1{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "e4d6014a524a26cf323d29f6", "attempt_id": "198debfc8cf2", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:05.711305Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 70.56966691743582, "ttft_ms": 13.580082915723324, "decode_ms": 133.09933303389698}, "total_wall_ms": 7606.1354170087725, "ttft_ms": 13.580082915723324, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 10}, "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": "WG-14H-1182", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}2{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "3a7862e06d5a28621d6558c3", "attempt_id": "ea464fda49ef", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:05.947390Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 600, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 70.54591609630734, "ttft_ms": 13.318874989636242, "decode_ms": 13.681416981853545}, "total_wall_ms": 7486.423374968581, "ttft_ms": 13.318874989636242, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}3{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "8fe0656fc337780a8dd4109b", "attempt_id": "bc2a8af8de0e", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:06.061895Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 600, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 70.04433299880475, "ttft_ms": 13.816624996252358, "decode_ms": 13.376791961491108}, "total_wall_ms": 7486.115916981362, "ttft_ms": 13.816624996252358, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}4{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "d6c66202a9977e9ce9be9b6e", "attempt_id": "df2eb4992ee4", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:06.175911Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 72.721833945252, "ttft_ms": 13.34204210434109, "decode_ms": 13.484457973390818}, "total_wall_ms": 7488.403292139992, "ttft_ms": 13.34204210434109, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}5{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "f9daf53ae4c359f1ffcfe01b", "attempt_id": "e05c9dd05f08", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:06.292234Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q04_multi_hop", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 605, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 80.6656670756638, "ttft_ms": 13.283834094181657, "decode_ms": 119.9960419908166}, "total_wall_ms": 7602.7952920412645, "ttft_ms": 13.283834094181657, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 9}, "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": "6,889,172", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "76875b24cee85c9daa41a3b2716f4617e3b85d1aa6a8a5fd34f349dcf4ae3d7e"}6{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "5c93c75e9fbdbcaa62c929d5", "attempt_id": "7d85efdf21da", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:06.521949Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q05_multi_hop", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 603, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 83.6761670652777, "ttft_ms": 13.48012499511242, "decode_ms": 133.4958749357611}, "total_wall_ms": 7619.5156670873985, "ttft_ms": 13.48012499511242, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 10}, "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": "SP-38G-4217", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "e643c21a78559b96fd65325d9ce779b7b8fd6a47c53cf7c2cda1efa8412458c4"}7{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "0d1c21da0c2ef7ac459880a8", "attempt_id": "3da528f59695", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:06.768717Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q06_negation", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 82.41020806599408, "ttft_ms": 13.700834009796381, "decode_ms": 13.601665967144072}, "total_wall_ms": 7498.5860420856625, "ttft_ms": 13.700834009796381, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "no", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "9390298f3fb0c5b160498935d79cb139aef28e1c47358b4bbba61862b9c26e59"}8{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "d5baf7618f6c26d9cb7e6e8e", "attempt_id": "b14008ba6e2c", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:06.895344Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q07_negation", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 595, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 87.12095802184194, "ttft_ms": 13.858709018677473, "decode_ms": 13.865667046047747}, "total_wall_ms": 7503.698958083987, "ttft_ms": 13.858709018677473, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}9{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "7a08e0ff0827c646feb5a691", "attempt_id": "c40dbba05788", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.027877Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q08_revision", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 611, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 92.70949999336153, "ttft_ms": 13.947332976385951, "decode_ms": 13.76683299895376}, "total_wall_ms": 7509.262875071727, "ttft_ms": 13.947332976385951, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}10{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "715da87439b9c2da1d80846c", "attempt_id": "0288e31dbdee", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.164798Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q09_revision", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 603, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 88.89854198787361, "ttft_ms": 13.895749929361045, "decode_ms": 13.664584024809301}, "total_wall_ms": 7505.350458086468, "ttft_ms": 