{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R5CRR3BTRYIGVXXDMHS6YKTZPZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a9c40329dcbcd15f91aa04dbb68946b4e35655adc2dbf6d8ea90420165f8c179","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-01T17:14:10Z","title_canon_sha256":"782f62e9a67d5412778cc522a346957aa4721263d2dcaec3897db371817a1a76"},"schema_version":"1.0","source":{"id":"2004.00584","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00584","created_at":"2026-07-05T01:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00584v3","created_at":"2026-07-05T01:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00584","created_at":"2026-07-05T01:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"R5CRR3BTRYIG","created_at":"2026-07-05T01:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"R5CRR3BTRYIGVXXD","created_at":"2026-07-05T01:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"R5CRR3BT","created_at":"2026-07-05T01:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:286e35874d23ee4978a2af530a33c5e28243611ffb639166044a6cb089bcdedd","target":"graph","created_at":"2026-07-05T01:32:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.00584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Ditto, a novel entity matching system based on pre-trained Transformer-based language models. We fine-tune and cast EM as a sequence-pair classification problem to leverage such models with a simple architecture. Our experiments show that a straightforward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets. We also developed three optimization techniques to further improve Ditto's match","authors_text":"AnHai Doan, Jinfeng Li, Wang-Chiew Tan, Yoshihiko Suhara, Yuliang Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-01T17:14:10Z","title":"Deep Entity Matching with Pre-Trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00584","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5659ef55e529caa23c52a4ab0a456d72c315e8b78a25f6b0a1076d8341c545b3","target":"record","created_at":"2026-07-05T01:32:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a9c40329dcbcd15f91aa04dbb68946b4e35655adc2dbf6d8ea90420165f8c179","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-01T17:14:10Z","title_canon_sha256":"782f62e9a67d5412778cc522a346957aa4721263d2dcaec3897db371817a1a76"},"schema_version":"1.0","source":{"id":"2004.00584","kind":"arxiv","version":3}},"canonical_sha256":"8f4518ec338e106adee361e5ec2a797e51c1469e5ea71e1843dc17f797573039","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f4518ec338e106adee361e5ec2a797e51c1469e5ea71e1843dc17f797573039","first_computed_at":"2026-07-05T01:32:43.768344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:32:43.768344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGRHEJkWKK4fNF5dQq/b7da9aRMIrQ7wN+ugSD7JVyuc4vVFtPzRlRtuC5YVl7/AQrnrg2BSCvbb8Pe+ReQiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:32:43.768819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.00584","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5659ef55e529caa23c52a4ab0a456d72c315e8b78a25f6b0a1076d8341c545b3","sha256:286e35874d23ee4978a2af530a33c5e28243611ffb639166044a6cb089bcdedd"],"state_sha256":"b9edf6204853bba73476f8a679256670286ef8d1a8d4682f8b391b70e95a0e42"}