{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y6UL35FGP7XJ4KY4EUG4CZMPMD","short_pith_number":"pith:Y6UL35FG","schema_version":"1.0","canonical_sha256":"c7a8bdf4a67fee9e2b1c250dc1658f60d7136b1b33c8dc49cac57bde30d7cbcb","source":{"kind":"arxiv","id":"2606.27342","version":1},"attestation_state":"computed","paper":{"title":"Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Gregory Goren, Nicholas Pulsone, Roee Shraga","submitted_at":"2026-06-25T17:49:48Z","abstract_excerpt":"Entity Matching (EM) is a core operation in the data integration pipeline, where records from different sources are compared to determine whether they refer to the same real-world entity. Recent work has incorporated domain information and low-resource learning techniques to better adapt EM systems to realistic settings. While these approaches have demonstrated strong performance, it remains unclear how they behave under varying data constraints and levels of supervision in practice. In this paper, we investigate a state-of-the-art method for low-resource, domain-aware EM--BEACON--and study ho"},"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":"2606.27342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-25T17:49:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1ce05dabe54ceb8a69dc8bf754e5fd8c50d1a93c1da66914723f815017aa1c9c","abstract_canon_sha256":"3e3c07ac39ddb8f611722b9204fde26e24dd8aac905f20d37ac8ac22c9dceb05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:19.260853Z","signature_b64":"qa5lPUjPfOiTS8GbtnEyjb+Sv7BkDcXNjRo4KzXjYM6GA9wYtcOSOZ1pCsn0JsGBaCRHxhIj3AJATX2bHyGeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a8bdf4a67fee9e2b1c250dc1658f60d7136b1b33c8dc49cac57bde30d7cbcb","last_reissued_at":"2026-06-26T01:16:19.260407Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:19.260407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Gregory Goren, Nicholas Pulsone, Roee Shraga","submitted_at":"2026-06-25T17:49:48Z","abstract_excerpt":"Entity Matching (EM) is a core operation in the data integration pipeline, where records from different sources are compared to determine whether they refer to the same real-world entity. Recent work has incorporated domain information and low-resource learning techniques to better adapt EM systems to realistic settings. While these approaches have demonstrated strong performance, it remains unclear how they behave under varying data constraints and levels of supervision in practice. In this paper, we investigate a state-of-the-art method for low-resource, domain-aware EM--BEACON--and study ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27342","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/2606.27342/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":"2606.27342","created_at":"2026-06-26T01:16:19.260470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27342v1","created_at":"2026-06-26T01:16:19.260470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27342","created_at":"2026-06-26T01:16:19.260470+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6UL35FGP7XJ","created_at":"2026-06-26T01:16:19.260470+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6UL35FGP7XJ4KY4","created_at":"2026-06-26T01:16:19.260470+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6UL35FG","created_at":"2026-06-26T01:16:19.260470+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/Y6UL35FGP7XJ4KY4EUG4CZMPMD","json":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD.json","graph_json":"https://pith.science/api/pith-number/Y6UL35FGP7XJ4KY4EUG4CZMPMD/graph.json","events_json":"https://pith.science/api/pith-number/Y6UL35FGP7XJ4KY4EUG4CZMPMD/events.json","paper":"https://pith.science/paper/Y6UL35FG"},"agent_actions":{"view_html":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD","download_json":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD.json","view_paper":"https://pith.science/paper/Y6UL35FG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27342&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6UL35FGP7XJ4KY4EUG4CZMPMD/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6UL35FGP7XJ4KY4EUG4CZMPMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD/action/storage_attestation","attest_author":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD/action/author_attestation","sign_citation":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD/action/citation_signature","submit_replication":"https://pith.science/pith/Y6UL35FGP7XJ4KY4EUG4CZMPMD/action/replication_record"}},"created_at":"2026-06-26T01:16:19.260470+00:00","updated_at":"2026-06-26T01:16:19.260470+00:00"}