13.895749929361045, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}11{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "f670c6c1f9a3016f46e0668a", "attempt_id": "f3db058d1537", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.297840Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q10_temporal", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 612, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 94.91300000809133, "ttft_ms": 13.864832930266857, "decode_ms": 68.32533294800669}, "total_wall_ms": 7565.9649590961635, "ttft_ms": 13.864832930266857, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 5}, "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": "Torsel-5", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "0a2de4a55396e5f7b4d24e988f7452e33fe7e43fd6e05881b80bcb3034d74d37"}12{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "106680d7384b75e470629b46", "attempt_id": "ff2215fa3b74", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.490963Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q11_aggregation", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 607, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 83.91812501940876, "ttft_ms": 13.685125042684376, "decode_ms": 96.26008395571262}, "total_wall_ms": 7582.891375059262, "ttft_ms": 13.685125042684376, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 7}, "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": "1379172", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "7d9e6c79de4e797c6177e40b49a810a6363041af98982dbd4243baf4bec5c971"}13{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "69c2449a5a3796644cc816ca", "attempt_id": "730ec68711a2", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.700942Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q12_unit_conversion", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 602, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 80.60191699769348, "ttft_ms": 13.449500082060695, "decode_ms": 55.076666991226375}, "total_wall_ms": 7538.049542112276, "ttft_ms": 13.449500082060695, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 4}, "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": "7640", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "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/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b7aa5cfd1d2529920befa138d570102a53952edfdd4823a958212feea0698adf"}14{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "20e3cca49e53c7a7a4486d47", "attempt_id": "be3fa64e72af", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.866998Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q13_unanswerable", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 607, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 79.90162493661046, "ttft_ms": 13.807334005832672, "decode_ms": 13.882457977160811}, "total_wall_ms": 7496.488250093535, "ttft_ms": 13.807334005832672, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}15{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "93cddd2a9c80209579d4603d", "attempt_id": "960b65285402", "run_group_id": "E4_smoke:A4|closed|qwen3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:07.989966Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q14_unanswerable", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 608, "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": {"chain_ms": 7388.310500071384, "hops": {"1": 7388.310500071384}, "receiver_prefill_ms": 80.64408297650516, "ttft_ms": 13.768291915766895, "decode_ms": 13.53445800486952}, "total_wall_ms": 7496.865458087996, "ttft_ms": 13.768291915766895, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "f811e3d2b4b96fb92f1cc9651f50294bf8a18ad7c33cafac648e5969f236fb1e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}16{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "fed4aa61963a7bf8327a9044", "attempt_id": "e294c1d78b77", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:15.145297Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 591, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 70.30716701410711, "ttft_ms": 13.295792043209076, "decode_ms": 133.86049994733185}, "total_wall_ms": 14635.955083067529, "ttft_ms": 13.295792043209076, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 10}, "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": "WG-14H-1182", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "e454fec67e299085db563490eff5a43753bbeed6d185376c1a5962c124db19eb"}17{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "1fd962b7fed8b7be0f957943", "attempt_id": "a185532acd87", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:15.379601Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 597, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.43875004071742, "ttft_ms": 13.473832979798317, "decode_ms": 13.634915929287672}, "total_wall_ms": 14514.995125005953, "ttft_ms": 13.473832979798317, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}18{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "44736994ac7d3c6e955ca246", "attempt_id": "1ba1eb8cf9e4", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:15.492830Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 597, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.44708398077637, "ttft_ms": 13.740207999944687, "decode_ms": 13.40095791965723}, "total_wall_ms": 14515.074791037478, "ttft_ms": 13.740207999944687, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}19{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "3b4059272a0084c78eb7bb71", "attempt_id": "ee0abde30be1", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:15.605864Z", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 594, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.15895803831518, "ttft_ms": 13.322583981789649, "decode_ms": 13.661875040270388}, "total_wall_ms": 14514.662832953036, "ttft_ms": 