{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LJ2XE2XVG4IY7S5B6444KAJPZT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5a0d87f51bcf48cdb1e4c06d293544ee6a2476137cbd3f1125b00310fa4613ec","cross_cats_sorted":["cs.CV","econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:25:33Z","title_canon_sha256":"c7c1492243bd3405800edb1fed65a5b2b6f2ea998d3feb15cb511cde6bd8dae0"},"schema_version":"1.0","source":{"id":"2305.14672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14672","created_at":"2026-07-05T06:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14672v1","created_at":"2026-07-05T06:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14672","created_at":"2026-07-05T06:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"LJ2XE2XVG4IY","created_at":"2026-07-05T06:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"LJ2XE2XVG4IY7S5B","created_at":"2026-07-05T06:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"LJ2XE2XV","created_at":"2026-07-05T06:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:b7fbac002a971317044881c77718beb6cc229b359fcba1b83916ceb1cf361fa0","target":"graph","created_at":"2026-07-05T06:13:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.14672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Record linkage is a bedrock of quantitative social science, as analyses often require linking data from multiple, noisy sources. Off-the-shelf string matching methods are widely used, as they are straightforward and cheap to implement and scale. Not all character substitutions are equally probable, and for some settings there are widely used handcrafted lists denoting which string substitutions are more likely, that improve the accuracy of string matching. However, such lists do not exist for many settings, skewing research with linked datasets towards a few high-resource contexts that are not","authors_text":"Abhishek Arora, Melissa Dell, Shao-Yu Jheng, Xinmei Yang","cross_cats":["cs.CV","econ.GN","q-fin.EC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:25:33Z","title":"Quantifying Character Similarity with Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14672","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:509ab99d5076a32b4435b60608e86eddd0b9370560e13d554df33ef716f93e25","target":"record","created_at":"2026-07-05T06:13:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5a0d87f51bcf48cdb1e4c06d293544ee6a2476137cbd3f1125b00310fa4613ec","cross_cats_sorted":["cs.CV","econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:25:33Z","title_canon_sha256":"c7c1492243bd3405800edb1fed65a5b2b6f2ea998d3feb15cb511cde6bd8dae0"},"schema_version":"1.0","source":{"id":"2305.14672","kind":"arxiv","version":1}},"canonical_sha256":"5a75726af537118fcba1f739c5012fccc6d06434bc2391f0ff7d6cf4371a8f68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a75726af537118fcba1f739c5012fccc6d06434bc2391f0ff7d6cf4371a8f68","first_computed_at":"2026-07-05T06:13:26.529399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:26.529399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qdwXUTBeFLlpvB3iGRN65ohBZ8DEzXLseBPBzDx2DmInI2CwOOvmu0ySlrZWujmsesqx22WEX/rZAFHwRudBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:26.529835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:509ab99d5076a32b4435b60608e86eddd0b9370560e13d554df33ef716f93e25","sha256:b7fbac002a971317044881c77718beb6cc229b359fcba1b83916ceb1cf361fa0"],"state_sha256":"f2a41324c009776a6ac76cae9ae2813bdf0f0e007bdac7612e5d882f89438cbb"}