{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RCFD4J776OU6PU7YPYNGJFVIZJ","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":"ffd92c7a4f39dd3fe85a17a33d94241e5a3f25378058405819021d81b07ebf8a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T16:41:30Z","title_canon_sha256":"ae44ed5d619afa68ed9762afd4706b3e0ba96725a06884066d6cce76861183f9"},"schema_version":"1.0","source":{"id":"2507.02778","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02778","created_at":"2026-08-04T01:57:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02778v3","created_at":"2026-08-04T01:57:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02778","created_at":"2026-08-04T01:57:35Z"},{"alias_kind":"pith_short_12","alias_value":"RCFD4J776OU6","created_at":"2026-08-04T01:57:35Z"},{"alias_kind":"pith_short_16","alias_value":"RCFD4J776OU6PU7Y","created_at":"2026-08-04T01:57:35Z"},{"alias_kind":"pith_short_8","alias_value":"RCFD4J77","created_at":"2026-08-04T01:57:35Z"}],"graph_snapshots":[{"event_id":"sha256:555e7b9c604407074682aac9dd944f4775f8a3b6b787ff8bca4ffc29d8f657d7","target":"graph","created_at":"2026-08-04T01:57:35Z","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/2507.02778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths. Self-correction is vital for safety-critical applications, but studying it requires disentangling activation failure from knowledge deficiency: when a model fails to correct an error, is it because it cannot, or because it does not? We introduce Self-Correction Bench, a controlled evaluation framework that isolates this distinction by injecting the same error as either an external (user-attributed) or internal (model-attributed) error, keeping all other context identical. ","authors_text":"Ken Tsui","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T16:41:30Z","title":"Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02778","kind":"arxiv","version":3},"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:cc1cffb12e43a488930023bac5150fa42ff6b4b6e03a065c1389efd30e27cd87","target":"record","created_at":"2026-08-04T01:57:35Z","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":"ffd92c7a4f39dd3fe85a17a33d94241e5a3f25378058405819021d81b07ebf8a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T16:41:30Z","title_canon_sha256":"ae44ed5d619afa68ed9762afd4706b3e0ba96725a06884066d6cce76861183f9"},"schema_version":"1.0","source":{"id":"2507.02778","kind":"arxiv","version":3}},"canonical_sha256":"888a3e27fff3a9e7d3f87e1a6496a8ca60ff571eaf88e61c264a330ace133790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"888a3e27fff3a9e7d3f87e1a6496a8ca60ff571eaf88e61c264a330ace133790","first_computed_at":"2026-08-04T01:57:35.539456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:57:35.539456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uDG155txaO15XW5mT1if1Dewg29i1DU0JyOPGCws1imyPFbG17rgCMTw29FZuKJloo0rxG25Iw2ygtu6nmGbDA==","signature_status":"signed_v1","signed_at":"2026-08-04T01:57:35.541183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02778","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc1cffb12e43a488930023bac5150fa42ff6b4b6e03a065c1389efd30e27cd87","sha256:555e7b9c604407074682aac9dd944f4775f8a3b6b787ff8bca4ffc29d8f657d7"],"state_sha256":"d219b6d4dd43f8db1781b26ad92931fbf080c89889d587988cdcf91078ad62f4"}