{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KEO7E7JI3Y4Y6WVEYF3OYRLQEV","short_pith_number":"pith:KEO7E7JI","schema_version":"1.0","canonical_sha256":"511df27d28de398f5aa4c176ec4570257b05b7d497ffa85f94958969711f950d","source":{"kind":"arxiv","id":"2110.07686","version":2},"attestation_state":"computed","paper":{"title":"Making Document-Level Information Extraction Right for the Right Reasons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhijeet Pradhan, Dhruv Rajan, Greg Durrett, Liyan Tang, R. Nick Bryan, Suyash Mohan","submitted_at":"2021-10-14T19:52:47Z","abstract_excerpt":"Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a radiology report may not be explicitly stated in one place, but nevertheless can be inferred from parts of the report's text. However, these models can easily learn spurious correlations between labels and irrelevant information. This work studies how to ensure that these models make correct inferences from complex text and make those inferences in an auditable wa"},"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":"2110.07686","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T19:52:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bf4c572b7344bb2ed66661d379e3897c35c6d8a1da1e99fc60cc170ae62af47","abstract_canon_sha256":"aeb7e8a7d4230093602fa8a496fabcc95a09850f111b3400fa2c212ca2afebe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:23.330028Z","signature_b64":"DO9k+9yYdD00mAtevvZw+nNm81ba2youTueQYuO1G5SZU8sG20YtYyQ1j0UWnYXtAE4xXBNGdTr9nq0DAZLjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511df27d28de398f5aa4c176ec4570257b05b7d497ffa85f94958969711f950d","last_reissued_at":"2026-07-05T04:24:23.329590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:23.329590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Document-Level Information Extraction Right for the Right Reasons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhijeet Pradhan, Dhruv Rajan, Greg Durrett, Liyan Tang, R. Nick Bryan, Suyash Mohan","submitted_at":"2021-10-14T19:52:47Z","abstract_excerpt":"Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a radiology report may not be explicitly stated in one place, but nevertheless can be inferred from parts of the report's text. However, these models can easily learn spurious correlations between labels and irrelevant information. This work studies how to ensure that these models make correct inferences from complex text and make those inferences in an auditable wa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07686","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/2110.07686/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":"2110.07686","created_at":"2026-07-05T04:24:23.329641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07686v2","created_at":"2026-07-05T04:24:23.329641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07686","created_at":"2026-07-05T04:24:23.329641+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEO7E7JI3Y4Y","created_at":"2026-07-05T04:24:23.329641+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEO7E7JI3Y4Y6WVE","created_at":"2026-07-05T04:24:23.329641+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEO7E7JI","created_at":"2026-07-05T04:24:23.329641+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/KEO7E7JI3Y4Y6WVEYF3OYRLQEV","json":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV.json","graph_json":"https://pith.science/api/pith-number/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/graph.json","events_json":"https://pith.science/api/pith-number/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/events.json","paper":"https://pith.science/paper/KEO7E7JI"},"agent_actions":{"view_html":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV","download_json":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV.json","view_paper":"https://pith.science/paper/KEO7E7JI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07686&json=true","fetch_graph":"https://pith.science/api/pith-number/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/graph.json","fetch_events":"https://pith.science/api/pith-number/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/action/storage_attestation","attest_author":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/action/author_attestation","sign_citation":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/action/citation_signature","submit_replication":"https://pith.science/pith/KEO7E7JI3Y4Y6WVEYF3OYRLQEV/action/replication_record"}},"created_at":"2026-07-05T04:24:23.329641+00:00","updated_at":"2026-07-05T04:24:23.329641+00:00"}