{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RHDIGH5IE65MHCSA3A37EDLUQA","short_pith_number":"pith:RHDIGH5I","schema_version":"1.0","canonical_sha256":"89c6831fa827bac38a40d837f20d74801a0673750c947c322a7e0d895a918d29","source":{"kind":"arxiv","id":"2605.13357","version":1},"attestation_state":"computed","paper":{"title":"AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Software-engineering capability for foundation-model agents emerges from a model-harness-environment system rather than from the model alone.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hailin Zhong, Shengxin Zhu","submitted_at":"2026-05-13T11:14:59Z","abstract_excerpt":"Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete. We formalize this substrate as an AI Harness Engineering and identify eleven component re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T11:14:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0912d0135db6157edf6996788b44b8c6fc70f8493c993ae6a8820ef3774e9d02","abstract_canon_sha256":"363e8ca21e15174c72e05081c081de279e31f39b66662fd97f6560d405c1840b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:48.199695Z","signature_b64":"e9qdhJ+qQJ6g1R4S3iaWork2YCgzm25isnwmM5oQmQEODbGEpS/czFYKH4Sy2TKLHm7uzl0T+MM+IUdZTB19BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c6831fa827bac38a40d837f20d74801a0673750c947c322a7e0d895a918d29","last_reissued_at":"2026-05-18T02:44:48.199273Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:48.199273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Software-engineering capability for foundation-model agents emerges from a model-harness-environment system rather than from the model alone.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hailin Zhong, Shengxin Zhu","submitted_at":"2026-05-13T11:14:59Z","abstract_excerpt":"Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete. We formalize this substrate as an AI Harness Engineering and identify eleven component re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That defining eleven component responsibilities and a four-level ladder will systematically improve agent reliability and verifiability, an assumption stated without supporting data or derivation in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper defines AI Harness Engineering as a runtime substrate with eleven components and a four-level ladder that reframes agent reliability as a model-harness-environment system property rather than model capability alone.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Software-engineering capability for foundation-model agents emerges from a model-harness-environment system rather than from the model alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"38745aeb6cb7ad7e0642a2fb3dedd7eacb6f398269ad58f160f8f180eb1fa2d2"},"source":{"id":"2605.13357","kind":"arxiv","version":1},"verdict":{"id":"f734b0c7-8b0d-4bdd-9d7c-aac713be3f00","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:10:33.629110Z","strongest_claim":"We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete.","one_line_summary":"The paper defines AI Harness Engineering as a runtime substrate with eleven components and a four-level ladder that reframes agent reliability as a model-harness-environment system property rather than model capability alone.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That defining eleven component responsibilities and a four-level ladder will systematically improve agent reliability and verifiability, an assumption stated without supporting data or derivation in the abstract.","pith_extraction_headline":"Software-engineering capability for foundation-model agents emerges from a model-harness-environment system rather than from the model alone."},"references":{"count":18,"sample":[{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":1,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":2020,"title":"Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, et al","work_id":"857e276a-33ad-44d4-9d43-c728bd2db249","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan","work_id":"faab4af1-0cb8-4520-9a0a-c7a1a55118e4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press","work_id":"7a8ddf3e-1730-4670-9cf2-8789e3706977","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H","work_id":"ba783dfe-165d-4d63-b7f9-9708af7040b3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"92dab86cc85b5856542c23b8222e918e76631680ad80ee1ff237fcbb35bbd41b","internal_anchors":2},"formal_canon":{"evidence_count":1,"snapshot_sha256":"f4ea6edfd57c9f674ea0a01065b5e807f2e7ea030a40fc70edb6d925cb813dfa"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13357","created_at":"2026-05-18T02:44:48.199360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13357v1","created_at":"2026-05-18T02:44:48.199360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13357","created_at":"2026-05-18T02:44:48.199360+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHDIGH5IE65M","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHDIGH5IE65MHCSA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHDIGH5I","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA","json":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA.json","graph_json":"https://pith.science/api/pith-number/RHDIGH5IE65MHCSA3A37EDLUQA/graph.json","events_json":"https://pith.science/api/pith-number/RHDIGH5IE65MHCSA3A37EDLUQA/events.json","paper":"https://pith.science/paper/RHDIGH5I"},"agent_actions":{"view_html":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA","download_json":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA.json","view_paper":"https://pith.science/paper/RHDIGH5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13357&json=true","fetch_graph":"https://pith.science/api/pith-number/RHDIGH5IE65MHCSA3A37EDLUQA/graph.json","fetch_events":"https://pith.science/api/pith-number/RHDIGH5IE65MHCSA3A37EDLUQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA/action/storage_attestation","attest_author":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA/action/author_attestation","sign_citation":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA/action/citation_signature","submit_replication":"https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA/action/replication_record"}},"created_at":"2026-05-18T02:44:48.199360+00:00","updated_at":"2026-05-18T02:44:48.199360+00:00"}