total_wall_ms": 289.03933404944837, "ttft_ms": 20.092083024792373, "input_usage": {"receiver_prompt_tokens": 589}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6600916992, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6563131480, "mlx_cache_bytes": 4122167616, "process_rss_bytes": 6600916992}, "peak_prefill_memory": null, "peak_decode_memory": 6563131480, "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.log", "payload_hash": "0c282c4bd4288101fb9f0b7c3f7960301f9b9cae0e1b006f3d55fa33cb6c3bdc", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}19{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "46b4c199d55ef7f74812ec8b", "attempt_id": "7ae1fd080653", "run_group_id": "E0_smoke:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:41.203354Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 499, "n_sentences": 24}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 580, "message_tokens": 499, "message_utf8_bytes": 1320, "cache_tensor_bytes": null, "serialized_payload_bytes": 1320, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.1374169262126088, "decode_payload_ms": 0.0, "receiver_prefill_ms": 96.964625059627, "ttft_ms": 15.490291989408433, "decode_ms": 136.05291699059308}, "total_wall_ms": 250.9514580015093, "ttft_ms": 15.490291989408433, "input_usage": {"receiver_prompt_tokens": 580}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6600916992, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6577401944, "mlx_cache_bytes": 4382132544, "process_rss_bytes": 6600916992}, "peak_prefill_memory": null, "peak_decode_memory": 6577401944, "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.log", "payload_hash": "77c2c83f97318ad674e337c84e8706903022a99e330a15111b84b24346998e7c", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}20{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "2919933128528059f21bcef7", "attempt_id": "bac3b7a88e92", "run_group_id": "E0_smoke:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:41.474626Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 499, "n_sentences": 17}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 577, "message_tokens": 499, "message_utf8_bytes": 1439, "cache_tensor_bytes": null, "serialized_payload_bytes": 1439, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.8985829772427678, "decode_payload_ms": 0.0, "receiver_prefill_ms": 201.23016694560647, "ttft_ms": 18.682542024180293, "decode_ms": 100.2345000160858}, "total_wall_ms": 322.1747080096975, "ttft_ms": 18.682542024180293, "input_usage": {"receiver_prompt_tokens": 577}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6600982528, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6555218008, "mlx_cache_bytes": 4697098560, "process_rss_bytes": 6600982528}, "peak_prefill_memory": null, "peak_decode_memory": 6555218008, "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.log", "payload_hash": "8c78c2c57027b9340eda90e83f732ddd57af36c5177bd2241b5f21f5452cfb30", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}21{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c9f341728f8327673d8c20fd", "attempt_id": "75d22a7bf90c", "run_group_id": "E0_smoke:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:52.355810Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 591, "message_tokens": 512, "message_utf8_bytes": 1196, "cache_tensor_bytes": null, "serialized_payload_bytes": 1196, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10538.946290966123, "decode_payload_ms": 0.0, "receiver_prefill_ms": 96.65604203473777, "ttft_ms": 21.105334046296775, "decode_ms": 193.9961250172928}, "total_wall_ms": 313.1064580520615, "ttft_ms": 21.105334046296775, "input_usage": {"receiver_prompt_tokens": 591, "sender_input_tokens": 2087, "sender_output_tokens": 512, "sender_prefill_ms": 310.1318330736831, "sender_ttft_ms": 21.124709048308432, "sender_decode_ms": 10205.545666976832}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6601342976, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6584578136, "mlx_cache_bytes": 5159553344, "process_rss_bytes": 6601342976}, "peak_prefill_memory": null, "peak_decode_memory": 6584578136, "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.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}22{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "3d4dd464f7010b36c96bc271", "attempt_id": "77a451d8dea8", "run_group_id": "E0_smoke:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:52.688816Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 597, "message_tokens": 512, "message_utf8_bytes": 1196, "cache_tensor_bytes": null, "serialized_payload_bytes": 1196, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10538.946290966123, "decode_payload_ms": 0.0, "receiver_prefill_ms": 99.47799996007234, "ttft_ms": 24.71804094966501, "decode_ms": 19.204750075004995}, "total_wall_ms": 144.63758398778737, "ttft_ms": 24.71804094966501, "input_usage": {"receiver_prompt_tokens": 597, "sender_input_tokens": 2087, "sender_output_tokens": 512, "sender_prefill_ms": 310.1318330736831, "sender_ttft_ms": 21.124709048308432, "sender_decode_ms": 10205.545666976832}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601375744, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6567653464, "mlx_cache_bytes": 5404920128, "process_rss_bytes": 6601375744}, "peak_prefill_memory": null, "peak_decode_memory": 6567653464, "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.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}23{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "0a2034eccdf34fd25393da3d", "attempt_id": "125915e60a3b", "run_group_id": "E0_smoke:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:52.855392Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 597, "message_tokens": 512, "message_utf8_bytes": 1196, "cache_tensor_bytes": null, "serialized_payload_bytes": 1196, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10538.946290966123, "decode_payload_ms": 0.0, "receiver_prefill_ms": 104.98479206580669, "ttft_ms": 21.320041036233306, "decode_ms": 13.582999934442341}, "total_wall_ms": 141.07616699766368, "ttft_ms": 21.320041036233306, "input_usage": {"receiver_prompt_tokens": 597, "sender_input_tokens": 2087, "sender_output_tokens": 512, "sender_prefill_ms": 310.1318330736831, "sender_ttft_ms": 21.124709048308432, "sender_decode_ms": 10205.545666976832}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601375744, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6567653464, "mlx_cache_bytes": 5404920128, "process_rss_bytes": 6601375744}, "peak_prefill_memory": null, "peak_decode_memory": 6567653464, "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.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}24{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "e8e8d23e7cdbfbbae9a8842f", "attempt_id": "1a19d08c27d6", "run_group_id": "E0_smoke:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:26:53.016421Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 594, "message_tokens": 512, "message_utf8_bytes": 1196, "cache_tensor_bytes": null, "serialized_payload_bytes": 1196, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10538.946290966123, "decode_payload_ms": 0.0, "receiver_prefill_ms": 98.61950005870312, "ttft_ms": 26.502083986997604, "decode_ms": 22.947457968257368}, "total_wall_ms": 149.47245793882757, "ttft_ms": 26.502083986997604, "input_usage": {"receiver_prompt_tokens": 594, "sender_input_tokens": 2087, "sender_output_tokens": 512, "sender_prefill_ms": 310.1318330736831, "sender_ttft_ms": 21.124709048308432, "sender_decode_ms": 10205.545666976832}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601375744, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6566572120, "mlx_cache_bytes": 5561616704, "process_rss_bytes": 6601375744}, "peak_prefill_memory": null, "peak_decode_memory": 6566572120, "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.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}25{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "bfe20256c44e4c579db64576", "attempt_id": "1297d741734b", "run_group_id": "E0_smoke:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:03.898439Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 8, "unresolved_quotes": 1, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 434, "message_tokens": 344, "message_utf8_bytes": 817, "cache_tensor_bytes": null, "serialized_payload_bytes": 817, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10709.832667023875, "decode_payload_ms": 0.0, "receiver_prefill_ms": 86.80112496949732, "ttft_ms": 15.794583945535123, "decode_ms": 15.125207952223718}, "total_wall_ms": 119.22554101329297, "ttft_ms": 15.794583945535123, "input_usage": {"receiver_prompt_tokens": 434, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 363.058082992211, "sender_ttft_ms": 21.328666945919394, "sender_decode_ms": 10323.293083929457}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601621504, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6536062772, "mlx_cache_bytes": 5921099780, "process_rss_bytes": 6601621504}, "peak_prefill_memory": null, "peak_decode_memory": 6536062772, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 8, "unresolved_quotes": 1, "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.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}26{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "14528bf1cb04b7494a446b9d", "attempt_id": "2940c8ef0c3d", "run_group_id": "E0_smoke:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:04.040109Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 8, "unresolved_quotes": 1, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 440, "message_tokens": 344, "message_utf8_bytes": 817, "cache_tensor_bytes": null, "serialized_payload_bytes": 817, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10709.832667023875, "decode_payload_ms": 0.0, "receiver_prefill_ms": 80.46558406203985, "ttft_ms": 26.1877499287948, "decode_ms": 23.025874979794025}, "total_wall_ms": 130.96516602672637, "ttft_ms": 26.1877499287948, "input_usage": {"receiver_prompt_tokens": 440, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 363.058082992211, "sender_ttft_ms": 21.328666945919394, "sender_decode_ms": 10323.293083929457}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601703424, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6540175180, "mlx_cache_bytes": 6264870624, "process_rss_bytes": 6601703424}, "peak_prefill_memory": null, "peak_decode_memory": 6540175180, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 8, "unresolved_quotes": 1, "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.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}27{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "ad104e7f7b140ccf40a30520", "attempt_id": "f9ea7cc2404d", "run_group_id": "E0_smoke:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:04.197844Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 8, "unresolved_quotes": 1, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 440, "message_tokens": 344, "message_utf8_bytes": 817, "cache_tensor_bytes": null, "serialized_payload_bytes": 817, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10709.832667023875, "decode_payload_ms": 0.0, "receiver_prefill_ms": 84.51795799192041, "ttft_ms": 22.2842920338735, "decode_ms": 20.577540970407426}, "total_wall_ms": 128.7586250109598, "ttft_ms": 22.2842920338735, "input_usage": {"receiver_prompt_tokens": 440, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 363.058082992211, "sender_ttft_ms": 21.328666945919394, "sender_decode_ms": 10323.293083929457}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601736192, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6540175180, "mlx_cache_bytes": 6264870624, "process_rss_bytes": 6601736192}, "peak_prefill_memory": null, "peak_decode_memory": 6540175180, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 8, "unresolved_quotes": 1, "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.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}28{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "0d6fd2ea1c04214d97935766", "attempt_id": "0efbda3ef5a6", "run_group_id": "E0_smoke:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:04.350742Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 8, "unresolved_quotes": 1, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 437, "message_tokens": 344, "message_utf8_bytes": 817, "cache_tensor_bytes": null, "serialized_payload_bytes": 817, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10709.832667023875, "decode_payload_ms": 0.0, "receiver_prefill_ms": 73.29770794603974, "ttft_ms": 22.63987495098263, "decode_ms": 22.071832907386124}, "total_wall_ms": 119.35541604179889, "ttft_ms": 22.63987495098263, "input_usage": {"receiver_prompt_tokens": 437, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 363.058082992211, "sender_ttft_ms": 21.328666945919394, "sender_decode_ms": 10323.293083929457}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601736192, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6537635660, "mlx_cache_bytes": 6504208096, "process_rss_bytes": 6601736192}, "peak_prefill_memory": null, "peak_decode_memory": 6537635660, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 8, "unresolved_quotes": 1, "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.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}29{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "cc55ee727e706809191c6b97", "attempt_id": "18419046d12f", "run_group_id": "E0_smoke:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:15.157932Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 7}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 1045, "message_tokens": 970, "message_utf8_bytes": 623, "cache_tensor_bytes": null, "serialized_payload_bytes": 623, "side_information_bytes": 0, "fetched_bytes": 1634, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10663.693792070262, "decode_payload_ms": 0.0, "receiver_prefill_ms": 158.85141701437533, "ttft_ms": 23.864249931648374, "decode_ms": 21.887833951041102}, "total_wall_ms": 206.70400001108646, "ttft_ms": 23.864249931648374, "input_usage": {"receiver_prompt_tokens": 1045, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 357.24162496626377, "sender_ttft_ms": 24.779249913990498, "sender_decode_ms": 10279.268582933582}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601932800, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6818152508, "mlx_cache_bytes": 7174788832, "process_rss_bytes": 6601932800}, "peak_prefill_memory": null, "peak_decode_memory": 6818152508, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1634, "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.log", "payload_hash": "561d3553701d834273477e7e81d6f4a2903e1fe9e09b5b4efdd73a721bde815e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}30{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "501d065cba8addb831258e6e", "attempt_id": "de2d1ad7bd00", "run_group_id": "E0_smoke:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:15.386259Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 7}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 1051, "message_tokens": 970, "message_utf8_bytes": 623, "cache_tensor_bytes": null, "serialized_payload_bytes": 623, "side_information_bytes": 0, "fetched_bytes": 1634, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10663.693792070262, "decode_payload_ms": 0.0, "receiver_prefill_ms": 189.56966698169708, "ttft_ms": 14.294749940745533, "decode_ms": 27.563792071305215}, "total_wall_ms": 233.33387507591397, "ttft_ms": 14.294749940745533, "input_usage": {"receiver_prompt_tokens": 1051, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 357.24162496626377, "sender_ttft_ms": 24.779249913990498, "sender_decode_ms": 10279.268582933582}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6601998336, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6821855292, "mlx_cache_bytes": 7792318176, "process_rss_bytes": 6601998336}, "peak_prefill_memory": null, "peak_decode_memory": 6821855292, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1634, "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.log", "payload_hash": "ab0e9c7021e297c7521daf9f4fa54de8136f15dc9e1c13a37a4af71f57687c8e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}31{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "f765949413aa3fedfc527088", "attempt_id": "ceca82621c8d", "run_group_id": "E0_smoke:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:15.642557Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 7}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 1051, "message_tokens": 970, "message_utf8_bytes": 623, "cache_tensor_bytes": null, "serialized_payload_bytes": 623, "side_information_bytes": 