{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6ONVFNPI3ZGS76LMCWLCTYR5MJ","short_pith_number":"pith:6ONVFNPI","canonical_record":{"source":{"id":"2604.25850","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-28T16:55:02Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"c7b83e7ad798a3955b2ec3441ac7ba8f62c56efb704cc3f89b7bf7fc8e01046f","abstract_canon_sha256":"5bbdee89bffc3cd0212d2d5031c2ed5765e647efb58f9c1cd03725e88a9fcd4e"},"schema_version":"1.0"},"canonical_sha256":"f39b52b5e8de4d2ff96c159629e23d625e1dc1ec86997f97438faaf942ee54ef","source":{"kind":"arxiv","id":"2604.25850","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.25850","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2604.25850v4","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.25850","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"6ONVFNPI3ZGS","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"6ONVFNPI3ZGS76LM","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"6ONVFNPI","created_at":"2026-05-20T00:05:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6ONVFNPI3ZGS76LMCWLCTYR5MJ","target":"record","payload":{"canonical_record":{"source":{"id":"2604.25850","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-28T16:55:02Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"c7b83e7ad798a3955b2ec3441ac7ba8f62c56efb704cc3f89b7bf7fc8e01046f","abstract_canon_sha256":"5bbdee89bffc3cd0212d2d5031c2ed5765e647efb58f9c1cd03725e88a9fcd4e"},"schema_version":"1.0"},"canonical_sha256":"f39b52b5e8de4d2ff96c159629e23d625e1dc1ec86997f97438faaf942ee54ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:45.402259Z","signature_b64":"ayKM+MK2fE7ADMXHqBY1pifaIU/4G1nPxNWuQhASB3ReG3PtJqdiKG8nbVO3ejnRC0GmzCxPKW2R3wbRxFaBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f39b52b5e8de4d2ff96c159629e23d625e1dc1ec86997f97438faaf942ee54ef","last_reissued_at":"2026-05-20T00:05:45.401710Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:45.401710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.25850","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kgOl7SP2JdjqbpAVi1fgZkFYVwN8Y9nS1HHwwSqENrjj+phr6/a2q0j6qwxmFoIpJ5AffWNQqykE7YSdeykBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T01:13:52.389639Z"},"content_sha256":"c9b8b64fd606b62041951ac97e930239faa2c11e7affbb60618a740eb5c25491","schema_version":"1.0","event_id":"sha256:c9b8b64fd606b62041951ac97e930239faa2c11e7affbb60618a740eb5c25491"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6ONVFNPI3ZGS76LMCWLCTYR5MJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Three observability pillars let coding-agent harnesses evolve autonomously to beat human designs and transfer across benchmarks.","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Chengjun Pan, Hang Yan, Jiahang Lin, Lizhi Lin, Shichun Liu, Shihan Dou, Tao Gui, Xuanjing Huang, Yu-Gang Jiang, Zhenhua Han, Zhiheng Xi","submitted_at":"2026-04-28T16:55:02Z","abstract_excerpt":"Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across editable components, voluminous trajectories that bury actionable signal, and edits whose effect is hard to attribute. We introduce Agentic Harness Engineering (AHE), a closed loop that addresses these challenges through three matched observability pillars: (1) component observability gives every editable harness component a file-level representation so the acti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ten AHE iterations lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI (71.9%) and the self-evolving baselines ACE and TF-GRPO. The frozen harness transfers without re-evolution: on SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains across three alternate model families.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three observability pillars sufficiently constrain the action space and provide actionable signal so that the evolution loop produces generalizable improvements rather than benchmark-specific overfitting or noise-driven changes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with transfer gains across models and benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Three observability pillars let coding-agent harnesses evolve autonomously to beat human designs and transfer across benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a2e5b0e9c835855ba0d59c28e90c9105e6239d1a8af3b112cca51ebd8cb8a7c5"},"source":{"id":"2604.25850","kind":"arxiv","version":4},"verdict":{"id":"887645bd-c5cc-42e6-b8be-6c0dde0800bc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T16:12:58.518385Z","strongest_claim":"ten AHE iterations lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI (71.9%) and the self-evolving baselines ACE and TF-GRPO. The frozen harness transfers without re-evolution: on SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains across three alternate model families.","one_line_summary":"AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with transfer gains across models and benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three observability pillars sufficiently constrain the action space and provide actionable signal so that the evolution loop produces generalizable improvements rather than benchmark-specific overfitting or noise-driven changes.","pith_extraction_headline":"Three observability pillars let coding-agent harnesses evolve autonomously to beat human designs and transfer across