{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UEX6YPOCLSJJ3X37QQXW2CVRXA","short_pith_number":"pith:UEX6YPOC","schema_version":"1.0","canonical_sha256":"a12fec3dc25c929ddf7f842f6d0ab1b81f54b3227721f98e7bfdb5331a901436","source":{"kind":"arxiv","id":"2407.04693","version":2},"attestation_state":"computed","paper":{"title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqi Lyu, Dahua Lin, Kai Chen, Wenwei Zhang, Yuzhe Gu, Ziwei Ji","submitted_at":"2024-07-05T17:56:38Z","abstract_excerpt":"Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications. Current hallucination detection and mitigation datasets are limited in domains and sizes, which struggle to scale due to prohibitive labor costs and insufficient reliability of existing hallucination annotators. To facilitate the scalable oversight of LLM hallucinations, this paper introduces an iterative self-training framework that simultaneously and progressively scales up the hallucination annotation dataset and improves the accuracy of the hallucination a"},"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":"2407.04693","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T17:56:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5af3ce31fe765b0cb7b516941f8b12bf7fb6ec403d2db76a16d949d35616d234","abstract_canon_sha256":"25881ce2300f1135e870c17c9c5d6dab1c88e824cc77e12604824ab328867748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:34.286629Z","signature_b64":"/h+EckG5nW3JR90Wk+Ys7os3X8f0ujucxZ/73DW8Z22o7EzXnRN9lswPn7LZyi2xEqJulDTCjAveEDTw74YpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a12fec3dc25c929ddf7f842f6d0ab1b81f54b3227721f98e7bfdb5331a901436","last_reissued_at":"2026-07-05T09:51:34.286100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:34.286100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqi Lyu, Dahua Lin, Kai Chen, Wenwei Zhang, Yuzhe Gu, Ziwei Ji","submitted_at":"2024-07-05T17:56:38Z","abstract_excerpt":"Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications. Current hallucination detection and mitigation datasets are limited in domains and sizes, which struggle to scale due to prohibitive labor costs and insufficient reliability of existing hallucination annotators. To facilitate the scalable oversight of LLM hallucinations, this paper introduces an iterative self-training framework that simultaneously and progressively scales up the hallucination annotation dataset and improves the accuracy of the hallucination a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04693","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/2407.04693/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":"2407.04693","created_at":"2026-07-05T09:51:34.286165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04693v2","created_at":"2026-07-05T09:51:34.286165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04693","created_at":"2026-07-05T09:51:34.286165+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEX6YPOCLSJJ","created_at":"2026-07-05T09:51:34.286165+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEX6YPOCLSJJ3X37","created_at":"2026-07-05T09:51:34.286165+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEX6YPOC","created_at":"2026-07-05T09:51:34.286165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05221","citing_title":"ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language Tracking","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA","json":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA.json","graph_json":"https://pith.science/api/pith-number/UEX6YPOCLSJJ3X37QQXW2CVRXA/graph.json","events_json":"https://pith.science/api/pith-number/UEX6YPOCLSJJ3X37QQXW2CVRXA/events.json","paper":"https://pith.science/paper/UEX6YPOC"},"agent_actions":{"view_html":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA","download_json":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA.json","view_paper":"https://pith.science/paper/UEX6YPOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04693&json=true","fetch_graph":"https://pith.science/api/pith-number/UEX6YPOCLSJJ3X37QQXW2CVRXA/graph.json","fetch_events":"https://pith.science/api/pith-number/UEX6YPOCLSJJ3X37QQXW2CVRXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA/action/storage_attestation","attest_author":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA/action/author_attestation","sign_citation":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA/action/citation_signature","submit_replication":"https://pith.science/pith/UEX6YPOCLSJJ3X37QQXW2CVRXA/action/replication_record"}},"created_at":"2026-07-05T09:51:34.286165+00:00","updated_at":"2026-07-05T09:51:34.286165+00:00"}