{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M5ORPBRQ7WIZZCQUSL7DHBC7NH","short_pith_number":"pith:M5ORPBRQ","schema_version":"1.0","canonical_sha256":"675d178630fd919c8a1492fe33845f69d26e19906a08cc9f0a80d096f3fbcbd5","source":{"kind":"arxiv","id":"2203.10900","version":1},"attestation_state":"computed","paper":{"title":"Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hwee Tou Ng, Lidong Bing, Qingyu Tan, Ruidan He","submitted_at":"2022-03-21T11:48:40Z","abstract_excerpt":"Document-level Relation Extraction (DocRE) is a more challenging task compared to its sentence-level counterpart. It aims to extract relations from multiple sentences at once. In this paper, we propose a semi-supervised framework for DocRE with three novel components. Firstly, we use an axial attention module for learning the interdependency among entity-pairs, which improves the performance on two-hop relations. Secondly, we propose an adaptive focal loss to tackle the class imbalance problem of DocRE. Lastly, we use knowledge distillation to overcome the differences between human annotated d"},"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":"2203.10900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-21T11:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"663cbb2f583dfd862a1b1684dcaa8f5cf5aca95f69f57a3f455b50f4cc84ba8c","abstract_canon_sha256":"5a345157313d2207fe8f939008d9020a10ce855347cc985415fceb8580f07bae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:58.643451Z","signature_b64":"B0MfBF6VMGdQmqZ89U3O68NVkWFzcXvxmt7gP0mjeH4ohEH2tTJPUL/CeEbt/W4fI5eiD3vf2qajYY/X6C2/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675d178630fd919c8a1492fe33845f69d26e19906a08cc9f0a80d096f3fbcbd5","last_reissued_at":"2026-07-05T04:06:58.642974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:58.642974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hwee Tou Ng, Lidong Bing, Qingyu Tan, Ruidan He","submitted_at":"2022-03-21T11:48:40Z","abstract_excerpt":"Document-level Relation Extraction (DocRE) is a more challenging task compared to its sentence-level counterpart. It aims to extract relations from multiple sentences at once. In this paper, we propose a semi-supervised framework for DocRE with three novel components. Firstly, we use an axial attention module for learning the interdependency among entity-pairs, which improves the performance on two-hop relations. Secondly, we propose an adaptive focal loss to tackle the class imbalance problem of DocRE. Lastly, we use knowledge distillation to overcome the differences between human annotated d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10900","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/2203.10900/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":"2203.10900","created_at":"2026-07-05T04:06:58.643044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10900v1","created_at":"2026-07-05T04:06:58.643044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10900","created_at":"2026-07-05T04:06:58.643044+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5ORPBRQ7WIZ","created_at":"2026-07-05T04:06:58.643044+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5ORPBRQ7WIZZCQU","created_at":"2026-07-05T04:06:58.643044+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5ORPBRQ","created_at":"2026-07-05T04:06:58.643044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22926","citing_title":"Multi-Relation Extraction in Entity Pairs using Global Context","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH","json":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH.json","graph_json":"https://pith.science/api/pith-number/M5ORPBRQ7WIZZCQUSL7DHBC7NH/graph.json","events_json":"https://pith.science/api/pith-number/M5ORPBRQ7WIZZCQUSL7DHBC7NH/events.json","paper":"https://pith.science/paper/M5ORPBRQ"},"agent_actions":{"view_html":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH","download_json":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH.json","view_paper":"https://pith.science/paper/M5ORPBRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10900&json=true","fetch_graph":"https://pith.science/api/pith-number/M5ORPBRQ7WIZZCQUSL7DHBC7NH/graph.json","fetch_events":"https://pith.science/api/pith-number/M5ORPBRQ7WIZZCQUSL7DHBC7NH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH/action/storage_attestation","attest_author":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH/action/author_attestation","sign_citation":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH/action/citation_signature","submit_replication":"https://pith.science/pith/M5ORPBRQ7WIZZCQUSL7DHBC7NH/action/replication_record"}},"created_at":"2026-07-05T04:06:58.643044+00:00","updated_at":"2026-07-05T04:06:58.643044+00:00"}