benchmarks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.25850/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T20:43:22.071216Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ea2b183ffce07ff7ac02fc3848eb521e69fa16beceae61e1f461ea05cac388f6"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"887645bd-c5cc-42e6-b8be-6c0dde0800bc"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDhby7Slk3PMsHsVtMLpHKa8sLaLh09llnBhayR94X6c1YqwFk5UDSFzFXSMOjptjc8uomqGklKslipiPb7sDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T01:13:52.390614Z"},"content_sha256":"c7970a0e08352713b60ec4a1277224663e5370d88b0882144e29d81915b5746e","schema_version":"1.0","event_id":"sha256:c7970a0e08352713b60ec4a1277224663e5370d88b0882144e29d81915b5746e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ/bundle.json","state_url":"https://pith.science/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T01:13:52Z","links":{"resolver":"https://pith.science/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ","bundle":"https://pith.science/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ/bundle.json","state":"https://pith.science/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ONVFNPI3ZGS76LMCWLCTYR5MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6ONVFNPI3ZGS76LMCWLCTYR5MJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5bbdee89bffc3cd0212d2d5031c2ed5765e647efb58f9c1cd03725e88a9fcd4e","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-28T16:55:02Z","title_canon_sha256":"c7b83e7ad798a3955b2ec3441ac7ba8f62c56efb704cc3f89b7bf7fc8e01046f"},"schema_version":"1.0","source":{"id":"2604.25850","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.25850","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2604.25850v4","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.25850","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"6ONVFNPI3ZGS","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"6ONVFNPI3ZGS76LM","created_at":"2026-05-20T00:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"6ONVFNPI","created_at":"2026-05-20T00:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:c7970a0e08352713b60ec4a1277224663e5370d88b0882144e29d81915b5746e","target":"graph","created_at":"2026-05-20T00:05:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ten AHE iterations lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI (71.9%) and the self-evolving baselines ACE and TF-GRPO. The frozen harness transfers without re-evolution: on SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains across three alternate model families."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the three observability pillars sufficiently constrain the action space and provide actionable signal so that the evolution loop produces generalizable improvements rather than benchmark-specific overfitting or noise-driven changes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with transfer gains across models and benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Three observability pillars let coding-agent harnesses evolve autonomously to beat human designs and transfer across benchmarks."}],"snapshot_sha256":"a2e5b0e9c835855ba0d59c28e90c9105e6239d1a8af3b112cca51ebd8cb8a7c5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T20:43:22.071216Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.25850/integrity.json","findings":[],"snapshot_sha256":"ea2b183ffce07ff7ac02fc3848eb521e69fa16beceae61e1f461ea05cac388f6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across editable components, voluminous trajectories that bury actionable signal, and edits whose effect is hard to attribute. We introduce Agentic Harness Engineering (AHE), a closed loop that addresses these challenges through three matched observability pillars: (1) component observability gives every editable harness component a file-level representation so the acti","authors_text":"Chengjun Pan, Hang Yan, Jiahang Lin, Lizhi Lin, Shichun Liu, Shihan Dou, Tao Gui, Xuanjing Huang, Yu-Gang Jiang, Zhenhua Han, Zhiheng Xi","cross_cats":["cs.SE"],"headline":"Three observability pillars let coding-agent harnesses evolve autonomously to beat human designs and transfer across benchmarks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-28T16:55:02Z","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.25850","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-07T16:12:58.518385Z","id":"887645bd-c5cc-42e6-b8be-6c0dde0800bc","model_set":{"reader":"grok-4.3"},"one_line_summary":"AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with transfer gains across models and benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Three observability pillars let coding-agent harnesses evolve autonomously to beat human designs and transfer across benchmarks.","strongest_claim":"ten AHE iterations lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI (71.9%) and the self-evolving baselines ACE and TF-GRPO. The frozen harness transfers without re-evolution: on SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains across three alternate model families.","weakest_assumption":"That the three observability pillars sufficiently constrain the action space and provide actionable signal so that the evolution loop produces generalizable improvements rather than benchmark-specific overfitting or noise-driven changes."}},"verdict_id":"887645bd-c5cc-42e6-b8be-6c0dde0800bc"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c9b8b64fd606b62041951ac97e930239faa2c11e7affbb60618a740eb5c25491","target":"record","created_at":"2026-05-20T00:05:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5bbdee89bffc3cd0212d2d5031c2ed5765e647efb58f9c1cd03725e88a9fcd4e","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-28T16:55:02Z","title_canon_sha256":"c7b83e7ad798a3955b2ec3441ac7ba8f62c56efb704cc3f89b7bf7fc8e01046f"},"schema_version":"1.0","source":{"id":"2604.25850","kind":"arxiv","version":4}},"canonical_sha256":"f39b52b5e8de4d2ff96c159629e23d625e1dc1ec86997f97438faaf942ee54ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f39b52b5e8de4d2ff96c159629e23d625e1dc1ec86997f97438faaf942ee54ef","first_computed_at":"2026-05-20T00:05:45.401710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:45.401710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ayKM+MK2fE7ADMXHqBY1pifaIU/4G1nPxNWuQhASB3ReG3PtJqdiKG8nbVO3ejnRC0GmzCxPKW2R3wbRxFaBBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:45.402259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.25850","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9b8b64fd606b62041951ac97e930239faa2c11e7affbb60618a740eb5c25491","sha256:c7970a0e08352713b60ec4a1277224663e5370d88b0882144e29d81915b5746e"],"state_sha256":"a00fa4ae4121e7fde174d3995338c655e1d6e4e3f4c82ff108485cfa6f77bc55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gtjjYGqQOe/cBQuxYp48NJ8gT+Yp5BUKLF6iOfY0RjEh9HfCGdtkt2qfi7VPJ6WpzuOMPtnvCK/6cgMSIz1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T01:13:52.395348Z","bundle_sha256":"74315330ca673c64a289804477a51e9202083d17a462093118f4aeccfc2207c8"}}