{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FW7UYH4EFFJSABCSNNBJCKTQVM","short_pith_number":"pith:FW7UYH4E","schema_version":"1.0","canonical_sha256":"2dbf4c1f8429532004526b42912a70ab1b9eb42de774d1a35b5a7632f639591f","source":{"kind":"arxiv","id":"2607.23002","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Arizona State University), Jeff Otterson (W. P. Carey School of Business","submitted_at":"2026-07-25T02:38:07Z","abstract_excerpt":"Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified. We study an adversarial test-hardening loop under a mechanical oracle: a Tester model writes tests, mutation testing names surviving injected defects, and a Critic model writes tests to kill exactly those, with every verdict decided mechanically, so no model judges another's output. In Experiment 1, on five Python subjects (one same-lineage-loop cell could not be scored), the loop killed 105 mutants that one-shot generation missed and lost none, and the cross-li"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.23002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-25T02:38:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eefbd62c46af9b67171765a3cbcefb83e4c9221de8980af3eb34a11252cec971","abstract_canon_sha256":"a9281104825b6423ca51b89710653c74fd2ad87c9a02d600e2971e0ec4ed5d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:07.017047Z","signature_b64":"Pdg22SadznDK4RKK3ZZpIQ8Vo77k8VZ/bhtRJVHKqxDN1kZAy6gHrMrDreHIGhjkjiZTz/5TjfI3X2trPXotAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dbf4c1f8429532004526b42912a70ab1b9eb42de774d1a35b5a7632f639591f","last_reissued_at":"2026-07-28T00:22:07.016194Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:07.016194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Arizona State University), Jeff Otterson (W. P. Carey School of Business","submitted_at":"2026-07-25T02:38:07Z","abstract_excerpt":"Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified. We study an adversarial test-hardening loop under a mechanical oracle: a Tester model writes tests, mutation testing names surviving injected defects, and a Critic model writes tests to kill exactly those, with every verdict decided mechanically, so no model judges another's output. In Experiment 1, on five Python subjects (one same-lineage-loop cell could not be scored), the loop killed 105 mutants that one-shot generation missed and lost none, and the cross-li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23002","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.23002/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.23002","created_at":"2026-07-28T00:22:07.016640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23002v1","created_at":"2026-07-28T00:22:07.016640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23002","created_at":"2026-07-28T00:22:07.016640+00:00"},{"alias_kind":"pith_short_12","alias_value":"FW7UYH4EFFJS","created_at":"2026-07-28T00:22:07.016640+00:00"},{"alias_kind":"pith_short_16","alias_value":"FW7UYH4EFFJSABCS","created_at":"2026-07-28T00:22:07.016640+00:00"},{"alias_kind":"pith_short_8","alias_value":"FW7UYH4E","created_at":"2026-07-28T00:22:07.016640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM","json":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM.json","graph_json":"https://pith.science/api/pith-number/FW7UYH4EFFJSABCSNNBJCKTQVM/graph.json","events_json":"https://pith.science/api/pith-number/FW7UYH4EFFJSABCSNNBJCKTQVM/events.json","paper":"https://pith.science/paper/FW7UYH4E"},"agent_actions":{"view_html":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM","download_json":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM.json","view_paper":"https://pith.science/paper/FW7UYH4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23002&json=true","fetch_graph":"https://pith.science/api/pith-number/FW7UYH4EFFJSABCSNNBJCKTQVM/graph.json","fetch_events":"https://pith.science/api/pith-number/FW7UYH4EFFJSABCSNNBJCKTQVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM/action/storage_attestation","attest_author":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM/action/author_attestation","sign_citation":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM/action/citation_signature","submit_replication":"https://pith.science/pith/FW7UYH4EFFJSABCSNNBJCKTQVM/action/replication_record"}},"created_at":"2026-07-28T00:22:07.016640+00:00","updated_at":"2026-07-28T00:22:07.016640+00:00"}