{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GZO6PVE46VOCABCWKMR2URUCHP","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":"5b98aaab0ca4bf3743e13ee3c9f91e802935ee0f7a533a17adad8c3c4005df8e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-27T19:57:15Z","title_canon_sha256":"cec01fca9b3685f6c7b7b63f9144255aaa1026b0ae0d74391b401983760f07fc"},"schema_version":"1.0","source":{"id":"2605.29054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29054","created_at":"2026-05-29T01:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29054v1","created_at":"2026-05-29T01:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29054","created_at":"2026-05-29T01:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"GZO6PVE46VOC","created_at":"2026-05-29T01:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"GZO6PVE46VOCABCW","created_at":"2026-05-29T01:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"GZO6PVE4","created_at":"2026-05-29T01:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:45ee33af90b32790622d85cf947043d5db61d4bd8d164c3b36e999ce427a7bc0","target":"graph","created_at":"2026-05-29T01:04:44Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.29054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Coding agents increasingly act as codebase-scale collaborators that can assist with codebase conversion, but this progress has exposed a critical weakness: agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks while violating the semantic contracts users actually care about. This problem is especially acute in codebase conversion, where prior evaluation is largely outcome-driven and therefore unstable: two implementations can match on a shallow outcome, such as a single forward loss, while diverging in gradients, optimizer beha","authors_text":"Bhavana Dalvi Mishra, Chi Wang, Jiefeng Chen, Jieyu Zhao, Jinsung Yoon, Linxin Song, Tomas Pfister, Yue Huang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-27T19:57:15Z","title":"Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29054","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f32bbc54bdd7c66501d29a543c6796ffa4a82780ffd6e0244bd034da498def9b","target":"record","created_at":"2026-05-29T01:04:44Z","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":"5b98aaab0ca4bf3743e13ee3c9f91e802935ee0f7a533a17adad8c3c4005df8e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-27T19:57:15Z","title_canon_sha256":"cec01fca9b3685f6c7b7b63f9144255aaa1026b0ae0d74391b401983760f07fc"},"schema_version":"1.0","source":{"id":"2605.29054","kind":"arxiv","version":1}},"canonical_sha256":"365de7d49cf55c2004565323aa46823beb83328cf03c8e93f352e10d7b7b4135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"365de7d49cf55c2004565323aa46823beb83328cf03c8e93f352e10d7b7b4135","first_computed_at":"2026-05-29T01:04:44.728491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:44.728491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"crdApwisAlEUhxtQeroR8HRfSB9IU614WIfiGX7LhIE2+7b8If+hTy74JEzlvPuAJEZu/i0DZZeE9T0h5uxxCg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:44.728959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f32bbc54bdd7c66501d29a543c6796ffa4a82780ffd6e0244bd034da498def9b","sha256:45ee33af90b32790622d85cf947043d5db61d4bd8d164c3b36e999ce427a7bc0"],"state_sha256":"740c46669e2f365435fbf09ed10f18490bbf50875d4575ec5713a291d7524668"}