13.322583981789649, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}20{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "a5a377217f065df885e17778", "attempt_id": "eab1d937151f", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:15.718152Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q04_multi_hop", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 602, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 70.07291703484952, "ttft_ms": 13.24529096018523, "decode_ms": 120.1137499883771}, "total_wall_ms": 14621.930750086904, "ttft_ms": 13.24529096018523, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 9}, "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": "6,889,172", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "76875b24cee85c9daa41a3b2716f4617e3b85d1aa6a8a5fd34f349dcf4ae3d7e"}21{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "75305a0fa99138dc19870aeb", "attempt_id": "1e9b18d736a8", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:15.937819Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q05_multi_hop", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 600, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.9936660239473, "ttft_ms": 13.173334067687392, "decode_ms": 133.35729099344462}, "total_wall_ms": 14635.019749985076, "ttft_ms": 13.173334067687392, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 10}, "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": "SP-38G-4217", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "e643c21a78559b96fd65325d9ce779b7b8fd6a47c53cf7c2cda1efa8412458c4"}22{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "02cb774895cb7f4200e25ac7", "attempt_id": "f91932e6db80", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:16.171074Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q06_negation", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 594, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.08262509386986, "ttft_ms": 13.466249918565154, "decode_ms": 13.275083969347179}, "total_wall_ms": 14514.30133311078, "ttft_ms": 13.466249918565154, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "no", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "9390298f3fb0c5b160498935d79cb139aef28e1c47358b4bbba61862b9c26e59"}23{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "836a2db482e48950e8112ef4", "attempt_id": "3ec99045954c", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:16.283280Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q07_negation", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 592, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.89300006534904, "ttft_ms": 13.15629098098725, "decode_ms": 13.341167010366917}, "total_wall_ms": 14514.862333075143, "ttft_ms": 13.15629098098725, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}24{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "e1d9c69d659fac9dbfa05d73", "attempt_id": "0581ed045141", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:16.396005Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q08_revision", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 608, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.83249995391816, "ttft_ms": 13.473790953867137, "decode_ms": 13.576042023487389}, "total_wall_ms": 14515.38841612637, "ttft_ms": 13.473790953867137, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}25{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "590e8690bc20f0eeb26cf3fe", "attempt_id": "1404cc3d5f3f", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:16.508754Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q09_revision", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 600, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 69.97666589450091, "ttft_ms": 13.296290999278426, "decode_ms": 13.450499973259866}, "total_wall_ms": 14515.232374076732, "ttft_ms": 13.296290999278426, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}26{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "acfb0023ca11a1d053425fb0", "attempt_id": "97c16ca89c34", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:16.622042Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q10_temporal", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 609, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 70.51529199816287, "ttft_ms": 13.40104197151959, "decode_ms": 66.48116698488593}, "total_wall_ms": 14568.905583000742, "ttft_ms": 13.40104197151959, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 5}, "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": "Torsel-5", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "0a2de4a55396e5f7b4d24e988f7452e33fe7e43fd6e05881b80bcb3034d74d37"}27{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "3ed2e99bfe065e96ba5567e6", "attempt_id": "1f628ef9ac35", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:16.788509Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q11_aggregation", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 604, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 70.03845798317343, "ttft_ms": 13.494165963493288, "decode_ms": 133.29291704576463}, "total_wall_ms": 14635.345748974942, "ttft_ms": 13.494165963493288, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 10}, "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": "19,431,432", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "06fe08c35e6644a2505156a3386f0e4d98a25b828e2efd638d491d710f856103"}28{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "f6d8b0874f8a14cbf833d123", "attempt_id": "85a8507f0396", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:17.021966Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q12_unit_conversion", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 599, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 70.00924996100366, "ttft_ms": 13.551250100135803, "decode_ms": 52.76383401360363}, "total_wall_ms": 14554.786042077467, "ttft_ms": 13.551250100135803, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 