{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MQVBAXNNKIZ7I65EBVFWAD7VEW","short_pith_number":"pith:MQVBAXNN","schema_version":"1.0","canonical_sha256":"642a105dad5233f47ba40d4b600ff5258197ca4bb3bb1ba7d81e743ca2794fc1","source":{"kind":"arxiv","id":"2309.00789","version":2},"attestation_state":"computed","paper":{"title":"LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhishek Arora, Melissa Dell","submitted_at":"2023-09-02T01:45:27Z","abstract_excerpt":"Linking information across sources is fundamental to a variety of analyses in social science, business, and government. While large language models (LLMs) offer enormous promise for improving record linkage in noisy datasets, in many domains approximate string matching packages in popular softwares such as R and Stata remain predominant. These packages have clean, simple interfaces and can be easily extended to a diversity of languages. Our open-source package LinkTransformer aims to extend the familiarity and ease-of-use of popular string matching methods to deep learning. It is a general pur"},"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":"2309.00789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-02T01:45:27Z","cross_cats_sorted":[],"title_canon_sha256":"aa3be7c888cea2ed9e6928fcd93fe8b480a3dbec69540dcb5463d83f90acfcbc","abstract_canon_sha256":"e2380bf32075bae08cfa134ed212f6f24dcf0192cdf017633c28f95d2b190abf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:05.191588Z","signature_b64":"qb1GGpj8ZnuRtVV59+j2p29CzvYLFBoZZPd7M08skjl6VjMAC95Dw3czDasMNft+UnpRHqZCvIrvtCiuj87VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"642a105dad5233f47ba40d4b600ff5258197ca4bb3bb1ba7d81e743ca2794fc1","last_reissued_at":"2026-07-05T08:36:05.191087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:05.191087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhishek Arora, Melissa Dell","submitted_at":"2023-09-02T01:45:27Z","abstract_excerpt":"Linking information across sources is fundamental to a variety of analyses in social science, business, and government. While large language models (LLMs) offer enormous promise for improving record linkage in noisy datasets, in many domains approximate string matching packages in popular softwares such as R and Stata remain predominant. These packages have clean, simple interfaces and can be easily extended to a diversity of languages. Our open-source package LinkTransformer aims to extend the familiarity and ease-of-use of popular string matching methods to deep learning. It is a general pur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00789","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/2309.00789/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":"2309.00789","created_at":"2026-07-05T08:36:05.191148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00789v2","created_at":"2026-07-05T08:36:05.191148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00789","created_at":"2026-07-05T08:36:05.191148+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQVBAXNNKIZ7","created_at":"2026-07-05T08:36:05.191148+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQVBAXNNKIZ7I65E","created_at":"2026-07-05T08:36:05.191148+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQVBAXNN","created_at":"2026-07-05T08:36:05.191148+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/MQVBAXNNKIZ7I65EBVFWAD7VEW","json":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW.json","graph_json":"https://pith.science/api/pith-number/MQVBAXNNKIZ7I65EBVFWAD7VEW/graph.json","events_json":"https://pith.science/api/pith-number/MQVBAXNNKIZ7I65EBVFWAD7VEW/events.json","paper":"https://pith.science/paper/MQVBAXNN"},"agent_actions":{"view_html":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW","download_json":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW.json","view_paper":"https://pith.science/paper/MQVBAXNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00789&json=true","fetch_graph":"https://pith.science/api/pith-number/MQVBAXNNKIZ7I65EBVFWAD7VEW/graph.json","fetch_events":"https://pith.science/api/pith-number/MQVBAXNNKIZ7I65EBVFWAD7VEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW/action/storage_attestation","attest_author":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW/action/author_attestation","sign_citation":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW/action/citation_signature","submit_replication":"https://pith.science/pith/MQVBAXNNKIZ7I65EBVFWAD7VEW/action/replication_record"}},"created_at":"2026-07-05T08:36:05.191148+00:00","updated_at":"2026-07-05T08:36:05.191148+00:00"}