0, "fetched_bytes": 1634, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10663.693792070262, "decode_payload_ms": 0.0, "receiver_prefill_ms": 189.3771659815684, "ttft_ms": 25.745707913301885, "decode_ms": 17.177957925014198}, "total_wall_ms": 234.096874948591, "ttft_ms": 25.745707913301885, "input_usage": {"receiver_prompt_tokens": 1051, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 357.24162496626377, "sender_ttft_ms": 24.779249913990498, "sender_decode_ms": 10279.268582933582}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6602014720, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6821855292, "mlx_cache_bytes": 7792318176, "process_rss_bytes": 6602014720}, "peak_prefill_memory": null, "peak_decode_memory": 6821855292, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1634, "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.log", "payload_hash": "ab0e9c7021e297c7521daf9f4fa54de8136f15dc9e1c13a37a4af71f57687c8e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}32{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "9b842e322458a64162511f40", "attempt_id": "c420975d5b17", "run_group_id": "E0_smoke:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:15.899962Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 7}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 1048, "message_tokens": 970, "message_utf8_bytes": 623, "cache_tensor_bytes": null, "serialized_payload_bytes": 623, "side_information_bytes": 0, "fetched_bytes": 1634, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10663.693792070262, "decode_payload_ms": 0.0, "receiver_prefill_ms": 191.9341660104692, "ttft_ms": 21.331749972887337, "decode_ms": 21.82987506967038}, "total_wall_ms": 236.95158294867724, "ttft_ms": 21.331749972887337, "input_usage": {"receiver_prompt_tokens": 1048, "sender_input_tokens": 2115, "sender_output_tokens": 512, "sender_prefill_ms": 357.24162496626377, "sender_ttft_ms": 24.779249913990498, "sender_decode_ms": 10279.268582933582}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6602031104, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6850740284, "mlx_cache_bytes": 8266307296, "process_rss_bytes": 6602031104}, "peak_prefill_memory": null, "peak_decode_memory": 6850740284, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"lookups": 6, "fetched_bytes": 1634, "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.log", "payload_hash": "ab0e9c7021e297c7521daf9f4fa54de8136f15dc9e1c13a37a4af71f57687c8e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}33{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "dbb4d6f308be12c0c7abcf21", "attempt_id": "0f02e576dce2", "run_group_id": "E0_smoke:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:16.163883Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2045, "message_tokens": 1971, "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": 5.297624971717596, "decode_payload_ms": 0.417957897298038, "receiver_prefill_ms": 351.0584579780698, "ttft_ms": 25.52862500306219, "decode_ms": 203.8207920268178}, "total_wall_ms": 583.828458096832, "ttft_ms": 25.52862500306219, "input_usage": {"receiver_prompt_tokens": 2045}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6602473472, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7061651504, "mlx_cache_bytes": 8266307296, "process_rss_bytes": 6602473472}, "peak_prefill_memory": null, "peak_decode_memory": 7061651504, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}34{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a05e1aeb0d35317b7f3245e7", "attempt_id": "5ae486a7ef40", "run_group_id": "E0_smoke:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:16.769440Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2051, "message_tokens": 1971, "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": 5.297624971717596, "decode_payload_ms": 0.417957897298038, "receiver_prefill_ms": 321.8972079921514, "ttft_ms": 22.83312496729195, "decode_ms": 189.30195807479322}, "total_wall_ms": 537.459957995452, "ttft_ms": 22.83312496729195, "input_usage": {"receiver_prompt_tokens": 2051}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6602522624, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7054786612, "mlx_cache_bytes": 8266307296, "process_rss_bytes": 6602522624}, "peak_prefill_memory": null, "peak_decode_memory": 7054786612, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}35{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a2c9f22c371cea273080a863", "attempt_id": "9bc42d166be3", "run_group_id": "E0_smoke:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:17.329219Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2051, "message_tokens": 1971, "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": 5.297624971717596, "decode_payload_ms": 0.417957897298038, "receiver_prefill_ms": 320.60200010892004, "ttft_ms": 21.40745904762298, "decode_ms": 157.95058303046972}, "total_wall_ms": 503.5944579867646, "ttft_ms": 21.40745904762298, "input_usage": {"receiver_prompt_tokens": 2051}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6602522624, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7054786612, "mlx_cache_bytes": 8266307296, "process_rss_bytes": 6602522624}, "peak_prefill_memory": null, "peak_decode_memory": 7054786612, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}36{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "0f75b3b41655640fb015977f", "attempt_id": "ce4f9d61ae8a", "run_group_id": "E0_smoke:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:17.855898Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 2048, "message_tokens": 1971, "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": 5.297624971717596, "decode_payload_ms": 0.417957897298038, "receiver_prefill_ms": 304.32729201857, "ttft_ms": 20.300709060393274, "decode_ms": 107.78937500435859}, "total_wall_ms": 435.70933397859335, "ttft_ms": 20.300709060393274, "input_usage": {"receiver_prompt_tokens": 2048}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6602539008, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7063175232, "mlx_cache_bytes": 8266307296, "process_rss_bytes": 6602539008}, "peak_prefill_memory": null, "peak_decode_memory": 7063175232, "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.log", "payload_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}37{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c5c8f77106a5a3772c8729a5", "attempt_id": "4c8b0eb2ff80", "run_group_id": "E0_smoke:B0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:18.659274Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321889288}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112716, "side_information_bytes": 16076, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 346.22316691093147, "doc_prefill_ms": 308.5541669279337, "compress_ms": 9.487665956839919, "serialize_ms": 24.9150829622522, "load_ms": 8.98820802103728, "receiver_prefill_ms": 0.0, "query_prefill_ms": 249.4774169754237, "ttft_ms": 249.4774169754237, "decode_ms": 216.42729197628796}, "total_wall_ms": 477.1647499874234, "ttft_ms": 249.4774169754237, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6751551488, "backend_memory": {"mlx_active_bytes": 6398566408, "mlx_peak_bytes": 6445818172, "mlx_cache_bytes": 9171015533, "process_rss_bytes": 6751551488}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6445818172, "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.log", "payload_hash": "0fd1e41ac9de2a394237f6d73e79f07db7814fc3daad26bdafb5187f0b9128ae", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}38{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "36b870572f370219b55f990f", "attempt_id": "90b0dceb3de2", "run_group_id": "E0_smoke:B0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:19.158034Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321889288}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112716, "side_information_bytes": 16076, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 346.22316691093147, "doc_prefill_ms": 308.5541669279337, "compress_ms": 9.487665956839919, "serialize_ms": 24.9150829622522, "load_ms": 0.8970829658210278, "receiver_prefill_ms": 0.0, "query_prefill_ms": 42.57166699972004, "ttft_ms": 42.57166699972004, "decode_ms": 185.1583339739591}, "total_wall_ms": 230.58637499343604, "ttft_ms": 42.57166699972004, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6751666176, "backend_memory": {"mlx_active_bytes": 6398566408, "mlx_peak_bytes": 6450323772, "mlx_cache_bytes": 9211369489, "process_rss_bytes": 6751666176}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6450323772, "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.log", "payload_hash": "0fd1e41ac9de2a394237f6d73e79f07db7814fc3daad26bdafb5187f0b9128ae", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}39{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "5c39b27a1d42aae9403aeea4", "attempt_id": "39eeebfa218d", "run_group_id": "E0_smoke:B0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:19.410787Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321889288}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112716, "side_information_bytes": 16076, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 346.22316691093147, "doc_prefill_ms": 308.5541669279337, "compress_ms": 9.487665956839919, "serialize_ms": 24.9150829622522, "load_ms": 0.850292039103806, "receiver_prefill_ms": 0.0, "query_prefill_ms": 32.38766698632389, "ttft_ms": 32.38766698632389, "decode_ms": 154.78104201611131}, "total_wall_ms": 190.03108399920166, "ttft_ms": 32.38766698632389, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6751666176, "backend_memory": {"mlx_active_bytes": 6398566408, "mlx_peak_bytes": 6450323684, "mlx_cache_bytes": 9211369489, "process_rss_bytes": 6751666176}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6450323684, "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.log", "payload_hash": "0fd1e41ac9de2a394237f6d73e79f07db7814fc3daad26bdafb5187f0b9128ae", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}40{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "f2fea6b40fbfa3efc8b41254", "attempt_id": "6551be76c24d", "run_group_id": "E0_smoke:B0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:19.622622Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321889288}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112716, "side_information_bytes": 16076, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 346.22316691093147, "doc_prefill_ms": 308.5541669279337, "compress_ms": 9.487665956839919, "serialize_ms": 24.9150829622522, "load_ms": 0.896209036000073, "receiver_prefill_ms": 0.0, "query_prefill_ms": 208.85649998672307, "ttft_ms": 208.85649998672307, "decode_ms": 107.41054196842015}, "total_wall_ms": 318.9865410095081, "ttft_ms": 208.85649998672307, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6751764480, "backend_memory": {"mlx_active_bytes": 6398566408, "mlx_peak_bytes": 6446309604, "mlx_cache_bytes": 9222920209, "process_rss_bytes": 6751764480}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6446309604, "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.log", "payload_hash": "0fd1e41ac9de2a394237f6d73e79f07db7814fc3daad26bdafb5187f0b9128ae", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}41{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "5242938fc112225287b86b4e", "attempt_id": "0439f90f11d2", "run_group_id": "E0_smoke:B1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:19.986065Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321692680}, "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": "5934e1e7b2bd92f6", "random_seed": 0, "source_tokens_sender": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112744, "side_information_bytes": 16104, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 21.857209037989378, "doc_prefill_ms": 308.5541669279337, "compress_ms": 1.7394160386174917, "serialize_ms": 19.88820801489055, "load_ms": 11.17420895025134, "receiver_prefill_ms": 0.0, "query_prefill_ms": 31.265333062037826, "ttft_ms": 31.265333062037826, "decode_ms": 209.63187504094094}, "total_wall_ms": 253.80166701506823, "ttft_ms": 31.265333062037826, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6826115072, "backend_memory": {"mlx_active_bytes": 6398369800, "mlx_peak_bytes": 6445654220, "mlx_cache_bytes": 9223116817, "process_rss_bytes": 6826115072}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6445654220, "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.log", "payload_hash": "eb4d9d05bd93beebadeb0b446aca6f8cd3f69a85009c57c2686509661e53bad1", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}42{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "7233daed51e30233779143b4", "attempt_id": "bc0068e8d567", "run_group_id": "E0_smoke:B1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:20.262668Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321692680}, "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": "5934e1e7b2bd92f6", "random_seed": 0, "source_tokens_sender": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112744, "side_information_bytes": 16104, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 21.857209037989378, "doc_prefill_ms": 308.5541669279337, "compress_ms": 1.7394160386174917, "serialize_ms": 19.88820801489055, "load_ms": 9.897915995679796, "receiver_prefill_ms": 0.0, "query_prefill_ms": 34.51216605026275, "ttft_ms": 34.51216605026275, "decode_ms": 170.15541705768555}, "total_wall_ms": 216.34687494952232, "ttft_ms": 34.51216605026275, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6832308224, "backend_memory": {"mlx_active_bytes": 6398369800, "mlx_peak_bytes": 6450159844, "mlx_cache_bytes": 9223116817, "process_rss_bytes": 6832308224}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6450159844, "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.log", "payload_hash": "eb4d9d05bd93beebadeb0b446aca6f8cd3f69a85009c57c2686509661e53bad1", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}43{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "160b26eb5f87ef0ce84beb4d", "attempt_id": "c503e8d98716", "run_group_id": "E0_smoke:B1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:20.502861Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321692680}, "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": "5934e1e7b2bd92f6", "random_seed": 0, "source_tokens_sender": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112744, "side_information_bytes": 16104, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 21.857209037989378, "doc_prefill_ms": 308.5541669279337, "compress_ms": 1.7394160386174917, "serialize_ms": 19.88820801489055, "load_ms": 9.91812499705702, "receiver_prefill_ms": 0.0, "query_prefill_ms": 33.97083294112235, "ttft_ms": 33.97083294112235, "decode_ms": 151.9315839977935}, "total_wall_ms": 197.57162500172853, "ttft_ms": 33.97083294112235, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6838501376, "backend_memory": {"mlx_active_bytes": 6398369800, "mlx_peak_bytes": 6450159844, "mlx_cache_bytes": 9223116817, "process_rss_bytes": 6838501376}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6450159844, "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.log", "payload_hash": "eb4d9d05bd93beebadeb0b446aca6f8cd3f69a85009c57c2686509661e53bad1", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}44{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "00a9e3a43807646a1eff16b6", "attempt_id": "b124df1d7a76", "run_group_id": "E0_smoke:B1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:20.724657Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6321692680}, "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": "5934e1e7b2bd92f6", "random_seed": 0, "source_tokens_sender": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 74096640, "serialized_payload_bytes": 74112744, "side_information_bytes": 16104, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 21.857209037989378, "doc_prefill_ms": 308.5541669279337, "compress_ms": 1.7394160386174917, "serialize_ms": 19.88820801489055, "load_ms": 7.181875058449805, "receiver_prefill_ms": 0.0, "query_prefill_ms": 38.916666992008686, "ttft_ms": 38.916666992008686, "decode_ms": 104.37366692349315}, "total_wall_ms": 152.26829203311354, "ttft_ms": 38.916666992008686, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6850887680, "backend_memory": {"mlx_active_bytes": 6398369800, "mlx_peak_bytes": 6446145764, "mlx_cache_bytes": 9223116817, "process_rss_bytes": 6850887680}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6446145764, "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.log", "payload_hash": "eb4d9d05bd93beebadeb0b446aca6f8cd3f69a85009c57c2686509661e53bad1", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}45{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "294ffec3fe617d6816ea913d", "attempt_id": "1828d4dd5c48", "run_group_id": "E0_smoke:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:20.938893Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6287739496}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 