{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OZO6W6MLSSUGW2I374YR4UWHAI","short_pith_number":"pith:OZO6W6ML","schema_version":"1.0","canonical_sha256":"765deb798b94a86b691bff311e52c702141325887dfa1d86e31aa3b92ebb59a3","source":{"kind":"arxiv","id":"2410.08393","version":1},"attestation_state":"computed","paper":{"title":"The Effects of Hallucinations in Synthetic Training Data for Relation Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Michael F\\\"arber, Nicholas Popovic, Steven Rogulsky","submitted_at":"2024-10-10T22:00:16Z","abstract_excerpt":"Relation extraction is crucial for constructing knowledge graphs, with large high-quality datasets serving as the foundation for training, fine-tuning, and evaluating models. Generative data augmentation (GDA) is a common approach to expand such datasets. However, this approach often introduces hallucinations, such as spurious facts, whose impact on relation extraction remains underexplored. In this paper, we examine the effects of hallucinations on the performance of relation extraction on the document and sentence levels. Our empirical study reveals that hallucinations considerably compromis"},"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":"2410.08393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T22:00:16Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"ca7144d572152def66b7e64a6c6444f25c9a21947aba5a1691276ddf1babe53e","abstract_canon_sha256":"0539b479fd43010c39660773ed76e585012a2a6e4023fd744e7a6e1cba3f2f16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:57.850188Z","signature_b64":"CKRdPaVtSUQGOJyssHy43EsB++6KwBI4Gfthnnt7CVoH+E+t852pyEBIfOS0uMvXLmyTGU/hn63WD1W7t4zaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"765deb798b94a86b691bff311e52c702141325887dfa1d86e31aa3b92ebb59a3","last_reissued_at":"2026-07-05T09:18:57.849647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:57.849647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Effects of Hallucinations in Synthetic Training Data for Relation Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Michael F\\\"arber, Nicholas Popovic, Steven Rogulsky","submitted_at":"2024-10-10T22:00:16Z","abstract_excerpt":"Relation extraction is crucial for constructing knowledge graphs, with large high-quality datasets serving as the foundation for training, fine-tuning, and evaluating models. Generative data augmentation (GDA) is a common approach to expand such datasets. However, this approach often introduces hallucinations, such as spurious facts, whose impact on relation extraction remains underexplored. In this paper, we examine the effects of hallucinations on the performance of relation extraction on the document and sentence levels. Our empirical study reveals that hallucinations considerably compromis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08393","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/2410.08393/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":"2410.08393","created_at":"2026-07-05T09:18:57.849728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08393v1","created_at":"2026-07-05T09:18:57.849728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08393","created_at":"2026-07-05T09:18:57.849728+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZO6W6MLSSUG","created_at":"2026-07-05T09:18:57.849728+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZO6W6MLSSUGW2I3","created_at":"2026-07-05T09:18:57.849728+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZO6W6ML","created_at":"2026-07-05T09:18:57.849728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI","json":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI.json","graph_json":"https://pith.science/api/pith-number/OZO6W6MLSSUGW2I374YR4UWHAI/graph.json","events_json":"https://pith.science/api/pith-number/OZO6W6MLSSUGW2I374YR4UWHAI/events.json","paper":"https://pith.science/paper/OZO6W6ML"},"agent_actions":{"view_html":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI","download_json":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI.json","view_paper":"https://pith.science/paper/OZO6W6ML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08393&json=true","fetch_graph":"https://pith.science/api/pith-number/OZO6W6MLSSUGW2I374YR4UWHAI/graph.json","fetch_events":"https://pith.science/api/pith-number/OZO6W6MLSSUGW2I374YR4UWHAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI/action/storage_attestation","attest_author":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI/action/author_attestation","sign_citation":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI/action/citation_signature","submit_replication":"https://pith.science/pith/OZO6W6MLSSUGW2I374YR4UWHAI/action/replication_record"}},"created_at":"2026-07-05T09:18:57.849728+00:00","updated_at":"2026-07-05T09:18:57.849728+00:00"}