{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2TFAUQGA5YMIG4MNNSQDAZKZ66","short_pith_number":"pith:2TFAUQGA","canonical_record":{"source":{"id":"2605.29087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T20:41:08Z","cross_cats_sorted":[],"title_canon_sha256":"98433f394aaf119718da7b82f13cff9a4799b28fbb01616a1dd93451e596e8da","abstract_canon_sha256":"d994f9113b3e927d4de9904bc5c20772a6e53f24a6fd04135960c92ddd1d3369"},"schema_version":"1.0"},"canonical_sha256":"d4ca0a40c0ee1883718d6ca0306559f7957123883b1a98ea52e264794802bc8c","source":{"kind":"arxiv","id":"2605.29087","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2TFAUQGA5YMIG4MNNSQDAZKZ66","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T20:41:08Z","cross_cats_sorted":[],"title_canon_sha256":"98433f394aaf119718da7b82f13cff9a4799b28fbb01616a1dd93451e596e8da","abstract_canon_sha256":"d994f9113b3e927d4de9904bc5c20772a6e53f24a6fd04135960c92ddd1d3369"},"schema_version":"1.0"},"canonical_sha256":"d4ca0a40c0ee1883718d6ca0306559f7957123883b1a98ea52e264794802bc8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:17.601976Z","signature_b64":"X36EVGqiD+Lp1wS5LfjMiUN3jfh9M+wjwwvYqG0WUkrMd0qGKrj4SkR0DXnKZv0ru4VO7vFHiym9GOew6PADCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4ca0a40c0ee1883718d6ca0306559f7957123883b1a98ea52e264794802bc8c","last_reissued_at":"2026-05-29T01:05:17.600920Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:17.600920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29087","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RITAjZzEM//LsZ0W9jL3zrUkIO8TYsrr00K+R8lq9cLkCfzXXJJltUJW3EEqIRvwAGy+HAamc31eFCg9EKdHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:59:29.221625Z"},"content_sha256":"cc0ba41b98009bf77660d02cbc32471eba75a716f0a4a22c31452e81336d311e","schema_version":"1.0","event_id":"sha256:cc0ba41b98009bf77660d02cbc32471eba75a716f0a4a22c31452e81336d311e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2TFAUQGA5YMIG4MNNSQDAZKZ66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ramayya Krishnan, Rema Padman, Yubo Li","submitted_at":"2026-05-27T20:41:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29087","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/2605.29087/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"av7rDGeT18y07fU1Bnrq7aAuCgaHOUDlmkiyQOF64VXDgA12GuO2QTa5rXIAcJQH4ox5J0f6wuZf9Fax76wfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:59:29.222011Z"},"content_sha256":"4a45cef2cfc9720bb79424cda54b7f95dc28af6c80682e17b479a6fc2d6bbd3f","schema_version":"1.0","event_id":"sha256:4a45cef2cfc9720bb79424cda54b7f95dc28af6c80682e17b479a6fc2d6bbd3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66/bundle.json","state_url":"https://pith.science/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66/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":"2026-06-02T17:59:29Z","links":{"resolver":"https://pith.science/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66","bundle":"https://pith.science/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66/bundle.json","state":"https://pith.science/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TFAUQGA5YMIG4MNNSQDAZKZ66/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"szn+Th9UHwGrdiV7DraZsZ0PXaq//jcqJYi38Yye0kvIF1QRMB2+SHjRaIIDmWDhPJSls7mlIhjOklXgtdVPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T17:59:29.224880Z","bundle_sha256":"c57ffa8a7794e9ffab1e4945376c71bc38593a63bb28809dd76ca2232c553921"}}