{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4VUTL42TBNAY52DP5CQ45W75GK","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":"70b703acbf1ee669f88355d885e3ff7a88e37c360997bc0764b880095f9578f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:13:08Z","title_canon_sha256":"c8f578a57a6a85a247f0672289794ea5f8f0bc0949049945284603e56414b290"},"schema_version":"1.0","source":{"id":"2501.08292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08292","created_at":"2026-07-05T10:00:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08292v1","created_at":"2026-07-05T10:00:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08292","created_at":"2026-07-05T10:00:58Z"},{"alias_kind":"pith_short_12","alias_value":"4VUTL42TBNAY","created_at":"2026-07-05T10:00:58Z"},{"alias_kind":"pith_short_16","alias_value":"4VUTL42TBNAY52DP","created_at":"2026-07-05T10:00:58Z"},{"alias_kind":"pith_short_8","alias_value":"4VUTL42T","created_at":"2026-07-05T10:00:58Z"}],"graph_snapshots":[{"event_id":"sha256:11f7bd8233e4c924c8f4d26ff6114a72ebc6561d5d67595120a9b878fa1ac4ce","target":"graph","created_at":"2026-07-05T10:00:58Z","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/2501.08292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhilasha Ravichander, David Wadden, Shrusti Ghela, Yejin Choi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:13:08Z","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08292","kind":"arxiv","version":1},"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":"sha256:926c32bafce2a1c78f5d2fc87e0e4102d857da583b77710e147e3addd9a68eec","target":"record","created_at":"2026-07-05T10:00:58Z","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":"70b703acbf1ee669f88355d885e3ff7a88e37c360997bc0764b880095f9578f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:13:08Z","title_canon_sha256":"c8f578a57a6a85a247f0672289794ea5f8f0bc0949049945284603e56414b290"},"schema_version":"1.0","source":{"id":"2501.08292","kind":"arxiv","version":1}},"canonical_sha256":"e56935f3530b418ee86fe8a1cedbfd32b2b2a05587fd018d1980e45df4fa39bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56935f3530b418ee86fe8a1cedbfd32b2b2a05587fd018d1980e45df4fa39bb","first_computed_at":"2026-07-05T10:00:58.935915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:58.935915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XAWxkW72zHJNRlSNMjBeO5G6oId4WTNC9Jh1A0C9aDSxje1x996kPDK8sHBxIjLjuWBpNmwEIZDDoigHlYXSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:58.936344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:926c32bafce2a1c78f5d2fc87e0e4102d857da583b77710e147e3addd9a68eec","sha256:11f7bd8233e4c924c8f4d26ff6114a72ebc6561d5d67595120a9b878fa1ac4ce"],"state_sha256":"452459e707ca0423b2b721e0ee2b65b26037569feea742d233a10eaf7c25ed0f"}