{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JFKHF4YBVVSAUEU6WUAITAQJKK","short_pith_number":"pith:JFKHF4YB","schema_version":"1.0","canonical_sha256":"495472f301ad640a129eb5008982095288e8d362ade3afa5e715aedaf6d1b7de","source":{"kind":"arxiv","id":"2109.09784","version":2},"attestation_state":"computed","paper":{"title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Meng Cao, Yue Dong","submitted_at":"2021-08-30T15:40:52Z","abstract_excerpt":"State-of-the-art abstractive summarization systems often generate \\emph{hallucinations}; i.e., content that is not directly inferable from the source text. Despite being assumed incorrect, we find that much hallucinated content is factual, namely consistent with world knowledge. These factual hallucinations can be beneficial in a summary by providing useful background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method utilizes an entity's prior and posterior probabilities according to pre-trained and f"},"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":"2109.09784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-30T15:40:52Z","cross_cats_sorted":[],"title_canon_sha256":"4c1a91b6bce181e2f837f464b1b898a53db886d52e44f70a378d1cb84afea42d","abstract_canon_sha256":"a91ad46aabbc6d7f1a9ecb80aa9c22eec4acf39c3f0ddb9d4be0790bf08a34fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:08.278752Z","signature_b64":"INV0QgQSVDOMvto3AJ7/HamsymnznCoug6qZgNlfes13M5ehEv8P+FdnRZuRmF/GIKIKu3RDlab+/NbgQ7ZeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"495472f301ad640a129eb5008982095288e8d362ade3afa5e715aedaf6d1b7de","last_reissued_at":"2026-07-05T03:38:08.278247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:08.278247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Meng Cao, Yue Dong","submitted_at":"2021-08-30T15:40:52Z","abstract_excerpt":"State-of-the-art abstractive summarization systems often generate \\emph{hallucinations}; i.e., content that is not directly inferable from the source text. Despite being assumed incorrect, we find that much hallucinated content is factual, namely consistent with world knowledge. These factual hallucinations can be beneficial in a summary by providing useful background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method utilizes an entity's prior and posterior probabilities according to pre-trained and f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09784","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/2109.09784/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":"2109.09784","created_at":"2026-07-05T03:38:08.278308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09784v2","created_at":"2026-07-05T03:38:08.278308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09784","created_at":"2026-07-05T03:38:08.278308+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFKHF4YBVVSA","created_at":"2026-07-05T03:38:08.278308+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFKHF4YBVVSAUEU6","created_at":"2026-07-05T03:38:08.278308+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFKHF4YB","created_at":"2026-07-05T03:38:08.278308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28044","citing_title":"A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK","json":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK.json","graph_json":"https://pith.science/api/pith-number/JFKHF4YBVVSAUEU6WUAITAQJKK/graph.json","events_json":"https://pith.science/api/pith-number/JFKHF4YBVVSAUEU6WUAITAQJKK/events.json","paper":"https://pith.science/paper/JFKHF4YB"},"agent_actions":{"view_html":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK","download_json":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK.json","view_paper":"https://pith.science/paper/JFKHF4YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09784&json=true","fetch_graph":"https://pith.science/api/pith-number/JFKHF4YBVVSAUEU6WUAITAQJKK/graph.json","fetch_events":"https://pith.science/api/pith-number/JFKHF4YBVVSAUEU6WUAITAQJKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK/action/storage_attestation","attest_author":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK/action/author_attestation","sign_citation":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK/action/citation_signature","submit_replication":"https://pith.science/pith/JFKHF4YBVVSAUEU6WUAITAQJKK/action/replication_record"}},"created_at":"2026-07-05T03:38:08.278308+00:00","updated_at":"2026-07-05T03:38:08.278308+00:00"}