4}, "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": "7640", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "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/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b7aa5cfd1d2529920befa138d570102a53952edfdd4823a958212feea0698adf"}29{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "3bbb5e2647d0d2231c6dc1a3", "attempt_id": "fa24afedd8b2", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:17.174862Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q13_unanswerable", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 604, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 70.16887504141778, "ttft_ms": 13.312499970197678, "decode_ms": 13.794707949273288}, "total_wall_ms": 14515.795915969647, "ttft_ms": 13.312499970197678, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}30{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "f81cbc0cf864774a3798a98d", "attempt_id": "40ab50e944d0", "run_group_id": "E4_smoke:A4|closed|qwen3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:17.288905Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q14_unanswerable", "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": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A4", "implementation_fidelity": "custom", "compression_config": {"mode": "closed", "agents": ["qwen3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_closed", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 605, "message_tokens": 509, "message_utf8_bytes": 1189, "cache_tensor_bytes": null, "serialized_payload_bytes": 1189, "side_information_bytes": 0, "fetched_bytes": 0, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 14417.945208027959, "hops": {"1": 7388.310500071384, "2": 7029.634707956575}, "receiver_prefill_ms": 74.4137919973582, "ttft_ms": 13.573125004768372, "decode_ms": 13.354499940760434}, "total_wall_ms": 14519.808249082416, "ttft_ms": 13.573125004768372, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1196}, "2": {"facts_total": 64, "facts_retained": 28, "retention_rate": 0.4375, "retention_by_kind": {"person": 0.6666666666666666, "date": 0.0, "amount": 0.42857142857142855, "status": 0.75, "place": 0.0, "identifier": 0.5, "quantity": 0.5}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1189}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "49b54c3c28297dd6f3503e10cc594cea5454825636b39e95a6e8663b6c37ed71", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}31{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "ef1cb0065f7c97faa4ef549b", "attempt_id": "4897ddef5806", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:28.381200Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 426, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 72.67737505026162, "ttft_ms": 13.352832989767194, "decode_ms": 13.35733407177031}, "total_wall_ms": 7289.022208889946, "ttft_ms": 13.352832989767194, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}32{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "5aead85d240368a08066c2c3", "attempt_id": "be42e414d32b", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:28.500359Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 432, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 124.0327499108389, "ttft_ms": 14.377749990671873, "decode_ms": 13.802209054119885}, "total_wall_ms": 7341.845458839089, "ttft_ms": 14.377749990671873, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}33{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "55c1fbf7e46378e1c4bdf6ad", "attempt_id": "3bdbc43d86b9", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:28.670566Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 432, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.62875002902001, "ttft_ms": 13.563584070652723, "decode_ms": 13.158750021830201}, "total_wall_ms": 7269.9129588436335, "ttft_ms": 13.563584070652723, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}34{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "15bba002b57c9391083f8b1a", "attempt_id": "134a07c6c081", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:28.770854Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 429, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.7230420159176, "ttft_ms": 13.315167045220733, "decode_ms": 13.420167029835284}, "total_wall_ms": 7269.994708942249, "ttft_ms": 13.315167045220733, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}35{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "75dc721488e0ef1126081271", "attempt_id": "bed9a2a1f704", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:28.869037Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q04_multi_hop", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 74.69737506471574, "ttft_ms": 13.112541986629367, "decode_ms": 144.9349169852212}, "total_wall_ms": 7422.3342089680955, "ttft_ms": 13.112541986629367, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 11}, "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": "6,889,172 NOK", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 0.0, "f1": 0.6666666666666666}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "ce5dae2b035af8d38bda9e7d1f1cb7eb7e4141e20298d86d8bce5fe5ac6c0246"}36{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "3e9a22c3f5104a1eddd41703", "attempt_id": "78399ab6c557", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.118864Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q05_multi_hop", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 435, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 64.27808292210102, "ttft_ms": 13.261125073768198, "decode_ms": 132.68429203890264}, "total_wall_ms": 7399.776375852525, "ttft_ms": 13.261125073768198, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 