{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B5NS5MWTFFVGXRRXOJO4GSRNWH","short_pith_number":"pith:B5NS5MWT","schema_version":"1.0","canonical_sha256":"0f5b2eb2d3296a6bc637725dc34a2db1e8a98f195c473df8e11485ed0dba863b","source":{"kind":"arxiv","id":"2104.04302","version":1},"attestation_state":"computed","paper":{"title":"Annotating and Modeling Fine-grained Factuality in Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Tanya Goyal","submitted_at":"2021-04-09T11:20:44Z","abstract_excerpt":"Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors. While a number of annotated datasets and statistical models for assessing factuality have been explored, there is no clear picture of what errors are most important to target or where current techniques are succeeding and failing. We explore both synthetic and human-labeled data sources for training models to identify factual errors in summarizat"},"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":"2104.04302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-09T11:20:44Z","cross_cats_sorted":[],"title_canon_sha256":"c7d90a5df3dba3b5b88425deb5c94e304b932e89a57160548dc7b906890d34c4","abstract_canon_sha256":"1552cd2a05094ae15a3a74efba8f449ba6c88b54d544c7ce385f7a651eee26fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:37.912057Z","signature_b64":"fhdu1MNixwokgDTrVXqdPo2ZE2RQIna0ZM9b90a0L/RO+pPrGxPAs2PCy20unOI6aOcfSj4LoxxOJlLiKokvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f5b2eb2d3296a6bc637725dc34a2db1e8a98f195c473df8e11485ed0dba863b","last_reissued_at":"2026-07-05T02:30:37.911687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:37.911687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Annotating and Modeling Fine-grained Factuality in Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Tanya Goyal","submitted_at":"2021-04-09T11:20:44Z","abstract_excerpt":"Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors. While a number of annotated datasets and statistical models for assessing factuality have been explored, there is no clear picture of what errors are most important to target or where current techniques are succeeding and failing. We explore both synthetic and human-labeled data sources for training models to identify factual errors in summarizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04302","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/2104.04302/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":"2104.04302","created_at":"2026-07-05T02:30:37.911743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04302v1","created_at":"2026-07-05T02:30:37.911743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04302","created_at":"2026-07-05T02:30:37.911743+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5NS5MWTFFVG","created_at":"2026-07-05T02:30:37.911743+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5NS5MWTFFVGXRRX","created_at":"2026-07-05T02:30:37.911743+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5NS5MWT","created_at":"2026-07-05T02:30:37.911743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19966","citing_title":"Bridging Context Gaps: Enhancing Comprehension in Long-Form Social Conversations Through Contextualized Excerpts","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH","json":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH.json","graph_json":"https://pith.science/api/pith-number/B5NS5MWTFFVGXRRXOJO4GSRNWH/graph.json","events_json":"https://pith.science/api/pith-number/B5NS5MWTFFVGXRRXOJO4GSRNWH/events.json","paper":"https://pith.science/paper/B5NS5MWT"},"agent_actions":{"view_html":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH","download_json":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH.json","view_paper":"https://pith.science/paper/B5NS5MWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04302&json=true","fetch_graph":"https://pith.science/api/pith-number/B5NS5MWTFFVGXRRXOJO4GSRNWH/graph.json","fetch_events":"https://pith.science/api/pith-number/B5NS5MWTFFVGXRRXOJO4GSRNWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH/action/storage_attestation","attest_author":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH/action/author_attestation","sign_citation":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH/action/citation_signature","submit_replication":"https://pith.science/pith/B5NS5MWTFFVGXRRXOJO4GSRNWH/action/replication_record"}},"created_at":"2026-07-05T02:30:37.911743+00:00","updated_at":"2026-07-05T02:30:37.911743+00:00"}