{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3TOMQJPZ5OM5H6MMTSHBNBYYP","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":"dc6afcaa6cf39c988aab47979ab201817f89c4e775b9505bac4a1ef6597394a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:18:56Z","title_canon_sha256":"a52a797fc8897da23a068b22cef1c6340e0e6d307454f8139694f345b1f50ff8"},"schema_version":"1.0","source":{"id":"2505.17656","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17656","created_at":"2026-07-05T12:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17656v3","created_at":"2026-07-05T12:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17656","created_at":"2026-07-05T12:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"P3TOMQJPZ5OM","created_at":"2026-07-05T12:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"P3TOMQJPZ5OM5H6M","created_at":"2026-07-05T12:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"P3TOMQJP","created_at":"2026-07-05T12:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:2b272dc56e5bbdbd5fb4da6d9025ac1dea980c1c3c3e307c79bb91e242becede","target":"graph","created_at":"2026-07-05T12:06:12Z","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/2505.17656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection methods often overlook a critical problem we term as self-consistent error, where LLMs repeatedly generate the same incorrect response across multiple stochastic samples. This work formally defines self-consistent errors and evaluates mainstream detection methods on them. Our investigation reveals two key findings: (1) Unlike inconsistent errors, whose frequency diminishes significantly as the LLM scale increases, t","authors_text":"Du Su, Fei Sun, Hexiang Tan, Huawei Shen, Jingang Wang, Qi Cao, Sha Liu, Xin Chen, Xueqi Cheng, Xunliang Cai, Yuanzhuo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:18:56Z","title":"Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17656","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:c64aa5d8956ba9f9b4ca7b8b823bd37be101700632ff265226981c6a68c93172","target":"record","created_at":"2026-07-05T12:06:12Z","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":"dc6afcaa6cf39c988aab47979ab201817f89c4e775b9505bac4a1ef6597394a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:18:56Z","title_canon_sha256":"a52a797fc8897da23a068b22cef1c6340e0e6d307454f8139694f345b1f50ff8"},"schema_version":"1.0","source":{"id":"2505.17656","kind":"arxiv","version":3}},"canonical_sha256":"7ee6e6412fcf5cce9fcc64e470b438c3ce7c630e6f831bdc5c35fc40efda53fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ee6e6412fcf5cce9fcc64e470b438c3ce7c630e6f831bdc5c35fc40efda53fd","first_computed_at":"2026-07-05T12:06:12.951023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:12.951023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BJ8YfmY91PZwf3p21IrCYP5mD7P6Ma+mKc48hGA/F709qM2bJDHphRP8dZA8BZ4eS+IUIj5aJI9KiNHvPel1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:12.951559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17656","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c64aa5d8956ba9f9b4ca7b8b823bd37be101700632ff265226981c6a68c93172","sha256:2b272dc56e5bbdbd5fb4da6d9025ac1dea980c1c3c3e307c79bb91e242becede"],"state_sha256":"64d6a7b8443c87918223f26ab03d9e51018c1ebbc63fe04e7ec4b7e90ba73121"}