10}, "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": "BH-71Y-2851", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "38b55d8642902ac72f5987064e67fbe9b766a04dc338df11f6fa45d4cb64179e"}37{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "eb3ecdabac7df3aa56f2db7d", "attempt_id": "99f7f5ca3819", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.346863Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q06_negation", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 429, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.109832922928035, "ttft_ms": 13.361750054173172, "decode_ms": 13.09916703030467}, "total_wall_ms": 7269.102249876596, "ttft_ms": 13.361750054173172, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "no", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "9390298f3fb0c5b160498935d79cb139aef28e1c47358b4bbba61862b9c26e59"}38{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "1adfc40d070513eb8dcaafa3", "attempt_id": "c00fc0794f37", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.443663Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q07_negation", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 427, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 67.15850008185953, "ttft_ms": 13.201624969951808, "decode_ms": 13.237791019491851}, "total_wall_ms": 7283.145666937344, "ttft_ms": 13.201624969951808, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}39{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "119e16c4305375bb8dc1f5c3", "attempt_id": "047930cf5767", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.554627Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q08_revision", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 443, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 112.22383310087025, "ttft_ms": 13.389540952630341, "decode_ms": 13.051833026111126}, "total_wall_ms": 7328.250583843328, "ttft_ms": 13.389540952630341, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}40{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "979bd81c65b6db191a8e985d", "attempt_id": "c54b44cc375b", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.711472Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q09_revision", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 435, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.7681250134483, "ttft_ms": 13.247541966848075, "decode_ms": 13.039291952736676}, "total_wall_ms": 7269.584166933782, "ttft_ms": 13.247541966848075, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}41{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "065a7e3fa74c1ad482af1d3e", "attempt_id": "8fd72b5c73ee", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.809877Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q10_temporal", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 444, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 110.29041605070233, "ttft_ms": 13.615458039566875, "decode_ms": 13.41954106464982}, "total_wall_ms": 7326.904041925445, "ttft_ms": 13.615458039566875, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}42{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "91f86e20ea07bbdb391d30a6", "attempt_id": "fff9ed3ee7b5", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:29.964638Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q11_aggregation", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 439, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.64233395084739, "ttft_ms": 13.906834064982831, "decode_ms": 94.21266708523035}, "total_wall_ms": 7351.373499841429, "ttft_ms": 13.906834064982831, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 7}, "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": "1418934", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b42460a96a2ffc3ec3bc3e8bb110e80b04f38ffa2f4006e5a3159cebdee13b7f"}43{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "4c81006b8214f8778abfbac8", "attempt_id": "c28310477a2b", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:30.144231Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q12_unit_conversion", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 68.86416592169553, "ttft_ms": 13.305291067808867, "decode_ms": 13.282250030897558}, "total_wall_ms": 7285.093041951768, "ttft_ms": 13.305291067808867, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "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/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}44{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "30262d87fea47fb55f4c9228", "attempt_id": "eea79bc96c46", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:30.258590Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q13_unanswerable", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1971, "query_tokens": 439, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.78554202616215, "ttft_ms": 13.282875064760447, "decode_ms": 13.299459009431303}, "total_wall_ms": 7269.934750860557, "ttft_ms": 13.282875064760447, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}45{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "e2fa4da7d7595a735512203b", "attempt_id": "4e5fc7bd7c56", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h1", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:30.357961Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q14_unanswerable", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11", "tokenizer_hashes": {"receiver": "5c5a439ba2677fe28e1dea9b22371b270ecd5e34acbc849bc619689605f9547b"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 1, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "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": {"chain_ms": 7189.094333909452, "hops": {"1": 7189.094333909452}, "receiver_prefill_ms": 53.51837503258139, "ttft_ms": 13.22641596198082, "decode_ms": 13.591583934612572}, "total_wall_ms": 7269.903499865904, "ttft_ms": 13.22641596198082, "input_usage": {"lookups": 