{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W2JWA2QIJKHKPXSPLRR3GFAEQC","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":"34cb5153d4009ed7c101f7c88cc1dad223951731f9b06e32a501b1024bb3a9b7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T08:45:56Z","title_canon_sha256":"1013f82d347ad36e8711fee9e195d918f7326826e876f62c3048911c65cb1010"},"schema_version":"1.0","source":{"id":"2106.09493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09493","created_at":"2026-07-05T02:50:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09493v1","created_at":"2026-07-05T02:50:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09493","created_at":"2026-07-05T02:50:16Z"},{"alias_kind":"pith_short_12","alias_value":"W2JWA2QIJKHK","created_at":"2026-07-05T02:50:16Z"},{"alias_kind":"pith_short_16","alias_value":"W2JWA2QIJKHKPXSP","created_at":"2026-07-05T02:50:16Z"},{"alias_kind":"pith_short_8","alias_value":"W2JWA2QI","created_at":"2026-07-05T02:50:16Z"}],"graph_snapshots":[{"event_id":"sha256:693a3fb8b75ee2d85aa6f52c413925ba4cb8ab2fe47730ed2a24ab9cf6dc706a","target":"graph","created_at":"2026-07-05T02:50:16Z","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/2106.09493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present SANTA, a scalable framework to automatically normalize E-commerce attribute values (e.g. \"Win 10 Pro\") to a fixed set of pre-defined canonical values (e.g. \"Windows 10\"). Earlier works on attribute normalization focused on fuzzy string matching (also referred as syntactic matching in this paper). In this work, we first perform an extensive study of nine syntactic matching algorithms and establish that 'cosine' similarity leads to best results, showing 2.7% improvement over commonly used Jaccard index. Next, we argue that string similarity alone is not sufficient for a","authors_text":"Kartik Mehta, Nikhil Rasiwasia, Ravi Shankar Mishra","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T08:45:56Z","title":"Scalable Approach for Normalizing E-commerce Text Attributes (SANTA)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09493","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":"sha256:7626a96099c2dcf9ccbbe41d8f1dd63d1da5f16d5a07043b5a3df5e6a89a99b0","target":"record","created_at":"2026-07-05T02:50:16Z","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":"34cb5153d4009ed7c101f7c88cc1dad223951731f9b06e32a501b1024bb3a9b7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-12T08:45:56Z","title_canon_sha256":"1013f82d347ad36e8711fee9e195d918f7326826e876f62c3048911c65cb1010"},"schema_version":"1.0","source":{"id":"2106.09493","kind":"arxiv","version":1}},"canonical_sha256":"b693606a084a8ea7de4f5c63b314048097239fd4033ed234981087a23d5a7fa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b693606a084a8ea7de4f5c63b314048097239fd4033ed234981087a23d5a7fa2","first_computed_at":"2026-07-05T02:50:16.775348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:16.775348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nEuO8WhQt+fJraef0TGre1+m5BmGnm1ieQYMlE7VnLzT8/FHRVBmt/ufgatvjduwPaSAzZpZQW4/0BaBUF34Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:16.775769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7626a96099c2dcf9ccbbe41d8f1dd63d1da5f16d5a07043b5a3df5e6a89a99b0","sha256:693a3fb8b75ee2d85aa6f52c413925ba4cb8ab2fe47730ed2a24ab9cf6dc706a"],"state_sha256":"4566a3464e0eba269c8d417c8da326489778a930cc668c05b25ece049acccd84"}