{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QE7HHVUBO367CBTSYCMKM2MWG4","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":"50536bee5804063cf1b3f8650579c614ba185a4741b399b3dbcac9ce5eec5615","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-23T22:41:22Z","title_canon_sha256":"b64431ac5ced74de150ab17a1c9347acdb645702913ef5d181c42f237e46ac67"},"schema_version":"1.0","source":{"id":"1907.10165","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10165","created_at":"2026-05-17T23:39:38Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10165v1","created_at":"2026-05-17T23:39:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10165","created_at":"2026-05-17T23:39:38Z"},{"alias_kind":"pith_short_12","alias_value":"QE7HHVUBO367","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QE7HHVUBO367CBTS","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QE7HHVUB","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:3440892f2c0f1159ec2335f4b990a1b698a0657f639632f47d95c6ab437500f4","target":"graph","created_at":"2026-05-17T23:39:38Z","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"},"paper":{"abstract_excerpt":"String similarity models are vital for record linkage, entity resolution, and search. In this work, we present STANCE --a learned model for computing the similarity of two strings. Our approach encodes the  characters of each string, aligns the encodings using Sinkhorn Iteration (alignment is posed as an instance of optimal transport) and scores the alignment with a convolutional neural network. We evaluate STANCE's ability to detect whether two strings can refer to the same entity--a task we term alias detection. We construct five new alias detection datasets (and make them publicly available","authors_text":"Aaron Traylor, Andrew McCallum, Ari Kobren, Derek Tam, Nicholas Monath, Rajarshi Das","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-23T22:41:22Z","title":"Optimal Transport-based Alignment of Learned Character Representations for String Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10165","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":"sha256:3b269d7ae2d62c6823fcedf36971c06ca8ce43648cb9131d2878e699a1770908","target":"record","created_at":"2026-05-17T23:39:38Z","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":"50536bee5804063cf1b3f8650579c614ba185a4741b399b3dbcac9ce5eec5615","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-23T22:41:22Z","title_canon_sha256":"b64431ac5ced74de150ab17a1c9347acdb645702913ef5d181c42f237e46ac67"},"schema_version":"1.0","source":{"id":"1907.10165","kind":"arxiv","version":1}},"canonical_sha256":"813e73d68176fdf10672c098a66996371ebf382a371d4b0c90754bcf90420a86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813e73d68176fdf10672c098a66996371ebf382a371d4b0c90754bcf90420a86","first_computed_at":"2026-05-17T23:39:38.832537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:38.832537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K8MOElFh64OXblC2CwblVYNPnr1x6U6i7ExFva+obo842AsK+kre6LwNyamYPs1ZRX9NtOt36QWT4Jg96RHZDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:38.833202Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10165","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b269d7ae2d62c6823fcedf36971c06ca8ce43648cb9131d2878e699a1770908","sha256:3440892f2c0f1159ec2335f4b990a1b698a0657f639632f47d95c6ab437500f4"],"state_sha256":"04fde10245fceb4f9287815a4e39cd94d58e9f4b7cde9dc25b24aa14de6ba682"}