0}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "448fbefbbf3dc2a8c9785c435f1c717947c9d692820d830c64b908b542a8566e", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}46{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "8888774dc820faf67464763e", "attempt_id": "bd23292acf1f", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:38.360272Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 587, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 77.82762497663498, "ttft_ms": 13.771916972473264, "decode_ms": 13.905708095990121}, "total_wall_ms": 15194.374041981064, "ttft_ms": 13.771916972473264, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}47{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "7f668e1f7b3eb3d9b9fd3057", "attempt_id": "e595c673de30", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:38.483820Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 592, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 74.5352499652654, "ttft_ms": 13.96233297418803, "decode_ms": 13.73537490144372}, "total_wall_ms": 15190.9696678631, "ttft_ms": 13.96233297418803, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}48{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "070822fa247dd66d78b6ffcd", "attempt_id": "6d31e2b2d76b", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:38.603556Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 592, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 73.35308298934251, "ttft_ms": 14.057875028811395, "decode_ms": 13.937833020463586}, "total_wall_ms": 15190.103625995107, "ttft_ms": 14.057875028811395, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}49{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "1c3f890e0a19b625c9227879", "attempt_id": "539634270a2e", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:38.721629Z", "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|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 589, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 74.27520793862641, "ttft_ms": 14.271625084802508, "decode_ms": 13.794749975204468}, "total_wall_ms": 15191.149875987321, "ttft_ms": 14.271625084802508, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}50{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "5c48647a9e1b348b9b640926", "attempt_id": "50e5bb1c3127", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:38.840822Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q04_multi_hop", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 598, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 77.12575001642108, "ttft_ms": 14.055041945539415, "decode_ms": 69.60441707633436}, "total_wall_ms": 15249.57975000143, "ttft_ms": 14.055041945539415, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 5}, "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": "6,889,172", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "76875b24cee85c9daa41a3b2716f4617e3b85d1aa6a8a5fd34f349dcf4ae3d7e"}51{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "e6a0f8ca62392e868ec815b1", "attempt_id": "80886cabcadb", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.019147Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q05_multi_hop", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 595, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 82.5685829622671, "ttft_ms": 14.223375008441508, "decode_ms": 14.372208039276302}, "total_wall_ms": 15199.900208972394, "ttft_ms": 14.223375008441508, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}52{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "05fe5b3197f86364deed50a4", "attempt_id": "413eadf2083b", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.148069Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q06_negation", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 589, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 84.24354100134224, "ttft_ms": 14.065457973629236, "decode_ms": 13.865416985936463}, "total_wall_ms": 15200.890749925748, "ttft_ms": 14.065457973629236, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "No", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "1ea442a134b2a184bd5d40104401f2a37fbc09ccf3f4bc9da161c6099be3691d"}53{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "069d1a413855b163acd583f6", "attempt_id": "5a23a496b605", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.276600Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q07_negation", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 587, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 86.33862505666912, "ttft_ms": 14.2137500224635, "decode_ms": 13.89129098970443}, "total_wall_ms": 15203.177750925533, "ttft_ms": 14.2137500224635, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "No", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "1ea442a134b2a184bd5d40104401f2a37fbc09ccf3f4bc9da161c6099be3691d"}54{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "caeca776a64b5957737b1f15", "attempt_id": "1d487926748b", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.407745Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q08_revision", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 603, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 91.23012493364513, "ttft_ms": 14.472333015874028, "decode_ms": 13.88770795892924}, "total_wall_ms": 15208.31024996005, "ttft_ms": 14.472333015874028, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}55{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "db28675b1125cfdf5b610b3d", "attempt_id": "0765c60f69f5", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.543531Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q09_revision", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 595, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 93.1548330700025, "ttft_ms": 14.234708971343935, "decode_ms": 14.128541923128068}, "total_wall_ms": 15210.25970892515, "ttft_ms": 