{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BYLEL2PFS4FCIS7MPZFQI6ZIDL","short_pith_number":"pith:BYLEL2PF","schema_version":"1.0","canonical_sha256":"0e1645e9e5970a244bec7e4b047b281aeadf4954b6ca655bbb608009b64086e4","source":{"kind":"arxiv","id":"2304.03464","version":3},"attestation_state":"computed","paper":{"title":"Linking Representations with Multimodal Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","econ.GN","q-fin.EC"],"primary_cat":"cs.CV","authors_text":"Abhishek Arora, Melissa Dell, Shao-Yu Jheng, Xinmei Yang","submitted_at":"2023-04-07T03:39:08Z","abstract_excerpt":"Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record linkage commonly approached using string matching techniques. Moreover, existing methods do not exploit the inherently multimodal nature of documents. In historical record linkage applications, documents are typically noisily transcribed by optical character recognition (OCR). Linkage with just OCR'ed texts may fail due to noise, whereas linkage with just image crops may also fail because vision models lack language"},"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":"2304.03464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T03:39:08Z","cross_cats_sorted":["cs.CL","econ.GN","q-fin.EC"],"title_canon_sha256":"15439857886860a78ec7852c7f2d1a833491adc8c4b8db02ab2a83ea322e943e","abstract_canon_sha256":"a755e783381c2850bd8b6aa04637ab6f8947d60d963c545b985579b09e790f7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:17.752469Z","signature_b64":"cB1UdcbrhdudFDHZcwBU8Z3BU6B4UBz+0W/NB3aDA5uX+Y9ao6U1xIdYJAboZMiRY1wEkc9MOP+HSRjZ1cgjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1645e9e5970a244bec7e4b047b281aeadf4954b6ca655bbb608009b64086e4","last_reissued_at":"2026-07-05T08:35:17.752030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:17.752030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linking Representations with Multimodal Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","econ.GN","q-fin.EC"],"primary_cat":"cs.CV","authors_text":"Abhishek Arora, Melissa Dell, Shao-Yu Jheng, Xinmei Yang","submitted_at":"2023-04-07T03:39:08Z","abstract_excerpt":"Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record linkage commonly approached using string matching techniques. Moreover, existing methods do not exploit the inherently multimodal nature of documents. In historical record linkage applications, documents are typically noisily transcribed by optical character recognition (OCR). Linkage with just OCR'ed texts may fail due to noise, whereas linkage with just image crops may also fail because vision models lack language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03464","kind":"arxiv","version":3},"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/2304.03464/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":"2304.03464","created_at":"2026-07-05T08:35:17.752091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03464v3","created_at":"2026-07-05T08:35:17.752091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03464","created_at":"2026-07-05T08:35:17.752091+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYLEL2PFS4FC","created_at":"2026-07-05T08:35:17.752091+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYLEL2PFS4FCIS7M","created_at":"2026-07-05T08:35:17.752091+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYLEL2PF","created_at":"2026-07-05T08:35:17.752091+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/BYLEL2PFS4FCIS7MPZFQI6ZIDL","json":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL.json","graph_json":"https://pith.science/api/pith-number/BYLEL2PFS4FCIS7MPZFQI6ZIDL/graph.json","events_json":"https://pith.science/api/pith-number/BYLEL2PFS4FCIS7MPZFQI6ZIDL/events.json","paper":"https://pith.science/paper/BYLEL2PF"},"agent_actions":{"view_html":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL","download_json":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL.json","view_paper":"https://pith.science/paper/BYLEL2PF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03464&json=true","fetch_graph":"https://pith.science/api/pith-number/BYLEL2PFS4FCIS7MPZFQI6ZIDL/graph.json","fetch_events":"https://pith.science/api/pith-number/BYLEL2PFS4FCIS7MPZFQI6ZIDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL/action/storage_attestation","attest_author":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL/action/author_attestation","sign_citation":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL/action/citation_signature","submit_replication":"https://pith.science/pith/BYLEL2PFS4FCIS7MPZFQI6ZIDL/action/replication_record"}},"created_at":"2026-07-05T08:35:17.752091+00:00","updated_at":"2026-07-05T08:35:17.752091+00:00"}