{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WWDXT3E5Y3BRGAOOXHHMO7AMHJ","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":"4999fb6121e7c8119c141aa93a83f7692a67c27784108008e95564b35b8697fb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:17Z","title_canon_sha256":"e83957b0bfe29a847be1f756a71051cee320fb99972fdd8eac184bfdee40bbe9"},"schema_version":"1.0","source":{"id":"2310.10627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10627","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10627v1","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10627","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"WWDXT3E5Y3BR","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"WWDXT3E5Y3BRGAOO","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"WWDXT3E5","created_at":"2026-07-05T07:01:22Z"}],"graph_snapshots":[{"event_id":"sha256:ead5f15a6a4c2fede070a305d02910757d5d241987b02a3dc157d0b1f271cd67","target":"graph","created_at":"2026-07-05T07:01:22Z","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/2310.10627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucination plagues even frontier LLMs--but how bad is it really for summarizing academic papers? We evaluate Factored Verification, a simple automated method for detecting hallucinations in abstractive summaries. This method sets a new SotA on hallucination detection in the summarization task of the HaluEval benchmark, achieving 76.2% accuracy. We then use this method to estimate how often language models hallucinate when summarizing across multiple academic papers and find 0.62 hallucinations in the average ChatGPT (16k) summary, 0.84 for GPT-4, and 1.55 for Claude 2. We ask models to self","authors_text":"Andreas Stuhlm\\\"uller, Charlie George","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:17Z","title":"Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10627","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":"sha256:8a181a41b918f27384e19c64566563bfa42a030a9fd2d0d7a8c394330784eeb6","target":"record","created_at":"2026-07-05T07:01:22Z","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":"4999fb6121e7c8119c141aa93a83f7692a67c27784108008e95564b35b8697fb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:17Z","title_canon_sha256":"e83957b0bfe29a847be1f756a71051cee320fb99972fdd8eac184bfdee40bbe9"},"schema_version":"1.0","source":{"id":"2310.10627","kind":"arxiv","version":1}},"canonical_sha256":"b58779ec9dc6c31301ceb9cec77c0c3a5340b076879e024ff4575a4aaffea7fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b58779ec9dc6c31301ceb9cec77c0c3a5340b076879e024ff4575a4aaffea7fd","first_computed_at":"2026-07-05T07:01:22.548751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:22.548751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ymt6IPE7KqSpP1vSa0SXAIHkATc1Hw6mG38ICjrr1nlIIkPilpCBQBFyOomYpppTIlj6rgXQs5LX2q2YUt0PAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:22.549237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a181a41b918f27384e19c64566563bfa42a030a9fd2d0d7a8c394330784eeb6","sha256:ead5f15a6a4c2fede070a305d02910757d5d241987b02a3dc157d0b1f271cd67"],"state_sha256":"729056b03dca5652280a371e66bc014ac89381ba7c3a5c36debc7f389b1ff523"}