39363840, "serialized_payload_bytes": 39398030, "side_information_bytes": 34190, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 39.9517499608919, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.196083027869463, "serialize_ms": 16.328124911524355, "load_ms": 12.6062500057742, "receiver_prefill_ms": 0.0, "query_prefill_ms": 273.0062920600176, "ttft_ms": 273.0062920600176, "decode_ms": 218.48266595043242}, "total_wall_ms": 505.92758296988904, "ttft_ms": 273.0062920600176, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6891094016, "backend_memory": {"mlx_active_bytes": 6331681384, "mlx_peak_bytes": 6388051512, "mlx_cache_bytes": 9450675425, "process_rss_bytes": 6891094016}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6388051512, "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.log", "payload_hash": "5f8624f35d651cd19bdb054c3205083465b76bee66103dc2a4d23dbd2e6dc167", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}46{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "bcbcd6fa055fead9c2aa2d75", "attempt_id": "1b94f96b3250", "run_group_id": "E0_smoke:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:21.469067Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6287739496}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 39363840, "serialized_payload_bytes": 39398030, "side_information_bytes": 34190, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 39.9517499608919, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.196083027869463, "serialize_ms": 16.328124911524355, "load_ms": 1.5839169500395656, "receiver_prefill_ms": 0.0, "query_prefill_ms": 25.846250005997717, "ttft_ms": 25.846250005997717, "decode_ms": 186.94529205095023}, "total_wall_ms": 216.11754200421274, "ttft_ms": 25.846250005997717, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6891143168, "backend_memory": {"mlx_active_bytes": 6331681384, "mlx_peak_bytes": 6397167472, "mlx_cache_bytes": 9476273137, "process_rss_bytes": 6891143168}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6397167472, "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.log", "payload_hash": "5f8624f35d651cd19bdb054c3205083465b76bee66103dc2a4d23dbd2e6dc167", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}47{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "ad87548daad905473e842531", "attempt_id": "507a3aee8516", "run_group_id": "E0_smoke:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:21.707191Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6287739496}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 39363840, "serialized_payload_bytes": 39398030, "side_information_bytes": 34190, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 39.9517499608919, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.196083027869463, "serialize_ms": 16.328124911524355, "load_ms": 1.4031250029802322, "receiver_prefill_ms": 0.0, "query_prefill_ms": 26.463374961167574, "ttft_ms": 26.463374961167574, "decode_ms": 176.86091596260667}, "total_wall_ms": 206.55783300753683, "ttft_ms": 26.463374961167574, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6891143168, "backend_memory": {"mlx_active_bytes": 6331665000, "mlx_peak_bytes": 6397168208, "mlx_cache_bytes": 9476289521, "process_rss_bytes": 6891143168}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6397168208, "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.log", "payload_hash": "5f8624f35d651cd19bdb054c3205083465b76bee66103dc2a4d23dbd2e6dc167", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}48{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "131a6411d0b38a14e350647f", "attempt_id": "72228fa64660", "run_group_id": "E0_smoke:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:21.935900Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6287739496}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 39363840, "serialized_payload_bytes": 39398030, "side_information_bytes": 34190, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 39.9517499608919, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.196083027869463, "serialize_ms": 16.328124911524355, "load_ms": 1.620083930902183, "receiver_prefill_ms": 0.0, "query_prefill_ms": 180.2529999986291, "ttft_ms": 180.2529999986291, "decode_ms": 113.61583299003541}, "total_wall_ms": 297.15695802588016, "ttft_ms": 180.2529999986291, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6891192320, "backend_memory": {"mlx_active_bytes": 6331681384, "mlx_peak_bytes": 6389402192, "mlx_cache_bytes": 9498686449, "process_rss_bytes": 6891192320}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6389402192, "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.log", "payload_hash": "5f8624f35d651cd19bdb054c3205083465b76bee66103dc2a4d23dbd2e6dc167", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}49{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "cfa6d276303301b1b0a340f3", "attempt_id": "3ce90c85cbe1", "run_group_id": "E0_smoke:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:22.289140Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6268712200}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 20839680, "serialized_payload_bytes": 20873736, "side_information_bytes": 34056, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 34.626082982867956, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.7636249512434, "serialize_ms": 10.439375066198409, "load_ms": 6.075291079469025, "receiver_prefill_ms": 0.0, "query_prefill_ms": 259.889583918266, "ttft_ms": 259.889583918266, "decode_ms": 1147.461749962531}, "total_wall_ms": 1415.1050000218675, "ttft_ms": 259.889583918266, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6912704512, "backend_memory": {"mlx_active_bytes": 6294484232, "mlx_peak_bytes": 6346778920, "mlx_cache_bytes": 9564606801, "process_rss_bytes": 6912704512}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6346778920, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "\n\nunknownunknownunknown memo\n\n5\nunknown memo\n5\n\n\n memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo memo", "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.log", "payload_hash": "76d58caa4868c5c31b8703292423da4d64fc4061ef7af423b7b0c2b1f80e4f14", "output_hash": "78d55bf7eaf8f5d5718fae1592c5390a9d4187e68a847a5372b8f5fb9e43768c"}50{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "34a0a1b53fd1dae009867c20", "attempt_id": "0d83c3b1bfcd", "run_group_id": "E0_smoke:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:23.727440Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6268712200}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 20839680, "serialized_payload_bytes": 20873736, "side_information_bytes": 34056, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 34.626082982867956, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.7636249512434, "serialize_ms": 10.439375066198409, "load_ms": 2.2449579555541277, "receiver_prefill_ms": 0.0, "query_prefill_ms": 32.74408390279859, "ttft_ms": 32.74408390279859, "decode_ms": 1060.114708961919}, "total_wall_ms": 1096.9503748929128, "ttft_ms": 32.74408390279859, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6912737280, "backend_memory": {"mlx_active_bytes": 6294549768, "mlx_peak_bytes": 6356190592, "mlx_cache_bytes": 9564541265, "process_rss_bytes": 6912737280}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6356190592, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": " \nuser\n\n memo20.\nat000000000 of000000000000000000000000 of000", "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.log", "payload_hash": "76d58caa4868c5c31b8703292423da4d64fc4061ef7af423b7b0c2b1f80e4f14", "output_hash": "f956396894d647df89bc96127bf3812773aa370217fc6449ccdda4300087a89f"}51{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a8b57b89f00aa8409a780a6d", "attempt_id": "65169d0f70f2", "run_group_id": "E0_smoke:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:24.846333Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6268712200}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 20839680, "serialized_payload_bytes": 20873736, "side_information_bytes": 34056, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 34.626082982867956, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.7636249512434, "serialize_ms": 10.439375066198409, "load_ms": 1.5409999759867787, "receiver_prefill_ms": 0.0, "query_prefill_ms": 25.786499958485365, "ttft_ms": 25.786499958485365, "decode_ms": 55.565542075783014}, "total_wall_ms": 84.65270895976573, "ttft_ms": 25.786499958485365, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6912737280, "backend_memory": {"mlx_active_bytes": 6294566152, "mlx_peak_bytes": 6356190592, "mlx_cache_bytes": 9564524881, "process_rss_bytes": 6912737280}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6356190592, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "\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": "invalid_output", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "76d58caa4868c5c31b8703292423da4d64fc4061ef7af423b7b0c2b1f80e4f14", "output_hash": "75a11da44c802486bc6f65640aa48a730f0f684c5c07a42ba3cd1735eb3fb070"}52{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "01f04fced02030ea8b7fb96c", "attempt_id": "91a614851ec3", "run_group_id": "E0_smoke:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:24.952208Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6268712200}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 20839680, "serialized_payload_bytes": 20873736, "side_information_bytes": 34056, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 34.626082982867956, "doc_prefill_ms": 308.5541669279337, "compress_ms": 23.7636249512434, "serialize_ms": 10.439375066198409, "load_ms": 1.630165963433683, "receiver_prefill_ms": 0.0, "query_prefill_ms": 180.5562499212101, "ttft_ms": 180.5562499212101, "decode_ms": 1070.0649589998648}, "total_wall_ms": 1254.2412499897182, "ttft_ms": 180.5562499212101, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6912786432, "backend_memory": {"mlx_active_bytes": 6294500616, "mlx_peak_bytes": 6348424592, "mlx_cache_bytes": 9564590417, "process_rss_bytes": 6912786432}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6348424592, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "user\n\nsystem 0 0 000000000000000000000000000000000000000", "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.log", "payload_hash": "76d58caa4868c5c31b8703292423da4d64fc4061ef7af423b7b0c2b1f80e4f14", "output_hash": "d3da647a46cbd3eb57b7ba22bfc90fff80e5d0dfb8efe06d0ea15bf1b7249bde"}53{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "3866a433f650f0db81383698", "attempt_id": "94d40d88413a", "run_group_id": "E0_smoke:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:26.301231Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 64.08412498421967}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521645, "side_information_bytes": 15917, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.80583295505494, "doc_prefill_ms": 308.5541669279337, "compress_ms": 64.13950002752244, "serialize_ms": 8.448374923318624, "load_ms": 1.023292075842619, "receiver_prefill_ms": 0.0, "query_prefill_ms": 35.569333005696535, "ttft_ms": 35.569333005696535, "decode_ms": 199.1004589945078}, "total_wall_ms": 237.6932919723913, "ttft_ms": 35.569333005696535, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 10}, "provider_cached_usage": null, "process_memory": 6914555904, "backend_memory": {"mlx_active_bytes": 6287777800, "mlx_peak_bytes": 6324363468, "mlx_cache_bytes": 9575183873, "process_rss_bytes": 6914555904}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6324363468, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "MP-89X-6320", "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.log", "payload_hash": "7f6ef81007573cfaec410eb9847c70ee516bcb552b3345400893355ca501b96b", "output_hash": "e07259f8346a7570e5b980e01a868e6af8ede517e6d7f6a2958e2f3b8da08023"}54{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c5a46a2a80d968eb5b9cfd03", "attempt_id": "d3ca7d571fc6", "run_group_id": "E0_smoke:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:26.559533Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 64.08412498421967}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521645, "side_information_bytes": 15917, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.80583295505494, "doc_prefill_ms": 308.5541669279337, "compress_ms": 64.13950002752244, "serialize_ms": 8.448374923318624, "load_ms": 0.7745410548523068, "receiver_prefill_ms": 0.0, "query_prefill_ms": 27.40566700231284, "ttft_ms": 27.40566700231284, "decode_ms": 165.24295799899846}, "total_wall_ms": 195.35333395469934, "ttft_ms": 27.40566700231284, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6914588672, "backend_memory": {"mlx_active_bytes": 6287777800, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9575183873, "process_rss_bytes": 6914588672}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "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.log", "payload_hash": "7f6ef81007573cfaec410eb9847c70ee516bcb552b3345400893355ca501b96b", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}55{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "9e9adefa1df3c8162ef90094", "attempt_id": "d4d46f7011e0", "run_group_id": "E0_smoke:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:26.777798Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 64.08412498421967}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521645, "side_information_bytes": 15917, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.80583295505494, "doc_prefill_ms": 308.5541669279337, "compress_ms": 64.13950002752244, "serialize_ms": 8.448374923318624, "load_ms": 0.9067920036613941, "receiver_prefill_ms": 0.0, "query_prefill_ms": 27.181916986592114, "ttft_ms": 27.181916986592114, "decode_ms": 32.393874949775636}, "total_wall_ms": 62.11195804644376, "ttft_ms": 27.181916986592114, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6914588672, "backend_memory": {"mlx_active_bytes": 6287745032, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9575216641, "process_rss_bytes": 6914588672}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Not provided", "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.log", "payload_hash": "7f6ef81007573cfaec410eb9847c70ee516bcb552b3345400893355ca501b96b", "output_hash": "d83b9ff3c07a8390e2ea0a2af45fba37595da25f31b85ba625363ee98c0c796f"}56{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a4e24a1d6a957db1e957f87c", "attempt_id": "642d96719fa3", "run_group_id": "E0_smoke:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:26.863105Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 64.08412498421967}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521645, "side_information_bytes": 15917, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 72.80583295505494, "doc_prefill_ms": 308.5541669279337, "compress_ms": 64.13950002752244, "serialize_ms": 8.448374923318624, "load_ms": 1.1591659858822823, "receiver_prefill_ms": 0.0, "query_prefill_ms": 27.929875068366528, "ttft_ms": 27.929875068366528, "decode_ms": 76.25045790337026}, "total_wall_ms": 106.98124999180436, "ttft_ms": 27.929875068366528, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6914588672, "backend_memory": {"mlx_active_bytes": 6287155208, "mlx_peak_bytes": 6325493988, "mlx_cache_bytes": 9575806465, "process_rss_bytes": 6914588672}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6325493988, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Milos Ferrante", "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.log", "payload_hash": "7f6ef81007573cfaec410eb9847c70ee516bcb552b3345400893355ca501b96b", "output_hash": "14ae3adaefbe5d307a9585834a37951eb0794dc1bfacd0739a580886526143d2"}57{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c5299d0a9079f76c811be8e1", "attempt_id": "a91029007c95", "run_group_id": "E0_smoke:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:27.021383Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 25.0343750230968}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521639, "side_information_bytes": 15911, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 31.907333061099052, "doc_prefill_ms": 308.5541669279337, "compress_ms": 25.070416973903775, "serialize_ms": 6.617291015572846, "load_ms": 0.7211669581010938, "receiver_prefill_ms": 0.0, "query_prefill_ms": 22.886250051669776, "ttft_ms": 22.886250051669776, "decode_ms": 