{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DX555K7346TYG6CBZLT54WB23X","short_pith_number":"pith:DX555K73","schema_version":"1.0","canonical_sha256":"1dfbdeabfbe7a7837841cae7de583addf2dc173f71481052fca09fa3ee16fb63","source":{"kind":"arxiv","id":"2412.13503","version":2},"attestation_state":"computed","paper":{"title":"VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khai Phan Tran, Wen Hua, Xue Li","submitted_at":"2024-12-18T04:55:29Z","abstract_excerpt":"Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel data augmentation approach using generative models to enhance data from the embedding space. Our method leverages the Variational Autoencoder (VAE) architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. To better "},"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":"2412.13503","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T04:55:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30442e3daf23e54c59b060b3ac904859260094ca192fcc8ea7684da397375af3","abstract_canon_sha256":"5f1476bfbf3caed3f1276ad255ecd43fdd7a4736c786cb76a11ec0cfca29b8bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:57.338082Z","signature_b64":"vwgzadvNatPt2gFmtlVofnNkLHo5ACByv4k0drB+127Jn9T6qtyRJR1+trxYxueFx5a+4agxYvVyqMI+9taEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dfbdeabfbe7a7837841cae7de583addf2dc173f71481052fca09fa3ee16fb63","last_reissued_at":"2026-07-05T09:59:57.337542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:57.337542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khai Phan Tran, Wen Hua, Xue Li","submitted_at":"2024-12-18T04:55:29Z","abstract_excerpt":"Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel data augmentation approach using generative models to enhance data from the embedding space. Our method leverages the Variational Autoencoder (VAE) architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. To better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13503","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/2412.13503/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":"2412.13503","created_at":"2026-07-05T09:59:57.337602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13503v2","created_at":"2026-07-05T09:59:57.337602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13503","created_at":"2026-07-05T09:59:57.337602+00:00"},{"alias_kind":"pith_short_12","alias_value":"DX555K7346TY","created_at":"2026-07-05T09:59:57.337602+00:00"},{"alias_kind":"pith_short_16","alias_value":"DX555K7346TYG6CB","created_at":"2026-07-05T09:59:57.337602+00:00"},{"alias_kind":"pith_short_8","alias_value":"DX555K73","created_at":"2026-07-05T09:59:57.337602+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/DX555K7346TYG6CBZLT54WB23X","json":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X.json","graph_json":"https://pith.science/api/pith-number/DX555K7346TYG6CBZLT54WB23X/graph.json","events_json":"https://pith.science/api/pith-number/DX555K7346TYG6CBZLT54WB23X/events.json","paper":"https://pith.science/paper/DX555K73"},"agent_actions":{"view_html":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X","download_json":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X.json","view_paper":"https://pith.science/paper/DX555K73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13503&json=true","fetch_graph":"https://pith.science/api/pith-number/DX555K7346TYG6CBZLT54WB23X/graph.json","fetch_events":"https://pith.science/api/pith-number/DX555K7346TYG6CBZLT54WB23X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X/action/storage_attestation","attest_author":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X/action/author_attestation","sign_citation":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X/action/citation_signature","submit_replication":"https://pith.science/pith/DX555K7346TYG6CBZLT54WB23X/action/replication_record"}},"created_at":"2026-07-05T09:59:57.337602+00:00","updated_at":"2026-07-05T09:59:57.337602+00:00"}