{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKJIP2OF3XKSC7IFILZ3WRZOWO","short_pith_number":"pith:QKJIP2OF","schema_version":"1.0","canonical_sha256":"829287e9c5ddd5217d0542f3bb472eb3928d3dd1a2c14cc18e2865515626a076","source":{"kind":"arxiv","id":"2409.04073","version":2},"attestation_state":"computed","paper":{"title":"AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Paul Groth, Sebastian Schelter, Zeyu Zhang","submitted_at":"2024-09-06T07:29:01Z","abstract_excerpt":"Entity matching (EM) is the problem of determining whether two records refer to same real-world entity, which is crucial in data integration, e.g., for product catalogs or address databases. A major drawback of many EM approaches is their dependence on labelled examples. We thus focus on the challenging setting of zero-shot entity matching where no labelled examples are available for an unseen target dataset. Recently, large language models (LLMs) have shown promising results for zero-shot EM, but their low throughput and high deployment cost limit their applicability and scalability.\n  We rev"},"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":"2409.04073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T07:29:01Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"33a2993a0da0745d9010861a58b6f754f8e3b381b36213536c583db235b31b34","abstract_canon_sha256":"4757b0cb556e743ccfc8a057e273e3dd54be15c05bc9f5a332f0a06b68bdd356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:41.278397Z","signature_b64":"GZobr26yd+Chu1mgzxk10AMB9j9asoihZ6lGWnr5UquTUsC3Df8GfIeTDjZMVYT47dd/KrLHYtFMuLjbRoIWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"829287e9c5ddd5217d0542f3bb472eb3928d3dd1a2c14cc18e2865515626a076","last_reissued_at":"2026-07-05T09:04:41.277971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:41.277971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Paul Groth, Sebastian Schelter, Zeyu Zhang","submitted_at":"2024-09-06T07:29:01Z","abstract_excerpt":"Entity matching (EM) is the problem of determining whether two records refer to same real-world entity, which is crucial in data integration, e.g., for product catalogs or address databases. A major drawback of many EM approaches is their dependence on labelled examples. We thus focus on the challenging setting of zero-shot entity matching where no labelled examples are available for an unseen target dataset. Recently, large language models (LLMs) have shown promising results for zero-shot EM, but their low throughput and high deployment cost limit their applicability and scalability.\n  We rev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04073","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/2409.04073/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":"2409.04073","created_at":"2026-07-05T09:04:41.278024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04073v2","created_at":"2026-07-05T09:04:41.278024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04073","created_at":"2026-07-05T09:04:41.278024+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKJIP2OF3XKS","created_at":"2026-07-05T09:04:41.278024+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKJIP2OF3XKSC7IF","created_at":"2026-07-05T09:04:41.278024+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKJIP2OF","created_at":"2026-07-05T09:04:41.278024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11086","citing_title":"Beyond Traditional Algorithms: Leveraging LLMs for Accurate Cross-Border Entity Identification","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO","json":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO.json","graph_json":"https://pith.science/api/pith-number/QKJIP2OF3XKSC7IFILZ3WRZOWO/graph.json","events_json":"https://pith.science/api/pith-number/QKJIP2OF3XKSC7IFILZ3WRZOWO/events.json","paper":"https://pith.science/paper/QKJIP2OF"},"agent_actions":{"view_html":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO","download_json":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO.json","view_paper":"https://pith.science/paper/QKJIP2OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04073&json=true","fetch_graph":"https://pith.science/api/pith-number/QKJIP2OF3XKSC7IFILZ3WRZOWO/graph.json","fetch_events":"https://pith.science/api/pith-number/QKJIP2OF3XKSC7IFILZ3WRZOWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO/action/storage_attestation","attest_author":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO/action/author_attestation","sign_citation":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO/action/citation_signature","submit_replication":"https://pith.science/pith/QKJIP2OF3XKSC7IFILZ3WRZOWO/action/replication_record"}},"created_at":"2026-07-05T09:04:41.278024+00:00","updated_at":"2026-07-05T09:04:41.278024+00:00"}