941.9688330963254}, "total_wall_ms": 967.6620420068502, "ttft_ms": 22.886250051669776, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6934003712, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6324363468, "mlx_cache_bytes": 9596089857, "process_rss_bytes": 6934003712}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6324363468, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant, Assistant\n\nAssistant, Assistant,", "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.log", "payload_hash": "367ec33700beb9aed70dd5a013f541cdebb9460e0b911a49ddd42cd63c849f4b", "output_hash": "a7f3f386f2ebe03f3097faba3f505d405d26b2f9abd5b6faacedc39b50901a2d"}58{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "92833db31d27eea8ff70489c", "attempt_id": "7e0b4656c29b", "run_group_id": "E0_smoke:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:28.012306Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 25.0343750230968}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521639, "side_information_bytes": 15911, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 31.907333061099052, "doc_prefill_ms": 308.5541669279337, "compress_ms": 25.070416973903775, "serialize_ms": 6.617291015572846, "load_ms": 0.9810830233618617, "receiver_prefill_ms": 0.0, "query_prefill_ms": 28.88324996456504, "ttft_ms": 28.88324996456504, "decode_ms": 929.5173750724643}, "total_wall_ms": 961.1695419298485, "ttft_ms": 28.88324996456504, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6934020096, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9596089857, "process_rss_bytes": 6934020096}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "I am a memo. I am a memo. I am a memo. I am a memo. I am a memo. I am a memo. I am a memo. I am a memo. I am a memo. I am a", "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.log", "payload_hash": "367ec33700beb9aed70dd5a013f541cdebb9460e0b911a49ddd42cd63c849f4b", "output_hash": "426a0f227def734f39a983ae88dcd05e8dcbe992627914324fb637eb8cb63e6b"}59{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "2cbc1b12a43668b7e57b864c", "attempt_id": "0d1f38b0b06c", "run_group_id": "E0_smoke:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:28.997109Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 25.0343750230968}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521639, "side_information_bytes": 15911, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 31.907333061099052, "doc_prefill_ms": 308.5541669279337, "compress_ms": 25.070416973903775, "serialize_ms": 6.617291015572846, "load_ms": 0.652667018584907, "receiver_prefill_ms": 0.0, "query_prefill_ms": 29.082583030685782, "ttft_ms": 29.082583030685782, "decode_ms": 957.0584170287475}, "total_wall_ms": 988.5560829425231, "ttft_ms": 29.082583030685782, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6934020096, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9596089857, "process_rss_bytes": 6934020096}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "The Project codes are the name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name name", "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.log", "payload_hash": "367ec33700beb9aed70dd5a013f541cdebb9460e0b911a49ddd42cd63c849f4b", "output_hash": "79576cc33fa68a3208636b2d8810c8c0d1f2117032776dc346a524e04fb85a25"}60{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "169b50740e3460318aa49fa9", "attempt_id": "e99d3d382fb0", "run_group_id": "E0_smoke:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:30.008009Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 2010, "keep": 502, "compress_ms": 25.0343750230968}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521639, "side_information_bytes": 15911, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 31.907333061099052, "doc_prefill_ms": 308.5541669279337, "compress_ms": 25.070416973903775, "serialize_ms": 6.617291015572846, "load_ms": 0.8759999182075262, "receiver_prefill_ms": 0.0, "query_prefill_ms": 30.01162502914667, "ttft_ms": 30.01162502914667, "decode_ms": 949.0018750075251}, "total_wall_ms": 981.6403749864548, "ttft_ms": 30.01162502914667, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6934020096, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6325493988, "mlx_cache_bytes": 9596089857, "process_rss_bytes": 6934020096}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6325493988, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "I will revise the project.\nI will revise the project.\nI will revise the project.\nI will revise the project.\nI will revise the project.\nI will revise the project.\nI will revise the project.\nI will revise the project.\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.log", "payload_hash": "367ec33700beb9aed70dd5a013f541cdebb9460e0b911a49ddd42cd63c849f4b", "output_hash": "ec85516726e09bae04746f5b6be22f47099830d26c5193e069713a8e4b00dca5"}61{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "93f6f7676d8794e607f42e04", "attempt_id": "da4d2710c0b7", "run_group_id": "E0_smoke:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:31.010413Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "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": 2010, "keep": 502, "window_tokens": 35, "compress_ms": 563.8788749929518}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521685, "side_information_bytes": 15957, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 572.4881670903414, "doc_prefill_ms": 308.5541669279337, "compress_ms": 565.5872919596732, "serialize_ms": 6.614041980355978, "load_ms": 0.8810000726953149, "receiver_prefill_ms": 0.0, "query_prefill_ms": 20.365500007756054, "ttft_ms": 20.365500007756054, "decode_ms": 119.11770806182176}, "total_wall_ms": 714.6071669412777, "ttft_ms": 20.365500007756054, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 6}, "provider_cached_usage": null, "process_memory": 6936444928, "backend_memory": {"mlx_active_bytes": 6286860296, "mlx_peak_bytes": 6322151628, "mlx_cache_bytes": 9625236993, "process_rss_bytes": 6936444928}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6322151628, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "WG-1482", "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.log", "payload_hash": "c45b4f30b880b0f5227d71d6f0c6992840fbb19374bbf7cfe2bdd05e112c7db5", "output_hash": "f5e9a6d78321ae31e0a3bdeeaf8c39b796c1fc12a0a8896955e8c411f428367c"}62{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "2f2d1a37db90019896731035", "attempt_id": "be106ee31fdd", "run_group_id": "E0_smoke:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:31.746833Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "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": 2010, "keep": 502, "window_tokens": 41, "compress_ms": 55.423791985958815}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521686, "side_information_bytes": 15958, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 63.9762079808861, "doc_prefill_ms": 308.5541669279337, "compress_ms": 57.0506660733372, "serialize_ms": 6.670959061011672, "load_ms": 0.9055420523509383, "receiver_prefill_ms": 0.0, "query_prefill_ms": 28.734207968227565, "ttft_ms": 28.734207968227565, "decode_ms": 179.1473749326542}, "total_wall_ms": 274.67562502715737, "ttft_ms": 28.734207968227565, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6936526848, "backend_memory": {"mlx_active_bytes": 6287777800, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9648109057, "process_rss_bytes": 6936526848}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "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.log", "payload_hash": "2133e2d8fb6fbe8bb2bc071e98a75ef68a33983b8f86299196b1d6fddcd4bf21", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}63{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "3c7f1c745d25a93cc74dfa5b", "attempt_id": "ea7dbd066ab8", "run_group_id": "E0_smoke:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.046152Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "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": 2010, "keep": 502, "window_tokens": 41, "compress_ms": 60.98887498956174}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521685, "side_information_bytes": 15957, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 69.41050000023097, "doc_prefill_ms": 308.5541669279337, "compress_ms": 62.77983298059553, "serialize_ms": 6.343499990180135, "load_ms": 0.7366250501945615, "receiver_prefill_ms": 0.0, "query_prefill_ms": 28.80037494469434, "ttft_ms": 28.80037494469434, "decode_ms": 144.29624995682389}, "total_wall_ms": 245.3072089701891, "ttft_ms": 28.80037494469434, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6936559616, "backend_memory": {"mlx_active_bytes": 6287745032, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9650468353, "process_rss_bytes": 6936559616}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "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.log", "payload_hash": "c45b4f30b880b0f5227d71d6f0c6992840fbb19374bbf7cfe2bdd05e112c7db5", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}64{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c8f2e4a96d7379d7d34702d1", "attempt_id": "e9277718bcd6", "run_group_id": "E0_smoke:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.313036Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "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": 2010, "keep": 502, "window_tokens": 38, "compress_ms": 175.28775008395314}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521686, "side_information_bytes": 15958, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 182.38962499890476, "doc_prefill_ms": 308.5541669279337, "compress_ms": 176.8307499587536, "serialize_ms": 5.288459011353552, "load_ms": 0.5769999697804451, "receiver_prefill_ms": 0.0, "query_prefill_ms": 26.420791051350534, "ttft_ms": 26.420791051350534, "decode_ms": 105.64537497702986}, "total_wall_ms": 316.87600002624094, "ttft_ms": 26.420791051350534, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6936657920, "backend_memory": {"mlx_active_bytes": 6287745032, "mlx_peak_bytes": 6325493988, "mlx_cache_bytes": 9655367169, "process_rss_bytes": 6936657920}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6325493988, "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.log", "payload_hash": "2133e2d8fb6fbe8bb2bc071e98a75ef68a33983b8f86299196b1d6fddcd4bf21", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}65{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a0f56d97be7daffa8cef249e", "attempt_id": "3e0f81469768", "run_group_id": "E0_smoke:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.713987Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "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": 2010, "keep": 502, "window_tokens": 19, "compress_ms": 58.06616693735123}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521685, "side_information_bytes": 15957, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 63.082249951548874, "doc_prefill_ms": 308.5541669279337, "compress_ms": 58.22541704401374, "serialize_ms": 4.690499976277351, "load_ms": 1.1760419001802802, "receiver_prefill_ms": 0.0, "query_prefill_ms": 31.72891598660499, "ttft_ms": 31.72891598660499, "decode_ms": 19.485582946799695}, "total_wall_ms": 54.12295798305422, "ttft_ms": 31.72891598660499, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6936887296, "backend_memory": {"mlx_active_bytes": 6286860296, "mlx_peak_bytes": 6322151628, "mlx_cache_bytes": 9674978817, "process_rss_bytes": 6936887296}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6322151628, "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.log", "payload_hash": "c45b4f30b880b0f5227d71d6f0c6992840fbb19374bbf7cfe2bdd05e112c7db5", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}66{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "490a5844ac7e4eb254afa577", "attempt_id": "24d3c5e9fd52", "run_group_id": "E0_smoke:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.789602Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "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": 2010, "keep": 502, "window_tokens": 19, "compress_ms": 58.06616693735123}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521685, "side_information_bytes": 15957, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 63.082249951548874, "doc_prefill_ms": 308.5541669279337, "compress_ms": 58.22541704401374, "serialize_ms": 4.690499976277351, "load_ms": 0.7209168979898095, "receiver_prefill_ms": 0.0, "query_prefill_ms": 25.789833045564592, "ttft_ms": 25.789833045564592, "decode_ms": 24.353457964025438}, "total_wall_ms": 52.51691699959338, "ttft_ms": 25.789833045564592, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6936920064, "backend_memory": {"mlx_active_bytes": 6286860296, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9674978817, "process_rss_bytes": 6936920064}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "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.log", "payload_hash": "c45b4f30b880b0f5227d71d6f0c6992840fbb19374bbf7cfe2bdd05e112c7db5", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}67{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "f43fe1d7913c24ca7775f970", "attempt_id": "a9cecb8c4957", "run_group_id": "E0_smoke:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.863379Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "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": 2010, "keep": 502, "window_tokens": 19, "compress_ms": 58.06616693735123}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521685, "side_information_bytes": 15957, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 63.082249951548874, "doc_prefill_ms": 308.5541669279337, "compress_ms": 58.22541704401374, "serialize_ms": 4.690499976277351, "load_ms": 0.816666055470705, "receiver_prefill_ms": 0.0, "query_prefill_ms": 19.551209057681262, "ttft_ms": 19.551209057681262, "decode_ms": 23.046249989420176}, "total_wall_ms": 45.09937507100403, "ttft_ms": 19.551209057681262, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6936920064, "backend_memory": {"mlx_active_bytes": 6286860296, "mlx_peak_bytes": 6327771364, "mlx_cache_bytes": 9674978817, "process_rss_bytes": 6936920064}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6327771364, "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.log", "payload_hash": "c45b4f30b880b0f5227d71d6f0c6992840fbb19374bbf7cfe2bdd05e112c7db5", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}68{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "23953c62f9522d607c97ebc1", "attempt_id": "df96117d0a60", "run_group_id": "E0_smoke:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.930619Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "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": 2010, "keep": 502, "window_tokens": 19, "compress_ms": 58.06616693735123}}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 18505728, "serialized_payload_bytes": 18521685, "side_information_bytes": 15957, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 63.082249951548874, "doc_prefill_ms": 308.5541669279337, "compress_ms": 58.22541704401374, "serialize_ms": 4.690499976277351, "load_ms": 1.2563749914988875, "receiver_prefill_ms": 0.0, "query_prefill_ms": 25.40870802477002, "ttft_ms": 25.40870802477002, "decode_ms": 13.515500002540648}, "total_wall_ms": 41.98029194958508, "ttft_ms": 25.40870802477002, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6936920064, "backend_memory": {"mlx_active_bytes": 6286860296, "mlx_peak_bytes": 6325493988, "mlx_cache_bytes": 9674978817, "process_rss_bytes": 6936920064}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6325493988, "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.log", "payload_hash": "c45b4f30b880b0f5227d71d6f0c6992840fbb19374bbf7cfe2bdd05e112c7db5", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}69{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "e4c6ac1cbe2528e118fc5703", "attempt_id": "a857f215ff82", "run_group_id": "E0_smoke:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:32.994458Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware"}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": null, "message_tokens": null, "message_utf8_bytes": null, "cache_tensor_bytes": null, "serialized_payload_bytes": null, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {}, "total_wall_ms": 77.96645897906274, "ttft_ms": null, "input_usage": {}, "output_usage": {}, "provider_cached_usage": null, "process_memory": null, "backend_memory": null, "peak_prefill_memory": null, "peak_decode_memory": null, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": null, "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": null, "status": "implementation_error", "error_code": "ValueError: [broadcast_shapes] Shapes (35,966) and (1,16,35,942) cannot be broadcast.", "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": null, "output_hash": null}70{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "e7b9ff431123b343d517b9dc", "attempt_id": "900e4aabd23d", "run_group_id": "E0_smoke:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.096831Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware"}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": null, "message_tokens": null, "message_utf8_bytes": null, "cache_tensor_bytes": null, "serialized_payload_bytes": null, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {}, "total_wall_ms": 66.20066694449633, "ttft_ms": null, "input_usage": {}, "output_usage": {}, "provider_cached_usage": null, "process_memory": null, "backend_memory": null, "peak_prefill_memory": null, "peak_decode_memory": null, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": null, "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": null, "status": "implementation_error", "error_code": "ValueError: [broadcast_shapes] Shapes (41,972) and (1,16,41,948) cannot be broadcast.", "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": null, "output_hash": null}71{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "4447de7a1f609caa2fe38d9d", "attempt_id": "77c4b23465cf", "run_group_id": "E0_smoke:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.184948Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware"}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": null, "message_tokens": null, "message_utf8_bytes": null, "cache_tensor_bytes": null, "serialized_payload_bytes": null, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {}, "total_wall_ms": 75.23312489502132, "ttft_ms": null, "input_usage": {}, "output_usage": {}, "provider_cached_usage": null, "process_memory": null, "backend_memory": null, "peak_prefill_memory": null, "peak_decode_memory": null, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": null, "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": null, "status": "implementation_error", "error_code": "ValueError: [broadcast_shapes] Shapes (41,972) and (1,16,41,948) cannot be broadcast.", "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": null, "output_hash": null}72{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "135f1a8ecad430fbb7dadf92", "attempt_id": "6f686bd52983", "run_group_id": "E0_smoke:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.282090Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware"}, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": null, "message_tokens": null, "message_utf8_bytes": null, "cache_tensor_bytes": null, "serialized_payload_bytes": null, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {}, "total_wall_ms": 71.89062493853271, "ttft_ms": null, "input_usage": {}, "output_usage": {}, "provider_cached_usage": null, "process_memory": null, "backend_memory": null, "peak_prefill_memory": null, "peak_decode_memory": null, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": null, "evidence_artifact": null, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": null, "status": "implementation_error", "error_code": "ValueError: [broadcast_shapes] Shapes (38,969) and (1,16,38,945) cannot be broadcast.", "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": null, "output_hash": null}73{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "56ee991b90464dd33a7c9ee5", "attempt_id": "f3c10dcea6ab", "run_group_id": "E0_smoke:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.403424Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6267434784}, "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": 2010, "keep": 1005, "compress_ms": 8.962583029642701, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 35, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 19681920, "serialized_payload_bytes": 19716076, "side_information_bytes": 34156, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 27.869292069226503, "doc_prefill_ms": 308.5541669279337, "compress_ms": 18.7781669665128, "serialize_ms": 8.690916933119297, "load_ms": 1.8424169393256307, "receiver_prefill_ms": 0.0, "query_prefill_ms": 19.6460000006482, "ttft_ms": 19.6460000006482, "decode_ms": 52.42887500207871}, "total_wall_ms": 75.69141697604209, "ttft_ms": 19.6460000006482, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 35}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 6983172096, "backend_memory": {"mlx_active_bytes": 6290394144, "mlx_peak_bytes": 6335647168, "mlx_cache_bytes": 9688339849, "process_rss_bytes": 6983172096}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6335647168, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Not provided", "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.log", "payload_hash": "7d69bc9e9fb081ba659e5e33c86d2bce4d329a5a3dbc4c317ae3342eb962c6d0", "output_hash": "d83b9ff3c07a8390e2ea0a2af45fba37595da25f31b85ba625363ee98c0c796f"}74{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "2f67a67e0c52d41f79c0f979", "attempt_id": "8b2fad1d3eca", "run_group_id": "E0_smoke:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.501685Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6267434784}, "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": 2010, "keep": 1005, "compress_ms": 8.962583029642701, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 19681920, "serialized_payload_bytes": 19716076, "side_information_bytes": 34156, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 27.869292069226503, "doc_prefill_ms": 308.5541669279337, "compress_ms": 18.7781669665128, "serialize_ms": 8.690916933119297, "load_ms": 1.884708064608276, "receiver_prefill_ms": 0.0, "query_prefill_ms": 27.582791983149946, "ttft_ms": 27.582791983149946, "decode_ms": 213.58125004917383}, "total_wall_ms": 244.85879205167294, "ttft_ms": 27.582791983149946, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 9}, "provider_cached_usage": null, "process_memory": 6983204864, "backend_memory": {"mlx_active_bytes": 6290656288, "mlx_peak_bytes": 6352739496, "mlx_cache_bytes": 9688077705, "process_rss_bytes": 6983204864}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6352739496, "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.log", "payload_hash": "7d69bc9e9fb081ba659e5e33c86d2bce4d329a5a3dbc4c317ae3342eb962c6d0", "output_hash": "b6582a041b3d2b38ac6924099568ca2e6f1a610c6fb5f4de2e0516b90433bc2a"}75{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "a457f580ccecc54298315139", "attempt_id": "5cf33b8c867a", "run_group_id": "E0_smoke:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.767722Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6267434784}, "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": 2010, "keep": 1005, "compress_ms": 8.962583029642701, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 41, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 19681920, "serialized_payload_bytes": 19716076, "side_information_bytes": 34156, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 27.869292069226503, "doc_prefill_ms": 308.5541669279337, "compress_ms": 18.7781669665128, "serialize_ms": 8.690916933119297, "load_ms": 1.6323330346494913, "receiver_prefill_ms": 0.0, "query_prefill_ms": 29.149292036890984, "ttft_ms": 29.149292036890984, "decode_ms": 161.35833400767297}, "total_wall_ms": 194.04400000348687, "ttft_ms": 29.149292036890984, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 41}, "output_usage": {"output_tokens": 7}, "provider_cached_usage": null, "process_memory": 6983204864, "backend_memory": {"mlx_active_bytes": 6290394144, "mlx_peak_bytes": 6352739496, "mlx_cache_bytes": 9688339849, "process_rss_bytes": 6983204864}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6352739496, "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.log", "payload_hash": "7d69bc9e9fb081ba659e5e33c86d2bce4d329a5a3dbc4c317ae3342eb962c6d0", "output_hash": "a6b0ea8de12cdf1084cdbceb42fd84946cd25a872f44d1f9a0846f3cf0f98534"}76{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "0a4e1364ef45cc38c5da4506", "attempt_id": "3b25f21b11c6", "run_group_id": "E0_smoke:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:33.985086Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6267434784}, "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": 2010, "keep": 1005, "compress_ms": 8.962583029642701, "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": 1971, "source_tokens_receiver": 1971, "query_tokens": 38, "message_tokens": 2010, "message_utf8_bytes": 7280, "cache_tensor_bytes": 19681920, "serialized_payload_bytes": 19716076, "side_information_bytes": 34156, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 27.869292069226503, "doc_prefill_ms": 308.5541669279337, "compress_ms": 18.7781669665128, "serialize_ms": 8.690916933119297, "load_ms": 1.4646250056102872, "receiver_prefill_ms": 0.0, "query_prefill_ms": 30.344999977387488, "ttft_ms": 30.344999977387488, "decode_ms": 122.02841695398092}, "total_wall_ms": 155.62674996908754, "ttft_ms": 30.344999977387488, "input_usage": {"receiver_prefix_tokens": 2010, "dense_cache_bytes": 74096640, "query_tokens": 38}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6983204864, "backend_memory": {"mlx_active_bytes": 6290361376, "mlx_peak_bytes": 6340107432, "mlx_cache_bytes": 9699874185, "process_rss_bytes": 6983204864}, "peak_prefill_memory": 7048478768, "peak_decode_memory": 6340107432, "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.log", "payload_hash": "7d69bc9e9fb081ba659e5e33c86d2bce4d329a5a3dbc4c317ae3342eb962c6d0", "output_hash": "48d8b48be3dac15e3a879049c76d1150b48d5cfd634a79a298cef143ea8a97c3"}77{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "b8d8e634e61d167ebc87181e", "attempt_id": "481c6ed42eac", "run_group_id": "E0_smoke:A0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:34.241172Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 73, "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": 0.011124997399747372, "decode_payload_ms": 0.0, "receiver_prefill_ms": 44.282374903559685, "ttft_ms": 19.709625048562884, "decode_ms": 20.926458993926644}, "total_wall_ms": 85.48883290495723, "ttft_ms": 19.709625048562884, "input_usage": {"receiver_prompt_tokens": 73}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6701006848, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6245949864, "mlx_cache_bytes": 172412400, "process_rss_bytes": 6701006848}, "peak_prefill_memory": null, "peak_decode_memory": 6245949864, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "exec:NameError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}78{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "826224a74ebf0be97179de8c", "attempt_id": "6aea9004d9cf", "run_group_id": "E0_smoke:A1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:34.374957Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 2020, "message_tokens": 1937, "message_utf8_bytes": 8125, "cache_tensor_bytes": null, "serialized_payload_bytes": 8125, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.02150004729628563, "decode_payload_ms": 0.0, "receiver_prefill_ms": 295.2367920661345, "ttft_ms": 14.32908303104341, "decode_ms": 1010.4336669901386}, "total_wall_ms": 1323.3462499920279, "ttft_ms": 14.32908303104341, "input_usage": {"receiver_prompt_tokens": 2020}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701006848, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7052050480, "mlx_cache_bytes": 1068830192, "process_rss_bytes": 6701006848}, "peak_prefill_memory": null, "peak_decode_memory": 7052050480, "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['region'] == 'Sud':\n continue\n if r['units", "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.log", "payload_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "output_hash": "a4b5ee1863268030f5b49a1b3ed1224905e65c6b49f3a7ab91a764f8de64d358"}79{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "b723bddfa5449bee38ed407a", "attempt_id": "4a8fdefb533f", "run_group_id": "E0_smoke:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:35.745633Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 1937}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 604, "message_tokens": 516, "message_utf8_bytes": 2156, "cache_tensor_bytes": null, "serialized_payload_bytes": 2156, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.090957947075367, "decode_payload_ms": 0.0, "receiver_prefill_ms": 93.57858297880739, "ttft_ms": 23.513957974500954, "decode_ms": 911.6655830293894}, "total_wall_ms": 1030.1828749943525, "ttft_ms": 23.513957974500954, "input_usage": {"receiver_prompt_tokens": 604}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701006848, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6569799768, "mlx_cache_bytes": 1469386224, "process_rss_bytes": 6701006848}, "peak_prefill_memory": null, "peak_decode_memory": 6569799768, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n total_revenue = 0\n for row in rows:\n if row['region'] != 'Sud' and row['units'] >= 2 and row['shipped_days'] <= ", "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.log", "payload_hash": "5668e3e1f062ec6fbeef2cd13bd6309d297d591e881d4bbc87cf51b2a5cfaf9f", "output_hash": "49013de476d48dbb78217dba376506dfae969e7e8e9e11415afad7ea2f53b479"}80{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "162117ede3591cddd228532b", "attempt_id": "e08d4687822b", "run_group_id": "E0_smoke:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:36.823140Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 500, "n_sentences": 3}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 584, "message_tokens": 499, "message_utf8_bytes": 1474, "cache_tensor_bytes": null, "serialized_payload_bytes": 1474, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2.0204579923301935, "decode_payload_ms": 0.0, "receiver_prefill_ms": 92.08316600415856, "ttft_ms": 20.726916030980647, "decode_ms": 923.1244999682531}, "total_wall_ms": 1037.3579170554876, "ttft_ms": 20.726916030980647, "input_usage": {"receiver_prompt_tokens": 584}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701056000, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6559985752, "mlx_cache_bytes": 1824361968, "process_rss_bytes": 6701056000}, "peak_prefill_memory": null, "peak_decode_memory": 6559985752, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n total_revenue = 0\n for row in rows:\n if row['region'] == 'Sud' or row['units'] < 2 or row['returned']:\n continue\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.log", "payload_hash": "0d0b68d8ccb32536ba23b7d25e38a4021a853137ff08f20815b4c3d2b9b45d64", "output_hash": "99475af42ec047e0ce1a7d674ae59578eb16d871e0e2d91661b164982ead65f8"}81{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "146dc78b2613ad3e8f9ca821", "attempt_id": "6654ee0f823d", "run_group_id": "E0_smoke:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:37.904166Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 506, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 590, "message_tokens": 506, "message_utf8_bytes": 2318, "cache_tensor_bytes": null, "serialized_payload_bytes": 2318, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 1.4914999483153224, "decode_payload_ms": 0.0, "receiver_prefill_ms": 98.94125000573695, "ttft_ms": 16.27620798535645, "decode_ms": 934.4471250660717}, "total_wall_ms": 1052.851833985187, "ttft_ms": 16.27620798535645, "input_usage": {"receiver_prompt_tokens": 590}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701056000, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6564016216, "mlx_cache_bytes": 2183368176, "process_rss_bytes": 6701056000}, "peak_prefill_memory": null, "peak_decode_memory": 6564016216, "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' or r['units'] < 2 or r['shipped_days'] > ", "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.log", "payload_hash": "32a2539d2b6ee4c06cee34a3497e76891f4e908fa56a9f3359ae6958be2a1961", "output_hash": "740d0b6993023215fc488fca5404cbe262f0405d7e3192da63ee24a24b6a699b"}82{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "6f8802cbd5053f88195deae0", "attempt_id": "ee7348e705c7", "run_group_id": "E0_smoke:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:49.622450Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 600, "message_tokens": 512, "message_utf8_bytes": 1493, "cache_tensor_bytes": null, "serialized_payload_bytes": 1493, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 10619.876333978027, "decode_payload_ms": 0.0, "receiver_prefill_ms": 107.23908396903425, "ttft_ms": 19.994916045106947, "decode_ms": 916.7372090741992}, "total_wall_ms": 1045.7014170242473, "ttft_ms": 19.994916045106947, "input_usage": {"receiver_prompt_tokens": 600, "sender_input_tokens": 