{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XTSUBT2226BOGGGPOTVHCOK6JD","short_pith_number":"pith:XTSUBT22","schema_version":"1.0","canonical_sha256":"bce540cf5ad782e318cf74ea71395e48de2c311e8ce356d37e040b6587071a23","source":{"kind":"arxiv","id":"2607.24688","version":1},"attestation_state":"computed","paper":{"title":"Beyond Scale and Generation: Understanding Language Model-based Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Iacer Calixto, Paul Groth, Sebastian Schelter, Xue Li, Zeyu Zhang","submitted_at":"2026-07-27T17:29:18Z","abstract_excerpt":"Entity matching identifies records that refer to the same real-world entity. Language models can be adapted to this task through bi-encoder, cross-encoder, and generative matcher architectures. However, prior studies often conflate matcher architecture with differences in model backbone, model variant(reflecting different pretraining objectives), and model size, making it difficult to isolate the sources of performance gains. We address this issue through a controlled factorial study spanning three matcher architectures, three model variants and three model sizes from the Qwen3 family, and nin"},"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":"2607.24688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-27T17:29:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2e2e236266a1bb46fabca6c052bc5e2b0d24f379184e9ed4426f772b406e7e23","abstract_canon_sha256":"b49b5450c770e280b4892822c114b879f3208c38b7698d878b9723723c63b0ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:22.554272Z","signature_b64":"41nAJ50zr+R45SgHU4gjo6UsIHFQARXSbt03//Rz7+1kAK7f+DmE6zw0tqO2Ie5ItJcyNfKFzSzX8gru0UI1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce540cf5ad782e318cf74ea71395e48de2c311e8ce356d37e040b6587071a23","last_reissued_at":"2026-07-28T02:24:22.553534Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:22.553534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Scale and Generation: Understanding Language Model-based Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Iacer Calixto, Paul Groth, Sebastian Schelter, Xue Li, Zeyu Zhang","submitted_at":"2026-07-27T17:29:18Z","abstract_excerpt":"Entity matching identifies records that refer to the same real-world entity. Language models can be adapted to this task through bi-encoder, cross-encoder, and generative matcher architectures. However, prior studies often conflate matcher architecture with differences in model backbone, model variant(reflecting different pretraining objectives), and model size, making it difficult to isolate the sources of performance gains. We address this issue through a controlled factorial study spanning three matcher architectures, three model variants and three model sizes from the Qwen3 family, and nin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24688","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/2607.24688/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":"2607.24688","created_at":"2026-07-28T02:24:22.553929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24688v1","created_at":"2026-07-28T02:24:22.553929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24688","created_at":"2026-07-28T02:24:22.553929+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTSUBT2226BO","created_at":"2026-07-28T02:24:22.553929+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTSUBT2226BOGGGP","created_at":"2026-07-28T02:24:22.553929+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTSUBT22","created_at":"2026-07-28T02:24:22.553929+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/XTSUBT2226BOGGGPOTVHCOK6JD","json":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD.json","graph_json":"https://pith.science/api/pith-number/XTSUBT2226BOGGGPOTVHCOK6JD/graph.json","events_json":"https://pith.science/api/pith-number/XTSUBT2226BOGGGPOTVHCOK6JD/events.json","paper":"https://pith.science/paper/XTSUBT22"},"agent_actions":{"view_html":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD","download_json":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD.json","view_paper":"https://pith.science/paper/XTSUBT22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24688&json=true","fetch_graph":"https://pith.science/api/pith-number/XTSUBT2226BOGGGPOTVHCOK6JD/graph.json","fetch_events":"https://pith.science/api/pith-number/XTSUBT2226BOGGGPOTVHCOK6JD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD/action/storage_attestation","attest_author":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD/action/author_attestation","sign_citation":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD/action/citation_signature","submit_replication":"https://pith.science/pith/XTSUBT2226BOGGGPOTVHCOK6JD/action/replication_record"}},"created_at":"2026-07-28T02:24:22.553929+00:00","updated_at":"2026-07-28T02:24:22.553929+00:00"}