14.234708971343935, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}56{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "06f0097c3db73ac91f6d5b1f", "attempt_id": "dcb96516ced4", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.681362Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q10_temporal", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 604, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 90.80570796504617, "ttft_ms": 14.129042043350637, "decode_ms": 14.112583012320101}, "total_wall_ms": 15207.776958937757, "ttft_ms": 14.129042043350637, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}57{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "ba7d480a807e039f9edb854f", "attempt_id": "b01c7d2c7f31", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:39.816641Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q11_aggregation", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 600, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 89.42750003188848, "ttft_ms": 14.108083094470203, "decode_ms": 68.82829195819795}, "total_wall_ms": 15261.129499878734, "ttft_ms": 14.108083094470203, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 5}, "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": "7,280,585", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "2b81d1bd559c98218f68f4bc6bf62ababe33d07bcf6ec2cd6c2cd0508c0e52b5"}58{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "b051902bc46dc13e0a1bf186", "attempt_id": "c6ae50cac079", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:40.005425Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q12_unit_conversion", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 595, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 87.34066702891141, "ttft_ms": 14.235583948902786, "decode_ms": 13.789458898827434}, "total_wall_ms": 15204.090374871157, "ttft_ms": 14.235583948902786, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "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/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}59{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "d011ea48a6559b63fe4420d2", "attempt_id": "183049fa628d", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:40.137750Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q13_unanswerable", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 600, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 84.58429202437401, "ttft_ms": 14.115125057287514, "decode_ms": 14.149583061225712}, "total_wall_ms": 15201.539375935681, "ttft_ms": 14.115125057287514, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}60{"schema_version": "wp30-attempt-1", "study_id": "WP30", "experiment_id": "E4_smoke", "trial_id": "46883052d3de12af358f9963", "attempt_id": "cbe9b3f834c6", "run_group_id": "E4_smoke:A5|repairable|qwen3b-llama3b:h2", "protocol_hash": "unfrozen", "config_hash": "6b824f39d528ca63caa404b46d54b529ed8a1bc08e5cc1584cda4d73da84aea9", "git_commit": "fea8e12394fac49c22b00e41baf681fd35f0576e", "timestamp_utc": "2026-10-30T03:34:40.266732Z", "task_family": "synthetic", "document_id": "syn_02000_2000", "document_hash": "3bcf1bb02792129efca162575bc2ef64622b41083d4e2870fed106d663e6417c", "question_id": "q14_unanswerable", "split": "dev", "cluster_id": "syn_02000_2000", "sender_model_revision": "mlx-community/Qwen2.5-3B-Instruct-bf16@bec1ad658e380044bbfe06d4a2268801d3379a11|mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "receiver_model_revision": "mlx-community/Llama-3.2-3B-Instruct-bf16@6d88ba43024fef71b10e52e101c7cd4598322601", "tokenizer_hashes": {"receiver": "b9d8872cf3a99da99e1fc4b0f71232a451632dc49ca4c6771549b4efa5c1c763"}, "backend_versions": {"mlx": "0.32.4", "mlx_lm": "0.32.2"}, "hardware_id": "laptop-m5max-48g", "device_state": {}, "weight_precision": "bf16", "method_id": "A5", "implementation_fidelity": "custom", "compression_config": {"mode": "repairable", "agents": ["qwen3b", "llama3b"], "budget_tokens": 512}, "question_access": "blind", "topology": "chain_repairable", "handoff_index": 2, "reuse_count": 15, "cache_hit": false, "cache_compatibility_hash": null, "random_seed": 0, "source_tokens_sender": null, "source_tokens_receiver": 1766, "query_tokens": 601, "message_tokens": 484, "message_utf8_bytes": 1403, "cache_tensor_bytes": null, "serialized_payload_bytes": 1403, "side_information_bytes": 0, "fetched_bytes": 540, "transport_bytes_if_measured": null, "timing_spans": {"chain_ms": 15088.201458915137, "hops": {"1": 7189.094333909452, "2": 7899.107125005685}, "receiver_prefill_ms": 86.56408300157636, "ttft_ms": 13.959750067442656, "decode_ms": 13.88420898001641}, "total_wall_ms": 15203.10266688466, "ttft_ms": 13.959750067442656, "input_usage": {"lookups": 1}, "output_usage": {"output_tokens": 1}, "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": "unknown", "evidence_artifact": {"ledger": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}, "ledger_by_hop": {"1": {"facts_total": 64, "facts_retained": 10, "retention_rate": 0.15625, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.125, "amount": 0.14285714285714285, "status": 0.3333333333333333, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 817}, "2": {"facts_total": 64, "facts_retained": 16, "retention_rate": 0.25, "retention_by_kind": {"person": 0.16666666666666666, "date": 0.25, "amount": 0.14285714285714285, "status": 0.75, "place": 0.0, "identifier": 0.08333333333333333, "quantity": 0.16666666666666666}, "unsupported_numbers": 0, "unsupported_identifiers": 0, "distorted_sentences": 0, "message_bytes": 1403}}}, "reference_key_id": "keys/synthetic/syn_02000_2000.json", "task_scores": {"correct": 1.0, "abstained": 1.0, "f1": 1.0}, "status": "success", "error_code": null, "retry_of": null, "log_artifact": "runs/logs/E4_smoke.log", "payload_hash": "1cc02e5fe068336092e7eb9c927276603bff34770095beec1e4af3e6ef63a8cd", "output_hash": "b23a6a8439c0dde5515893e7c90c1e3233b8616e634470f20dc4928bcf3609bc"}61