{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4VUTL42TBNAY52DP5CQ45W75GK","short_pith_number":"pith:4VUTL42T","schema_version":"1.0","canonical_sha256":"e56935f3530b418ee86fe8a1cedbfd32b2b2a05587fd018d1980e45df4fa39bb","source":{"kind":"arxiv","id":"2501.08292","version":1},"attestation_state":"computed","paper":{"title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, David Wadden, Shrusti Ghela, Yejin Choi","submitted_at":"2025-01-14T18:13:08Z","abstract_excerpt":"Despite their impressive ability to generate high-quality and fluent text, generative large language models (LLMs) also produce hallucinations: statements that are misaligned with established world knowledge or provided input context. However, measuring hallucination can be challenging, as having humans verify model generations on-the-fly is both expensive and time-consuming. In this work, we release HALoGEN, a comprehensive hallucination benchmark consisting of: (1) 10,923 prompts for generative models spanning nine domains including programming, scientific attribution, and summarization, and"},"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":"2501.08292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:13:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8f578a57a6a85a247f0672289794ea5f8f0bc0949049945284603e56414b290","abstract_canon_sha256":"70b703acbf1ee669f88355d885e3ff7a88e37c360997bc0764b880095f9578f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:58.936344Z","signature_b64":"XAWxkW72zHJNRlSNMjBeO5G6oId4WTNC9Jh1A0C9aDSxje1x996kPDK8sHBxIjLjuWBpNmwEIZDDoigHlYXSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56935f3530b418ee86fe8a1cedbfd32b2b2a05587fd018d1980e45df4fa39bb","last_reissued_at":"2026-07-05T10:00:58.935915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:58.935915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, David Wadden, Shrusti Ghela, Yejin Choi","submitted_at":"2025-01-14T18:13:08Z","abstract_excerpt":"Despite their impressive ability to generate high-quality and fluent text, generative large language models (LLMs) also produce hallucinations: statements that are misaligned with established world knowledge or provided input context. However, measuring hallucination can be challenging, as having humans verify model generations on-the-fly is both expensive and time-consuming. In this work, we release HALoGEN, a comprehensive hallucination benchmark consisting of: (1) 10,923 prompts for generative models spanning nine domains including programming, scientific attribution, and summarization, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08292","kind":"arxiv","version":1},"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/2501.08292/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":"2501.08292","created_at":"2026-07-05T10:00:58.935971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08292v1","created_at":"2026-07-05T10:00:58.935971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08292","created_at":"2026-07-05T10:00:58.935971+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VUTL42TBNAY","created_at":"2026-07-05T10:00:58.935971+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VUTL42TBNAY52DP","created_at":"2026-07-05T10:00:58.935971+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VUTL42T","created_at":"2026-07-05T10:00:58.935971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23414","citing_title":"When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25868","citing_title":"ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06635","citing_title":"Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK","json":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK.json","graph_json":"https://pith.science/api/pith-number/4VUTL42TBNAY52DP5CQ45W75GK/graph.json","events_json":"https://pith.science/api/pith-number/4VUTL42TBNAY52DP5CQ45W75GK/events.json","paper":"https://pith.science/paper/4VUTL42T"},"agent_actions":{"view_html":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK","download_json":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK.json","view_paper":"https://pith.science/paper/4VUTL42T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08292&json=true","fetch_graph":"https://pith.science/api/pith-number/4VUTL42TBNAY52DP5CQ45W75GK/graph.json","fetch_events":"https://pith.science/api/pith-number/4VUTL42TBNAY52DP5CQ45W75GK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK/action/storage_attestation","attest_author":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK/action/author_attestation","sign_citation":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK/action/citation_signature","submit_replication":"https://pith.science/pith/4VUTL42TBNAY52DP5CQ45W75GK/action/replication_record"}},"created_at":"2026-07-05T10:00:58.935971+00:00","updated_at":"2026-07-05T10:00:58.935971+00:00"}