{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2TFAUQGA5YMIG4MNNSQDAZKZ66","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":"d994f9113b3e927d4de9904bc5c20772a6e53f24a6fd04135960c92ddd1d3369","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T20:41:08Z","title_canon_sha256":"98433f394aaf119718da7b82f13cff9a4799b28fbb01616a1dd93451e596e8da"},"schema_version":"1.0","source":{"id":"2605.29087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29087","created_at":"2026-05-29T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29087v1","created_at":"2026-05-29T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29087","created_at":"2026-05-29T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"2TFAUQGA5YMI","created_at":"2026-05-29T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"2TFAUQGA5YMIG4MN","created_at":"2026-05-29T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"2TFAUQGA","created_at":"2026-05-29T01:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:4a45cef2cfc9720bb79424cda54b7f95dc28af6c80682e17b479a6fc2d6bbd3f","target":"graph","created_at":"2026-05-29T01:05:17Z","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/2605.29087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the chain-of-thought stays factually correct from first turn to last while the emitted answer flips wrong. We call this unfaithful capitulation (UC) and isolate it with a $2\\times 2$ latent-versus-behavioral framework that flip-rate metrics and single-turn faithfulness probes both miss. Across three datasets (MT-Consistency, MMLU-Pro, GSM8K), the latent-correct rate at the beh","authors_text":"Ramayya Krishnan, Rema Padman, Yubo Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T20:41:08Z","title":"The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29087","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:cc0ba41b98009bf77660d02cbc32471eba75a716f0a4a22c31452e81336d311e","target":"record","created_at":"2026-05-29T01:05:17Z","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":"d994f9113b3e927d4de9904bc5c20772a6e53f24a6fd04135960c92ddd1d3369","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T20:41:08Z","title_canon_sha256":"98433f394aaf119718da7b82f13cff9a4799b28fbb01616a1dd93451e596e8da"},"schema_version":"1.0","source":{"id":"2605.29087","kind":"arxiv","version":1}},"canonical_sha256":"d4ca0a40c0ee1883718d6ca0306559f7957123883b1a98ea52e264794802bc8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4ca0a40c0ee1883718d6ca0306559f7957123883b1a98ea52e264794802bc8c","first_computed_at":"2026-05-29T01:05:17.600920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:17.600920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X36EVGqiD+Lp1wS5LfjMiUN3jfh9M+wjwwvYqG0WUkrMd0qGKrj4SkR0DXnKZv0ru4VO7vFHiym9GOew6PADCA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:17.601976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc0ba41b98009bf77660d02cbc32471eba75a716f0a4a22c31452e81336d311e","sha256:4a45cef2cfc9720bb79424cda54b7f95dc28af6c80682e17b479a6fc2d6bbd3f"],"state_sha256":"f77fb652cf398b5e9f757c831723893289dc390394b56ba56efbb0fde0347c13"}