{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JWSPTDHBXNS2PFTU5F4DFR5XPI","short_pith_number":"pith:JWSPTDHB","schema_version":"1.0","canonical_sha256":"4da4f98ce1bb65a79674e97832c7b77a1634c815c4ecb226ab43573e3179f1b9","source":{"kind":"arxiv","id":"2308.03188","version":2},"attestation_state":"computed","paper":{"title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Deepak Nathani, Liangming Pan, Michael Saxon, Wenda Xu, William Yang Wang, Xinyi Wang","submitted_at":"2023-08-06T18:38:52Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and de"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.03188","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-06T18:38:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3f4583a106c09e823c97ab678763e1ebc7cf6bda75e8250bc52b64ee268801fb","abstract_canon_sha256":"88f84c09e9ce1130847a4e0bc65f9704068250ae3b620e4669183176f3c18756"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:07.344604Z","signature_b64":"z/iBTM1IQu0tQbnjt5U+0d3CufMZL/NVA1z37vEJZkFC4yZY2Sz8DLrtud3AAeUQA9RsGAcGDQSFpqgX/wdkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4da4f98ce1bb65a79674e97832c7b77a1634c815c4ecb226ab43573e3179f1b9","last_reissued_at":"2026-07-05T06:46:07.344115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:07.344115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Deepak Nathani, Liangming Pan, Michael Saxon, Wenda Xu, William Yang Wang, Xinyi Wang","submitted_at":"2023-08-06T18:38:52Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03188","kind":"arxiv","version":2},"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/2308.03188/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.03188","created_at":"2026-07-05T06:46:07.344172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.03188v2","created_at":"2026-07-05T06:46:07.344172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03188","created_at":"2026-07-05T06:46:07.344172+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWSPTDHBXNS2","created_at":"2026-07-05T06:46:07.344172+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWSPTDHBXNS2PFTU","created_at":"2026-07-05T06:46:07.344172+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWSPTDHB","created_at":"2026-07-05T06:46:07.344172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08068","citing_title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04435","citing_title":"Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01976","citing_title":"AutoBG: A Board Game Design Assistant with Interactive Ideation, Iterative Rulebook Generation, and Individualized Feedback","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02724","citing_title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30449","citing_title":"Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21773","citing_title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01481","citing_title":"TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22972","citing_title":"Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2401.11817","citing_title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2602.24273","citing_title":"A Minimal Agent for Automated Theorem Proving","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03245","citing_title":"FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29908","citing_title":"C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10020","citing_title":"Self-Rewarding Language Models","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":248,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01798","citing_title":"Large Language Models Cannot Self-Correct Reasoning Yet","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05497","citing_title":"Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07900","citing_title":"AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02236","citing_title":"Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI","json":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI.json","graph_json":"https://pith.science/api/pith-number/JWSPTDHBXNS2PFTU5F4DFR5XPI/graph.json","events_json":"https://pith.science/api/pith-number/JWSPTDHBXNS2PFTU5F4DFR5XPI/events.json","paper":"https://pith.science/paper/JWSPTDHB"},"agent_actions":{"view_html":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI","download_json":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI.json","view_paper":"https://pith.science/paper/JWSPTDHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.03188&json=true","fetch_graph":"https://pith.science/api/pith-number/JWSPTDHBXNS2PFTU5F4DFR5XPI/graph.json","fetch_events":"https://pith.science/api/pith-number/JWSPTDHBXNS2PFTU5F4DFR5XPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI/action/storage_attestation","attest_author":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI/action/author_attestation","sign_citation":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI/action/citation_signature","submit_replication":"https://pith.science/pith/JWSPTDHBXNS2PFTU5F4DFR5XPI/action/replication_record"}},"created_at":"2026-07-05T06:46:07.344172+00:00","updated_at":"2026-07-05T06:46:07.344172+00:00"}