{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PWFA3BUFWZE35PSE6PLB3PUXFR","short_pith_number":"pith:PWFA3BUF","schema_version":"1.0","canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","source":{"kind":"arxiv","id":"2106.04174","version":1},"attestation_state":"computed","paper":{"title":"Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengjiang Li, Jifan Yu, Juanzi Li, Lei Hou, Tiansi Dong, Xin Lv, Yichi Zhang, Zelin Dai, Zijun Yao","submitted_at":"2021-06-08T08:27:31Z","abstract_excerpt":"Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embedding"},"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":"2106.04174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T08:27:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e36918c90c337e6387b6d1b70912e91779abfaee5b6048c79a3ba5c33888f7b6","abstract_canon_sha256":"90f114e370b9e1c851589827559273001a2d515b77f45f2010591a2fb07744e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:12.908230Z","signature_b64":"vD1V4RXfBC5D3cZNQ7Cf0lV/SZFu1AD7TQKpGs054/jMuUkQKzrADZ1QRBaEDc1QuK1XPNuTzPiBrAW3skObDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","last_reissued_at":"2026-07-05T02:47:12.907703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:12.907703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengjiang Li, Jifan Yu, Juanzi Li, Lei Hou, Tiansi Dong, Xin Lv, Yichi Zhang, Zelin Dai, Zijun Yao","submitted_at":"2021-06-08T08:27:31Z","abstract_excerpt":"Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embedding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04174","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/2106.04174/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":"2106.04174","created_at":"2026-07-05T02:47:12.907765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04174v1","created_at":"2026-07-05T02:47:12.907765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04174","created_at":"2026-07-05T02:47:12.907765+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWFA3BUFWZE3","created_at":"2026-07-05T02:47:12.907765+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWFA3BUFWZE35PSE","created_at":"2026-07-05T02:47:12.907765+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWFA3BUF","created_at":"2026-07-05T02:47:12.907765+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/PWFA3BUFWZE35PSE6PLB3PUXFR","json":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR.json","graph_json":"https://pith.science/api/pith-number/PWFA3BUFWZE35PSE6PLB3PUXFR/graph.json","events_json":"https://pith.science/api/pith-number/PWFA3BUFWZE35PSE6PLB3PUXFR/events.json","paper":"https://pith.science/paper/PWFA3BUF"},"agent_actions":{"view_html":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR","download_json":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR.json","view_paper":"https://pith.science/paper/PWFA3BUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04174&json=true","fetch_graph":"https://pith.science/api/pith-number/PWFA3BUFWZE35PSE6PLB3PUXFR/graph.json","fetch_events":"https://pith.science/api/pith-number/PWFA3BUFWZE35PSE6PLB3PUXFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/action/storage_attestation","attest_author":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/action/author_attestation","sign_citation":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/action/citation_signature","submit_replication":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/action/replication_record"}},"created_at":"2026-07-05T02:47:12.907765+00:00","updated_at":"2026-07-05T02:47:12.907765+00:00"}