{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HAMR7AM3OU3LSTZBHTAXSNQRSQ","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":"9ddfd395bc04d01a34910a93a9a510be12c7f869972b0ce70aac0886cffbff4d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T08:43:46Z","title_canon_sha256":"34b605e23c0ccae2ec037b258b586bfcfffd8c3e9a3e6f992b6322896423872d"},"schema_version":"1.0","source":{"id":"2305.15852","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15852","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15852v3","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15852","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_12","alias_value":"HAMR7AM3OU3L","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_16","alias_value":"HAMR7AM3OU3LSTZB","created_at":"2026-07-05T07:56:48Z"},{"alias_kind":"pith_short_8","alias_value":"HAMR7AM3","created_at":"2026-07-05T07:56:48Z"}],"graph_snapshots":[{"event_id":"sha256:eeb086b86104b2e903e9d70403e85cac52dbed951b085bd379b70909d62fe805","target":"graph","created_at":"2026-07-05T07:56:48Z","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/2305.15852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (large LMs) are susceptible to producing text that contains hallucinated content. An important instance of this problem is self-contradiction, where the LM generates two contradictory sentences within the same context. In this work, we present a comprehensive investigation into self-contradiction for various instruction-tuned LMs, covering evaluation, detection, and mitigation. Our primary evaluation task is open-domain text generation, but we also demonstrate the applicability of our approach to shorter question answering. Our analysis reveals the prevalence of self-cont","authors_text":"Jingxuan He, Martin Vechev, Niels M\\\"undler, Slobodan Jenko","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T08:43:46Z","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15852","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":"sha256:48c5c8e6623dc4fb9e8ea23ea16053c5b9d4ad78e19d30af4d00065ed44b8f70","target":"record","created_at":"2026-07-05T07:56:48Z","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":"9ddfd395bc04d01a34910a93a9a510be12c7f869972b0ce70aac0886cffbff4d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T08:43:46Z","title_canon_sha256":"34b605e23c0ccae2ec037b258b586bfcfffd8c3e9a3e6f992b6322896423872d"},"schema_version":"1.0","source":{"id":"2305.15852","kind":"arxiv","version":3}},"canonical_sha256":"38191f819b7536b94f213cc1793611942372268cbd5d62efdd9c10d4789eea10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38191f819b7536b94f213cc1793611942372268cbd5d62efdd9c10d4789eea10","first_computed_at":"2026-07-05T07:56:48.726188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:48.726188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XD2l5HQXUBOF+/sAKzFx5120fHzp4ckym1xUk1GlTgn/CmJtFzEYA9sAb7R3eqTpwhPsssvyH9zqEVL22MGBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:48.726835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15852","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48c5c8e6623dc4fb9e8ea23ea16053c5b9d4ad78e19d30af4d00065ed44b8f70","sha256:eeb086b86104b2e903e9d70403e85cac52dbed951b085bd379b70909d62fe805"],"state_sha256":"e4dcef343289cfc4192b51786d83c0fdb25c3718e08a7b1be9ec76bae3b50d44"}