{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4SA6VYCIUAA6EWBBYCZUSVB5LR","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":"ae35390d5d19ee3c2389a01b7bc8b08e3fc6f317c10551b162ca540e581551bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-17T05:15:24Z","title_canon_sha256":"6d75eaa37d76eefe233a3d29de1eab0be00efe1fa7b48ae31070c9ee745c107f"},"schema_version":"1.0","source":{"id":"2204.07931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07931","created_at":"2026-07-05T04:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07931v1","created_at":"2026-07-05T04:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07931","created_at":"2026-07-05T04:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"4SA6VYCIUAA6","created_at":"2026-07-05T04:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"4SA6VYCIUAA6EWBB","created_at":"2026-07-05T04:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"4SA6VYCI","created_at":"2026-07-05T04:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:0bd632f8fbff5d7181fc0c49d4f1559dd1d2bedbcbf4d4a45ad9398fb4cfebb7","target":"graph","created_at":"2026-07-05T04:15:19Z","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/2204.07931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination. In this work, we investigate the underlying causes of this phenomenon: is hallucination due to the training data, or to the models? We conduct a comprehensive human study on both existing knowledge-grounded conversational benchmarks and several state-of-the-art models. Our study reveals that the standard benchmarks consist of >60% hallucinated responses, leading to models that not only hallucinate but even amplify hallucinations. Our findings rai","authors_text":"Mo Yu, Nouha Dziri, Osmar Zaiane, Sivan Milton, Siva Reddy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-17T05:15:24Z","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07931","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:c2e869e0efb05b847fd28662e04dc554eefe43848376e40b1fd3685be93c1311","target":"record","created_at":"2026-07-05T04:15:19Z","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":"ae35390d5d19ee3c2389a01b7bc8b08e3fc6f317c10551b162ca540e581551bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-17T05:15:24Z","title_canon_sha256":"6d75eaa37d76eefe233a3d29de1eab0be00efe1fa7b48ae31070c9ee745c107f"},"schema_version":"1.0","source":{"id":"2204.07931","kind":"arxiv","version":1}},"canonical_sha256":"e481eae048a001e25821c0b349543d5c72a42cf44ecb12453e528d2507adb3ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e481eae048a001e25821c0b349543d5c72a42cf44ecb12453e528d2507adb3ab","first_computed_at":"2026-07-05T04:15:19.929137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:19.929137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9RODOW9pYaaiC9C3UtLP/RkLw26Ugw0Ms7kzwZnAcx66yAEjYdwAbuoAy9Y9djUHIstz178SZfun59chwueOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:19.929551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2e869e0efb05b847fd28662e04dc554eefe43848376e40b1fd3685be93c1311","sha256:0bd632f8fbff5d7181fc0c49d4f1559dd1d2bedbcbf4d4a45ad9398fb4cfebb7"],"state_sha256":"03869189a31ea41d29f615d1f8626c61ff3d91f86dc52a8d2f4998b5a41d13fa"}