2053, "sender_output_tokens": 512, "sender_prefill_ms": 348.635541042313, "sender_ttft_ms": 21.78091707173735, "sender_decode_ms": 10246.84870801866}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701105152, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6582726744, "mlx_cache_bytes": 3477464560, "process_rss_bytes": 6701105152}, "peak_prefill_memory": null, "peak_decode_memory": 6582726744, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n total_revenue = 0\n for row in rows:\n if row['region'] != 'Sud' and row['units'] >= 2 and not row['returned'] and row['", "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.log", "payload_hash": "a5360f49c84c5d88602af0cacb8eb14a906d47404d247d72e28a9c373feb8bd9", "output_hash": "ad6a28cb17112d61c6e0861769c09b6aca4ac8b11382ab844d0d76d38aeeeddd"}83{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "dff5b8ff7f0b562672df6bac", "attempt_id": "4af52d4fb1cc", "run_group_id": "E0_smoke:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:52.967207Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "n_facts": 1, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 165, "message_tokens": 67, "message_utf8_bytes": 238, "cache_tensor_bytes": null, "serialized_payload_bytes": 238, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2254.3724169954658, "decode_payload_ms": 0.0, "receiver_prefill_ms": 43.76500006765127, "ttft_ms": 20.686833071522415, "decode_ms": 18.83375004399568}, "total_wall_ms": 84.36074992641807, "ttft_ms": 20.686833071522415, "input_usage": {"receiver_prompt_tokens": 165, "sender_input_tokens": 2081, "sender_output_tokens": 85, "sender_prefill_ms": 492.3774159979075, "sender_ttft_ms": 25.297958054579794, "sender_decode_ms": 1734.3169170198962}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6701236224, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6314550016, "mlx_cache_bytes": 3624036480, "process_rss_bytes": 6701236224}, "peak_prefill_memory": null, "peak_decode_memory": 6314550016, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "unknown", "evidence_artifact": {"n_facts": 1, "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": "exec:NameError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "c42d3913024ae8df3e3c52d4d39f2ffe452760aa6268f9e8a4cd162fdc0c1244", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}84{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c11304744694f15ee8ad5b33", "attempt_id": "072e89355803", "run_group_id": "E0_smoke:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:55.240687Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 214, "message_tokens": 130, "message_utf8_bytes": 103, "cache_tensor_bytes": null, "serialized_payload_bytes": 103, "side_information_bytes": 0, "fetched_bytes": 269, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 2144.001582986675, "decode_payload_ms": 0.0, "receiver_prefill_ms": 49.391667009331286, "ttft_ms": 20.21337498445064, "decode_ms": 926.9428750267252}, "total_wall_ms": 997.4543750286102, "ttft_ms": 20.21337498445064, "input_usage": {"receiver_prompt_tokens": 214, "sender_input_tokens": 2081, "sender_output_tokens": 85, "sender_prefill_ms": 341.33658302016556, "sender_ttft_ms": 22.545540938153863, "sender_decode_ms": 1777.7792499400675}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701236224, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6353527748, "mlx_cache_bytes": 3800132564, "process_rss_bytes": 6701236224}, "peak_prefill_memory": null, "peak_decode_memory": 6353527748, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n total_revenue = 0\n for row in rows:\n price = row['unit_price'] * (1 - row['discount_pct'] / 100)\n if row['returned", "evidence_artifact": {"lookups": 1, "fetched_bytes": 269, "retrieved_refs": 1}, "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.log", "payload_hash": "1ca01c6841ec89d2df6a744602238891e2a504aadf6d34de0cd09f8e803fe6dc", "output_hash": "1866ddef1765909117151568b3585703a3a42efe40e7c57f45cb199860548258"}85{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "56ea44a15f71c558c2dced6e", "attempt_id": "caaced348dec", "run_group_id": "E0_smoke:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:56.283336Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A7", "implementation_fidelity": "custom", "compression_config": {"codec": "zstd", "realized": {"codec": "zstd", "ratio": 5.879160636758321}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 2020, "message_tokens": 1937, "message_utf8_bytes": 8125, "cache_tensor_bytes": null, "serialized_payload_bytes": 1382, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 0.09729096200317144, "decode_payload_ms": 0.018749968148767948, "receiver_prefill_ms": 294.89733395166695, "ttft_ms": 14.12741607055068, "decode_ms": 1023.5364160034806}, "total_wall_ms": 1336.8795829592273, "ttft_ms": 14.12741607055068, "input_usage": {"receiver_prompt_tokens": 2020}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6701236224, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7052050480, "mlx_cache_bytes": 3800132564, "process_rss_bytes": 6701236224}, "peak_prefill_memory": null, "peak_decode_memory": 7052050480, "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['region'] == 'Sud':\n continue\n if r['units", "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.log", "payload_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "output_hash": "a4b5ee1863268030f5b49a1b3ed1224905e65c6b49f3a7ab91a764f8de64d358"}86{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "da82041b0960ddc3a14c4229", "attempt_id": "6a38b839a652", "run_group_id": "E0_smoke:B0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:58.001090Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6320513032}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 72843264, "serialized_payload_bytes": 72859340, "side_information_bytes": 16076, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 333.8079579407349, "doc_prefill_ms": 309.61087497416884, "compress_ms": 2.533124992623925, "serialize_ms": 17.797374981455505, "load_ms": 2.209541038610041, "receiver_prefill_ms": 0.0, "query_prefill_ms": 49.67045795638114, "ttft_ms": 49.67045795638114, "decode_ms": 1017.886417103}, "total_wall_ms": 1071.5985000133514, "ttft_ms": 49.67045795638114, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6847250432, "backend_memory": {"mlx_active_bytes": 6397190152, "mlx_peak_bytes": 6449848672, "mlx_cache_bytes": 4718079109, "process_rss_bytes": 6847250432}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6449848672, "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['region'] == 'Sud':\n continue\n if r['units", "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.log", "payload_hash": "698a195b26016f12bd71d6631fda0686907c1fdcb84c16df4296b26693b09e5c", "output_hash": "a4b5ee1863268030f5b49a1b3ed1224905e65c6b49f3a7ab91a764f8de64d358"}87{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "bbd615e60e849d8b1a7ba1ac", "attempt_id": "46733e8c5df8", "run_group_id": "E0_smoke:B1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:27:59.142860Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6320513032}, "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": "08df6c56032443d5", "random_seed": 0, "source_tokens_sender": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 72843264, "serialized_payload_bytes": 72859368, "side_information_bytes": 16104, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 24.76350008510053, "doc_prefill_ms": 309.61087497416884, "compress_ms": 2.834332990460098, "serialize_ms": 21.69116702862084, "load_ms": 12.23729201592505, "receiver_prefill_ms": 0.0, "query_prefill_ms": 40.432416019029915, "ttft_ms": 40.432416019029915, "decode_ms": 1000.5399170331657}, "total_wall_ms": 1054.9829159863293, "ttft_ms": 40.432416019029915, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6920404992, "backend_memory": {"mlx_active_bytes": 6397190152, "mlx_peak_bytes": 6449848560, "mlx_cache_bytes": 4718079109, "process_rss_bytes": 6920404992}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6449848560, "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['region'] == 'Sud':\n continue\n if r['units", "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.log", "payload_hash": "2c13aad81bcd8dfdb14c874ddc3a115036f4e8d9db3242e3aa526e85a72a8286", "output_hash": "a4b5ee1863268030f5b49a1b3ed1224905e65c6b49f3a7ab91a764f8de64d358"}88{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "d0d767d6b99935891bed0b25", "attempt_id": "cf27b3f98bac", "run_group_id": "E0_smoke:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:00.269067Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6286408072}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 38697984, "serialized_payload_bytes": 38732174, "side_information_bytes": 34190, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 26.633040979504585, "doc_prefill_ms": 309.61087497416884, "compress_ms": 13.843290973454714, "serialize_ms": 12.345083057880402, "load_ms": 2.3097090888768435, "receiver_prefill_ms": 0.0, "query_prefill_ms": 24.407291086390615, "ttft_ms": 24.407291086390615, "decode_ms": 1126.3775830157101}, "total_wall_ms": 1154.8897090833634, "ttft_ms": 24.407291086390615, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6958333952, "backend_memory": {"mlx_active_bytes": 6330349960, "mlx_peak_bytes": 6395258492, "mlx_cache_bytes": 5054269957, "process_rss_bytes": 6958333952}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6395258492, "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':\n continue\n if r['units'] < 2:\n continue\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.log", "payload_hash": "86fd69e1ab032c32583a0b7f11de3578bace1807d2de39b464d21bd2715100fa", "output_hash": "c03c392e692f4c667997049602f7e27418e41f00feeb390a815250c0569c1b13"}89{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "b0e0b0cdf8a9e8bf185f2ee9", "attempt_id": "e3d8c7bde859", "run_group_id": "E0_smoke:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:01.493320Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6268525576}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 20487168, "serialized_payload_bytes": 20521220, "side_information_bytes": 34052, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 22.63975003734231, "doc_prefill_ms": 309.61087497416884, "compress_ms": 13.28904100228101, "serialize_ms": 8.920374908484519, "load_ms": 2.213416970334947, "receiver_prefill_ms": 0.0, "query_prefill_ms": 33.245792030356824, "ttft_ms": 33.245792030356824, "decode_ms": 1108.6429170100018}, "total_wall_ms": 1146.063124993816, "ttft_ms": 33.245792030356824, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6960431104, "backend_memory": {"mlx_active_bytes": 6294297608, "mlx_peak_bytes": 6354684588, "mlx_cache_bytes": 5121994885, "process_rss_bytes": 6960431104}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6354684588, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "user\nunknown\n the the the\n document\n document the\n the\n\n the The existing\n the\n\n\n the The\n\n\n the the the\n the the the, the the the the The the the The\n The the", "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": {"correct": 0.0, "pass_rate": 0.0, "error": "exec:IndentationError"}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "ca347fd0215673b4a988d4223cdd6c3b690c3e1c9eb09e181f013f0778625d27", "output_hash": "c02cea32658f86423a17c812c900737ca47ebf057e88e9371d3fa6d2eff848a6"}90{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "90260663756f15d8ab415e67", "attempt_id": "682b8fe93539", "run_group_id": "E0_smoke:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:02.701867Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 1976, "keep": 494, "compress_ms": 7.7032080153003335}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 18210816, "serialized_payload_bytes": 18226732, "side_information_bytes": 15916, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 14.727665926329792, "doc_prefill_ms": 309.61087497416884, "compress_ms": 7.759916945360601, "serialize_ms": 6.733249989338219, "load_ms": 0.9612080175429583, "receiver_prefill_ms": 0.0, "query_prefill_ms": 32.56879199761897, "ttft_ms": 32.56879199761897, "decode_ms": 855.7253750041127}, "total_wall_ms": 891.3752499502152, "ttft_ms": 32.56879199761897, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 44}, "provider_cached_usage": null, "process_memory": 6964920320, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6329884912, "mlx_cache_bytes": 5153287301, "process_rss_bytes": 6964920320}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6329884912, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n total_revenue = 0\n for row in rows:\n if row['status'] == 'completed':\n total_revenue += row['amount']\n return total_revenue", "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.log", "payload_hash": "77876ae624b46c34b40953b0b294518e8694fcb2fbdff1665ed3871727ddf56f", "output_hash": "c1a9a621f1cfa430e5d57319c441f0b3699df1bdd0916d47d16bd8d3b636329d"}91{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "faf3c5252bcbb25b131280a7", "attempt_id": "58c23501aa9f", "run_group_id": "E0_smoke:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:03.653051Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 1976, "keep": 494, "compress_ms": 6.551417056471109}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 18210816, "serialized_payload_bytes": 18226726, "side_information_bytes": 15910, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 12.743625091388822, "doc_prefill_ms": 309.61087497416884, "compress_ms": 6.587499985471368, "serialize_ms": 5.920208059251308, "load_ms": 0.679041026160121, "receiver_prefill_ms": 0.0, "query_prefill_ms": 29.208042076788843, "ttft_ms": 29.208042076788843, "decode_ms": 932.1196250384673}, "total_wall_ms": 963.8700410723686, "ttft_ms": 29.208042076788843, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6979092480, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6329884912, "mlx_cache_bytes": 5153287301, "process_rss_bytes": 6979092480}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6329884912, "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'] != 'S' and row['region'] != 'Centre':\n total += row['units'] * row['price", "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.log", "payload_hash": "4dbdad308845b08c8ddd8b1fd3d33a76db9d3416f55bc59b4a5b91ea60ddf302", "output_hash": "1b45a1a25e468a6175f2069e3767b3b695f311b3606ae8a8aa1c17d84cd9c6a7"}92{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "5949397e740909d42f727519", "attempt_id": "06844a495723", "run_group_id": "E0_smoke:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:04.665719Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "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": 1976, "keep": 494, "window_tokens": 44, "compress_ms": 58.248165994882584}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 18210816, "serialized_payload_bytes": 18226772, "side_information_bytes": 15956, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 65.47891697846353, "doc_prefill_ms": 309.61087497416884, "compress_ms": 60.018207994289696, "serialize_ms": 5.194208002649248, "load_ms": 0.6166669772937894, "receiver_prefill_ms": 0.0, "query_prefill_ms": 23.563917027786374, "ttft_ms": 23.563917027786374, "decode_ms": 943.9251670846716}, "total_wall_ms": 1035.5242089135572, "ttft_ms": 23.563917027786374, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6979223552, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6329884912, "mlx_cache_bytes": 5256199293, "process_rss_bytes": 6979223552}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6329884912, "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'] == 'Shud' or len(r['units']) < 2:\n continue\n if r['", "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.log", "payload_hash": "c4eae48b1e15863a34266e4931e222e4c99ef00239336c8a4747c8ecf10da1ad", "output_hash": "eee59974af47160590a101092589ed6092783b0739bc4edfcc774b7d9be5d4cc"}93{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "4fc13be8620c3c81f55b6e3c", "attempt_id": "838ba2ff669e", "run_group_id": "E0_smoke:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:05.814399Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6266249224}, "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": 1976, "keep": 494, "window_tokens": 19, "compress_ms": 58.98000008892268}}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 18210816, "serialized_payload_bytes": 18226771, "side_information_bytes": 15955, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 65.83225005306304, "doc_prefill_ms": 309.61087497416884, "compress_ms": 59.280334040522575, "serialize_ms": 6.3120829872787, "load_ms": 0.8338750340044498, "receiver_prefill_ms": 0.0, "query_prefill_ms": 29.883750015869737, "ttft_ms": 29.883750015869737, "decode_ms": 947.136375005357}, "total_wall_ms": 979.7340830555186, "ttft_ms": 29.883750015869737, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6979289088, "backend_memory": {"mlx_active_bytes": 6288662536, "mlx_peak_bytes": 6329884912, "mlx_cache_bytes": 5266635901, "process_rss_bytes": 6979289088}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6329884912, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "def net_revenue(rows):\n rows = [r for r in rows if r['units'] >= 2 and r['region'] != 'S']\n rows = [r for r in rows if r['shipped_days']", "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.log", "payload_hash": "c2c7ecc64c9caf7ce1f6ad2de4912a25a929a2366bc0119fd9f498ffff62858a", "output_hash": "a18179203926d78856727d2c151d583a3bfd58bcc61dc42e63a72dbf44494cba"}94{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c46cf3e234e112a0f5f8112b", "attempt_id": "41b243f2a98e", "run_group_id": "E0_smoke:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:06.840622Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6247374856}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware"}, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": null, "message_tokens": null, "message_utf8_bytes": null, "cache_tensor_bytes": null, "serialized_payload_bytes": null, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {}, "total_wall_ms": 72.07979203667492, "ttft_ms": null, "input_usage": {}, "output_usage": {}, "provider_cached_usage": null, "process_memory": null, "backend_memory": null, "peak_prefill_memory": null, "peak_decode_memory": null, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": null, "evidence_artifact": null, "reference_key_id": "keys/exec/exec_00101_2000.json", "task_scores": null, "status": "implementation_error", "error_code": "ValueError: [broadcast_shapes] Shapes (44,974) and (1,16,44,949) cannot be broadcast.", "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": null, "output_hash": null}95{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "2ec276c68d8afd8d728c36d2", "attempt_id": "99963ae12b8e", "run_group_id": "E0_smoke:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:06.959128Z", "task_family": "exec", "document_id": "exec_00101_2000", "document_hash": "932bac511f2c5ee3faf8c1f37b853fcd2be373db29c6a84b2d7f8c3ab71ee6f9", "question_id": "q00_exec", "split": "dev", "cluster_id": "exec_00101_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6267434784}, "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": 1976, "keep": 988, "compress_ms": 8.043541922233999, "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": 1937, "source_tokens_receiver": 1937, "query_tokens": 44, "message_tokens": 1976, "message_utf8_bytes": 8125, "cache_tensor_bytes": 19348992, "serialized_payload_bytes": 19382643, "side_information_bytes": 33651, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 25.42837499640882, "doc_prefill_ms": 309.61087497416884, "compress_ms": 16.244541970081627, "serialize_ms": 8.818165981210768, "load_ms": 1.8096249550580978, "receiver_prefill_ms": 0.0, "query_prefill_ms": 30.5376669857651, "ttft_ms": 30.5376669857651, "decode_ms": 1107.7149999327958}, "total_wall_ms": 1142.3345000948757, "ttft_ms": 30.5376669857651, "input_usage": {"receiver_prefix_tokens": 1976, "dense_cache_bytes": 72843264, "query_tokens": 44}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 6999080960, "backend_memory": {"mlx_active_bytes": 6290392416, "mlx_peak_bytes": 6345574196, "mlx_cache_bytes": 5288831909, "process_rss_bytes": 6999080960}, "peak_prefill_memory": 7034568616, "peak_decode_memory": 6345574196, "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 d = r['discount", "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.log", "payload_hash": "6cd4d317f609771874f10328ee8c9d0593582762cc86c71221870cbe34b03bf2", "output_hash": "11ef43e7a25672ac1b5bda0cb1f1c298234481cd58e721fb63925aba7d5c84b9"}96{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "ada2dd091bdea89a3739786c", "attempt_id": "19610da4e3c9", "run_group_id": "E0_smoke:A0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:08.198628Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 60, "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": 0.01325004268437624, "decode_payload_ms": 0.0, "receiver_prefill_ms": 22.8534999769181, "ttft_ms": 19.033625023439527, "decode_ms": 18.955833977088332}, "total_wall_ms": 61.44804204814136, "ttft_ms": 19.033625023439527, "input_usage": {"receiver_prompt_tokens": 60}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6773866496, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6224191848, "mlx_cache_bytes": 131829180, "process_rss_bytes": 6773866496}, "peak_prefill_memory": null, "peak_decode_memory": 6224191848, "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.log", "payload_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}97{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "3cd7ce88f7932e2fe3a5dca6", "attempt_id": "ff9af49a194b", "run_group_id": "E0_smoke:A1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:08.286310Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 3314, "message_tokens": 3244, "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": 0.011375057511031628, "decode_payload_ms": 0.0, "receiver_prefill_ms": 623.0147909373045, "ttft_ms": 22.94987498316914, "decode_ms": 757.846082909964}, "total_wall_ms": 1410.354790976271, "ttft_ms": 22.94987498316914, "input_usage": {"receiver_prompt_tokens": 3314}, "output_usage": {"output_tokens": 34}, "provider_cached_usage": null, "process_memory": 6773866496, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7054791664, "mlx_cache_bytes": 1964671360, "process_rss_bytes": 6773866496}, "peak_prefill_memory": null, "peak_decode_memory": 7054791664, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD is an extension of the NetVLAD approach, adding Ghost clusters to map noisy or irrelevant content into ghost clusters, which are not included during feature aggregation.", "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.log", "payload_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "output_hash": "ba5fb8f0ad59cb232cd6f80c40ee8d80776fb7390bc885bdbaae680052882740"}98{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "e9ea83259bd11521d23b5992", "attempt_id": "cda8cd210413", "run_group_id": "E0_smoke:A2|budget_tokens=512", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:09.724185Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A2", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "realized": {"budget_tokens": 512, "source_tokens": 3244}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 591, "message_tokens": 516, "message_utf8_bytes": 2729, "cache_tensor_bytes": null, "serialized_payload_bytes": 2729, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 3.2423330703750253, "decode_payload_ms": 0.0, "receiver_prefill_ms": 101.38687491416931, "ttft_ms": 27.95499993953854, "decode_ms": 100.74745898600668}, "total_wall_ms": 231.90870904363692, "ttft_ms": 27.95499993953854, "input_usage": {"receiver_prompt_tokens": 591}, "output_usage": {"output_tokens": 5}, "provider_cached_usage": null, "process_memory": 6773866496, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6564311128, "mlx_cache_bytes": 2357264768, "process_rss_bytes": 6773866496}, "peak_prefill_memory": null, "peak_decode_memory": 6564311128, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD pooling 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.log", "payload_hash": "11ac585095e23aad2dc25c5d250ea6fc439122cd288e6814f52c1cea040db97b", "output_hash": "b396b6ce678924171263f2c16423a6fb5ea85d772a5b7e43ad73b71e42b11ad7"}99{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "2c10d09f655cb2217d462ef3", "attempt_id": "fb2521d6b85c", "run_group_id": "E0_smoke:A3|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:09.990150Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "blind", "realized": {"budget_tokens": 512, "realized_tokens": 500, "n_sentences": 11}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 571, "message_tokens": 500, "message_utf8_bytes": 2058, "cache_tensor_bytes": null, "serialized_payload_bytes": 2058, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 4.259041976183653, "decode_payload_ms": 0.0, "receiver_prefill_ms": 102.35675005242229, "ttft_ms": 26.3324580155313, "decode_ms": 24.861750076524913}, "total_wall_ms": 155.5670410161838, "ttft_ms": 26.3324580155313, "input_usage": {"receiver_prompt_tokens": 571}, "output_usage": {"output_tokens": 1}, "provider_cached_usage": null, "process_memory": 6773866496, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6552219736, "mlx_cache_bytes": 2704474496, "process_rss_bytes": 6773866496}, "peak_prefill_memory": null, "peak_decode_memory": 6552219736, "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.log", "payload_hash": "a804cda2443cf12a08e11e226234585e0d1edf60d020061934488a33516d413b", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}100{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "e5a31efff5f91b7eb69a8bc1", "attempt_id": "d3c27d3f5d40", "run_group_id": "E0_smoke:A3|budget_tokens=512|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:10.174696Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "weight_precision": "bf16", "method_id": "A3", "implementation_fidelity": "custom", "compression_config": {"budget_tokens": 512, "access": "aware", "realized": {"budget_tokens": 512, "realized_tokens": 506, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 578, "message_tokens": 507, "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": 1.6516250325366855, "decode_payload_ms": 0.0, "receiver_prefill_ms": 122.30041704606265, "ttft_ms": 17.13062508497387, "decode_ms": 417.9142080247402}, "total_wall_ms": 560.8353751013055, "ttft_ms": 17.13062508497387, "input_usage": {"receiver_prompt_tokens": 578}, "output_usage": {"output_tokens": 19}, "provider_cached_usage": null, "process_memory": 6773866496, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6557036632, "mlx_cache_bytes": 3041952128, "process_rss_bytes": 6773866496}, "peak_prefill_memory": null, "peak_decode_memory": 6557036632, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension to VLAD where hard assignment is replaced with soft assignment for end-to-end training.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.27027027027027023, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "785023803d7f2c38c80debcdc8309ffa1c94e3c99227c52a36e7e66d830d2d9e", "output_hash": "e746ed4fb6926b79617f224cc269a459de798a399cfc39ed7c9b314e07455f73"}101{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "7ee46ca5b5986914ad0f70a5", "attempt_id": "27e4e6a2dd08", "run_group_id": "E0_smoke:A4|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:16.132554Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 294, "message_tokens": 220, "message_utf8_bytes": 1044, "cache_tensor_bytes": null, "serialized_payload_bytes": 1044, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 5371.418667025864, "decode_payload_ms": 0.0, "receiver_prefill_ms": 71.67716696858406, "ttft_ms": 19.78166599292308, "decode_ms": 70.39725000504404}, "total_wall_ms": 163.06179203093052, "ttft_ms": 19.78166599292308, "input_usage": {"receiver_prompt_tokens": 294, "sender_input_tokens": 3360, "sender_output_tokens": 220, "sender_prefill_ms": 656.0712079517543, "sender_ttft_ms": 15.746999997645617, "sender_decode_ms": 4695.432165986858}, "output_usage": {"output_tokens": 4}, "provider_cached_usage": null, "process_memory": 6773899264, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6424421636, "mlx_cache_bytes": 3801168528, "process_rss_bytes": 6773899264}, "peak_prefill_memory": null, "peak_decode_memory": 6424421636, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Ghost-VLAD", "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.log", "payload_hash": "3b08a9dd9882d778138853f9b9a6a55c7176ad67e2db289645e13b8fc1bac590", "output_hash": "4a81758367f5a2ca4e9aa1c032ddd94e54a15042d670c320c4955ecf300ae450"}102{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "fa7aaf225eb9ea8ec9a07212", "attempt_id": "e68901764e49", "run_group_id": "E0_smoke:A5|budget_tokens=512|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:24.829477Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 1, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 306, "message_tokens": 221, "message_utf8_bytes": 756, "cache_tensor_bytes": null, "serialized_payload_bytes": 756, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 8506.694042007439, "decode_payload_ms": 0.0, "receiver_prefill_ms": 55.022082990035415, "ttft_ms": 21.521249902434647, "decode_ms": 58.01579204853624}, "total_wall_ms": 135.69395896047354, "ttft_ms": 21.521249902434647, "input_usage": {"receiver_prompt_tokens": 306, "sender_input_tokens": 3388, "sender_output_tokens": 380, "sender_prefill_ms": 809.7484159516171, "sender_ttft_ms": 25.65774996764958, "sender_decode_ms": 7667.614832986146}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 6773932032, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6434170164, "mlx_cache_bytes": 4717179968, "process_rss_bytes": 6773932032}, "peak_prefill_memory": null, "peak_decode_memory": 6434170164, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "pooling method", "evidence_artifact": {"n_facts": 5, "unresolved_quotes": 1, "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.log", "payload_hash": "3bb6e01e5b80c84d0441a0b53d50795f440126a2d273b098a4adc01abc60175f", "output_hash": "8c7e3b1576d203644fb74ba50478132796f7da6038f8971317fa262590fd6536"}103{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "fc7f1dec81af51ed135642f5", "attempt_id": "7ca101f1952a", "run_group_id": "E0_smoke:A6|budget_tokens=512|max_fetch_bytes=2000|max_lookups=6|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:33.574996Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 4}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 544, "message_tokens": 473, "message_utf8_bytes": 371, "cache_tensor_bytes": null, "serialized_payload_bytes": 371, "side_information_bytes": 0, "fetched_bytes": 1373, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 8585.026083979756, "decode_payload_ms": 0.0, "receiver_prefill_ms": 104.83375005424023, "ttft_ms": 22.171457996591926, "decode_ms": 62.47520900797099}, "total_wall_ms": 190.89829095173627, "ttft_ms": 22.171457996591926, "input_usage": {"receiver_prompt_tokens": 544, "sender_input_tokens": 3388, "sender_output_tokens": 380, "sender_prefill_ms": 719.3035829113796, "sender_ttft_ms": 25.42624995112419, "sender_decode_ms": 7836.96520794183}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 6773915648, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 6535016536, "mlx_cache_bytes": 5052789824, "process_rss_bytes": 6773915648}, "peak_prefill_memory": null, "peak_decode_memory": 6535016536, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "pooling method", "evidence_artifact": {"lookups": 4, "fetched_bytes": 1373, "retrieved_refs": 4}, "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.log", "payload_hash": "15bd5c2c7fa5c1256d4044abb684ec5f8ec847c3e301d4402dc3bc463138b521", "output_hash": "8c7e3b1576d203644fb74ba50478132796f7da6038f8971317fa262590fd6536"}104{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "9c0b36e54acecbc04d506a33", "attempt_id": "79213f5e6476", "run_group_id": "E0_smoke:A7|codec=zstd", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:33.790608Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6171877384}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 3314, "message_tokens": 3244, "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": 0.09345798753201962, "decode_payload_ms": 0.02058397512882948, "receiver_prefill_ms": 704.8352500423789, "ttft_ms": 24.021124932914972, "decode_ms": 774.4359999196604}, "total_wall_ms": 1509.2177080223337, "ttft_ms": 24.021124932914972, "input_usage": {"receiver_prompt_tokens": 3314}, "output_usage": {"output_tokens": 34}, "provider_cached_usage": null, "process_memory": 6773915648, "backend_memory": {"mlx_active_bytes": 6171877384, "mlx_peak_bytes": 7054791664, "mlx_cache_bytes": 5052789824, "process_rss_bytes": 6773915648}, "peak_prefill_memory": null, "peak_decode_memory": 7054791664, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD is an extension of the NetVLAD approach, adding Ghost clusters to map noisy or irrelevant content into ghost clusters, which are not included during feature aggregation.", "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.log", "payload_hash": "1704f1d50b2554aebd4feef979b444ef2634aca15e51d3608364aaf7b146ae43", "output_hash": "ba5fb8f0ad59cb232cd6f80c40ee8d80776fb7390bc885bdbaae680052882740"}105{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "ee0a4bf8945963b7984eda04", "attempt_id": "7a5edbe6a2aa", "run_group_id": "E0_smoke:B0", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:35.959615Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6416064520}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 121024512, "serialized_payload_bytes": 121040621, "side_information_bytes": 16109, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 635.4355829535052, "doc_prefill_ms": 601.0837500216439, "compress_ms": 4.678208031691611, "serialize_ms": 23.705999949015677, "load_ms": 2.692666952498257, "receiver_prefill_ms": 0.0, "query_prefill_ms": 62.39358300808817, "ttft_ms": 62.39358300808817, "decode_ms": 771.4831250486895}, "total_wall_ms": 839.4441249547526, "ttft_ms": 62.39358300808817, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 34}, "provider_cached_usage": null, "process_memory": 7016480768, "backend_memory": {"mlx_active_bytes": 6539927560, "mlx_peak_bytes": 6590084908, "mlx_cache_bytes": 5976129213, "process_rss_bytes": 7016480768}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6590084908, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD is an extension of the NetVLAD approach, adding Ghost clusters to map noisy or irrelevant content into ghost clusters, which are not included during feature aggregation.", "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.log", "payload_hash": "e72b7ab2934cfcf6888dcc2d829003003dc376d34928371486fae694c1a2098c", "output_hash": "ba5fb8f0ad59cb232cd6f80c40ee8d80776fb7390bc885bdbaae680052882740"}106{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "6d448ed450568948fe73b33b", "attempt_id": "962989a845d3", "run_group_id": "E0_smoke:B1", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:36.848715Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6416064520}, "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": "35aaed2f1f78202e", "random_seed": 0, "source_tokens_sender": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 121024512, "serialized_payload_bytes": 121040649, "side_information_bytes": 16137, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 25.53833299316466, "doc_prefill_ms": 601.0837500216439, "compress_ms": 1.076459069736302, "serialize_ms": 24.271624977700412, "load_ms": 16.446624998934567, "receiver_prefill_ms": 0.0, "query_prefill_ms": 49.789458978921175, "ttft_ms": 49.789458978921175, "decode_ms": 747.1429159631953}, "total_wall_ms": 816.2833329988644, "ttft_ms": 49.789458978921175, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 34}, "provider_cached_usage": null, "process_memory": 7137984512, "backend_memory": {"mlx_active_bytes": 6539927560, "mlx_peak_bytes": 6590084796, "mlx_cache_bytes": 5976129213, "process_rss_bytes": 7137984512}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6590084796, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD is an extension of the NetVLAD approach, adding Ghost clusters to map noisy or irrelevant content into ghost clusters, which are not included during feature aggregation.", "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.log", "payload_hash": "e188c41f1d9a05bc6e14927399c189fe21e3a4e72cabf24975d723a2d32d953f", "output_hash": "ba5fb8f0ad59cb232cd6f80c40ee8d80776fb7390bc885bdbaae680052882740"}107{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "1ac34c36ff3d7315fc796eae", "attempt_id": "d79add9587e3", "run_group_id": "E0_smoke:B2|bits=8", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:37.723313Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6360621064}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 64294272, "serialized_payload_bytes": 64328508, "side_information_bytes": 34236, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 33.56612497009337, "doc_prefill_ms": 601.0837500216439, "compress_ms": 16.29454200156033, "serialize_ms": 16.862374963238835, "load_ms": 3.4387909108772874, "receiver_prefill_ms": 0.0, "query_prefill_ms": 132.63883395120502, "ttft_ms": 132.63883395120502, "decode_ms": 75.75041695963591}, "total_wall_ms": 214.81683303136379, "ttft_ms": 132.63883395120502, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 3}, "provider_cached_usage": null, "process_memory": 7201554432, "backend_memory": {"mlx_active_bytes": 6426681352, "mlx_peak_bytes": 6493745728, "mlx_cache_bytes": 6267740861, "process_rss_bytes": 7201554432}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6493745728, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD", "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.log", "payload_hash": "2a1a43b3fa4a399c34ba6ec7a1917e4c670fbe4963cb057ca7ec0551e351b23d", "output_hash": "75a872242c44bab0506befcac9b6a38c36a90ed87a8b8fbe27f7514cdf9dbb77"}108{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "ca17bd88ada65a286ee0a6f7", "attempt_id": "3187f01cea42", "run_group_id": "E0_smoke:B2|bits=4", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:37.984179Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6329950216}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 34038144, "serialized_payload_bytes": 34072304, "side_information_bytes": 34160, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 22.94916706159711, "doc_prefill_ms": 601.0837500216439, "compress_ms": 11.391667067073286, "serialize_ms": 11.177083011716604, "load_ms": 2.3093329509720206, "receiver_prefill_ms": 0.0, "query_prefill_ms": 143.6609170632437, "ttft_ms": 143.6609170632437, "decode_ms": 1126.990083954297}, "total_wall_ms": 1278.614499955438, "ttft_ms": 143.6609170632437, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 48}, "provider_cached_usage": null, "process_memory": 7232307200, "backend_memory": {"mlx_active_bytes": 6366519304, "mlx_peak_bytes": 6424664597, "mlx_cache_bytes": 6436792893, "process_rss_bytes": 7232307200}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6424664597, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": " answer is is is the map is is the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the theuss the the the the", "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.log", "payload_hash": "1b95c993af3d21a934574f795df3e1fbf79b282247215a9eb48cbf2a848afa55", "output_hash": "2c0f9e0ae3f39ad1661d054a003adda4563e4914e846c6b20e1739fe08202a49"}109{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "0b133b77ac8a96e5c6b5bc99", "attempt_id": "72a86d76f83b", "run_group_id": "E0_smoke:B3|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:39.307416Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6325231624}, "weight_precision": "bf16", "method_id": "B3", "implementation_fidelity": "inspired", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "sink_recent", "keep_frac": 0.25, "T": 3283, "keep": 821, "compress_ms": 8.413915988057852}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 30265344, "serialized_payload_bytes": 30281293, "side_information_bytes": 15949, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 19.421624951064587, "doc_prefill_ms": 601.0837500216439, "compress_ms": 8.4537910297513, "serialize_ms": 10.77312498819083, "load_ms": 1.2885419419035316, "receiver_prefill_ms": 0.0, "query_prefill_ms": 30.25900002103299, "ttft_ms": 30.25900002103299, "decode_ms": 44.62770896498114}, "total_wall_ms": 79.53341701067984, "ttft_ms": 30.25900002103299, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 2}, "provider_cached_usage": null, "process_memory": 7236452352, "backend_memory": {"mlx_active_bytes": 6357082120, "mlx_peak_bytes": 6390658748, "mlx_cache_bytes": 6446230077, "process_rss_bytes": 7236452352}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6390658748, "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.log", "payload_hash": "203c88371d6551640470222a8f0db73f9cca2629b2d98351a486b0cc01f024f0", "output_hash": "aea88d526d067608708536c90844a71e2fdd73002205449a86f1441074ce02df"}110{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "cecbdd65d043b664a2811af6", "attempt_id": "86745d804a03", "run_group_id": "E0_smoke:B4|keep_frac=0.25", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:39.430851Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6325231624}, "weight_precision": "bf16", "method_id": "B4", "implementation_fidelity": "custom", "compression_config": {"keep_frac": 0.25, "realized": {"policy": "random", "keep_frac": 0.25, "T": 3283, "keep": 821, "compress_ms": 7.425334071740508}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 30265344, "serialized_payload_bytes": 30281288, "side_information_bytes": 15944, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 16.988249961286783, "doc_prefill_ms": 601.0837500216439, "compress_ms": 7.470625103451312, "serialize_ms": 9.28033294621855, "load_ms": 0.7437919266521931, "receiver_prefill_ms": 0.0, "query_prefill_ms": 32.686542021110654, "ttft_ms": 32.686542021110654, "decode_ms": 219.86454201396555}, "total_wall_ms": 256.39504101127386, "ttft_ms": 32.686542021110654, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 11}, "provider_cached_usage": null, "process_memory": 7259455488, "backend_memory": {"mlx_active_bytes": 6357082120, "mlx_peak_bytes": 6390658748, "mlx_cache_bytes": 6446230077, "process_rss_bytes": 7259455488}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6390658748, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "An extension of VLAD with additional \"ghost\" clusters", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.588235294117647, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "70ea332320edce996b98525a13cea25477ebb6008fd834fc605091509e59c638", "output_hash": "2186a0d38b03b30a9f490d89c4029f93aed3afbdfe49ce3b728692172ec75684"}111{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "34c653518a2822f0248089b7", "attempt_id": "f3b6dad3ff16", "run_group_id": "E0_smoke:B5|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:39.712620Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6294560776}, "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": 3283, "keep": 821, "window_tokens": 31, "compress_ms": 73.18974996451288}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 30265344, "serialized_payload_bytes": 30281333, "side_information_bytes": 15989, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 83.91400007531047, "doc_prefill_ms": 601.0837500216439, "compress_ms": 76.17241598200053, "serialize_ms": 7.476332946680486, "load_ms": 0.6962079787626863, "receiver_prefill_ms": 0.0, "query_prefill_ms": 23.969750036485493, "ttft_ms": 23.969750036485493, "decode_ms": 469.9488329933956}, "total_wall_ms": 581.5955420257524, "ttft_ms": 23.969750036485493, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 23}, "provider_cached_usage": null, "process_memory": 7261257728, "backend_memory": {"mlx_active_bytes": 6358261768, "mlx_peak_bytes": 6390658748, "mlx_cache_bytes": 6516845253, "process_rss_bytes": 7261257728}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6390658748, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "GhostVLAD is an extension of the NetVLAD approach, adding Ghost clusters to improve aggregation of local features.", "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": {"f1": 0.4, "em": 0.0, "abstained": 0.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": "47e80056bbc1a4eb0bd50907f4df60fa9febc185c53aa9bfb01a998dafb1fe62", "output_hash": "fecf4b3747739da00410fc6decc4ba4dde1d66f25ed88cb4a76dc7d3b1f7a46b"}112{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "963b06874aa12c25afdf0c63", "attempt_id": "6b3a3d3bfe73", "run_group_id": "E0_smoke:B5|keep_frac=0.25|blind", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:40.399242Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6325231624}, "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": 3283, "keep": 821, "window_tokens": 19, "compress_ms": 73.75320896971971}}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 30265344, "serialized_payload_bytes": 30281333, "side_information_bytes": 15989, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 79.70887504052371, "doc_prefill_ms": 601.0837500216439, "compress_ms": 73.89700005296618, "serialize_ms": 5.637041991576552, "load_ms": 1.3112499145790935, "receiver_prefill_ms": 0.0, "query_prefill_ms": 31.88529098406434, "ttft_ms": 31.88529098406434, "decode_ms": 456.10237505752593}, "total_wall_ms": 492.16875003185123, "ttft_ms": 31.88529098406434, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 22}, "provider_cached_usage": null, "process_memory": 7269089280, "backend_memory": {"mlx_active_bytes": 6358261768, "mlx_peak_bytes": 6390658748, "mlx_cache_bytes": 6539504325, "process_rss_bytes": 7269089280}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6390658748, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "Ghost-VLAD approach is a pooling method used for language identification, inspired by recent work on speaker identification.", "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.log", "payload_hash": "47e80056bbc1a4eb0bd50907f4df60fa9febc185c53aa9bfb01a998dafb1fe62", "output_hash": "ba29f94ed96dd49c401ef0be023381ab5ee8b988ed76f46cdc19c5602ac9b29c"}113{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "f7d0a3fc2321b3c9704b89ec", "attempt_id": "d2a08aee8841", "run_group_id": "E0_smoke:B6|keep_frac=0.25|aware", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:40.919206Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6294560776}, "weight_precision": "bf16", "method_id": "B6", "implementation_fidelity": "faithful_reimplementation", "compression_config": {"keep_frac": 0.25, "access": "aware"}, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": null, "message_tokens": null, "message_utf8_bytes": null, "cache_tensor_bytes": null, "serialized_payload_bytes": null, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {}, "total_wall_ms": 87.07641693763435, "ttft_ms": null, "input_usage": {}, "output_usage": {}, "provider_cached_usage": null, "process_memory": null, "backend_memory": null, "peak_prefill_memory": null, "peak_decode_memory": null, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": null, "evidence_artifact": null, "reference_key_id": "keys/public_qasper/lb_qasper_db6c4d611b78c840972b57ee0b245003566b982feaff1084.json", "task_scores": null, "status": "implementation_error", "error_code": "ValueError: [broadcast_shapes] Shapes (31,1574) and (1,16,31,1533) cannot be broadcast.", "retry_of": null, "log_artifact": "runs/logs/E0_smoke.log", "payload_hash": null, "output_hash": null}114{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E0_smoke", "trial_id": "c08a83e61897f15f24d32a73", "attempt_id": "a9fbb7a566b2", "run_group_id": "E0_smoke:B9|bits=8|keep_frac=0.5", "protocol_hash": "unfrozen", "config_hash": "966dc0b4711f65959caf629a7f306c5833596a1dea7d7e43c07a6279909beec3", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:28:41.064575Z", "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/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"sender": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b", "receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {"mlx_active_before": 6327222532}, "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": 3283, "keep": 1642, "compress_ms": 8.948500035330653, "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": 3244, "source_tokens_receiver": 3244, "query_tokens": 31, "message_tokens": 3283, "message_utf8_bytes": 15217, "cache_tensor_bytes": 32156928, "serialized_payload_bytes": 32191192, "side_information_bytes": 34264, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"encode_ms": 33.74208300374448, "doc_prefill_ms": 601.0837500216439, "compress_ms": 20.669832942076027, "serialize_ms": 12.674166937358677, "load_ms": 2.0706249633803964, "receiver_prefill_ms": 0.0, "query_prefill_ms": 23.13250000588596, "ttft_ms": 23.13250000588596, "decode_ms": 386.1410419922322}, "total_wall_ms": 414.49383401777595, "ttft_ms": 23.13250000588596, "input_usage": {"receiver_prefix_tokens": 3283, "dense_cache_bytes": 121024512, "query_tokens": 31}, "output_usage": {"output_tokens": 17}, "provider_cached_usage": null, "process_memory": 7299727360, "backend_memory": {"mlx_active_bytes": 6361179844, "mlx_peak_bytes": 6420485060, "mlx_cache_bytes": 6590475617, "process_rss_bytes": 7299727360}, "peak_prefill_memory": 7054791664, "peak_decode_memory": 6420485060, "mapper_memory": null, "cost_with_source": null, "prediction_artifact": "A pooling technique for aggregating frame-level features into a single utterance-level feature.", "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.log", "payload_hash": "6f0cea2ea0fe134b9e5552bf881dec82625be5d2070aeab1427d56c909191a1b", "output_hash": "3ffdac3b266bbffe84697d9ce063315e72265a67e2c7d367e858dea2fc84ec04"}115