{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EUB5U2N7WFK5CSSRPYJVLOFPFN","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":"0405f4859e847d0711b797a5eb25f6ee140c2c6011da626b18121e60d8fb309d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-09-03T12:45:02Z","title_canon_sha256":"7b19159513610cbd54fcba46597f6f6510a592243d45e8196d90f4d342c71a86"},"schema_version":"1.0","source":{"id":"1909.01120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01120","created_at":"2026-07-05T01:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01120v2","created_at":"2026-07-05T01:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01120","created_at":"2026-07-05T01:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"EUB5U2N7WFK5","created_at":"2026-07-05T01:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"EUB5U2N7WFK5CSSR","created_at":"2026-07-05T01:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"EUB5U2N7","created_at":"2026-07-05T01:32:41Z"}],"graph_snapshots":[{"event_id":"sha256:7e06942053d6fb5ac21ad2ac7ed6d9d348bd0ea24b9ca75feb78c9055e490276","target":"graph","created_at":"2026-07-05T01:32:41Z","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/1909.01120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning based techniques have been recently used with promising results for data integration problems. Some methods directly use pre-trained embeddings that were trained on a large corpus such as Wikipedia. However, they may not always be an appropriate choice for enterprise datasets with custom vocabulary. Other methods adapt techniques from natural language processing to obtain embeddings for the enterprise's relational data. However, this approach blindly treats a tuple as a sentence, thus losing a large amount of contextual information present in the tuple.\n  We propose algorithms fo","authors_text":"Paolo Papotti, Riccardo Cappuzzo, Saravanan Thirumuruganathan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-09-03T12:45:02Z","title":"Local Embeddings for Relational Data Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01120","kind":"arxiv","version":2},"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:ff3ced72f4d23829d6cab2568c01dda78ade8a0d75c7182538f5cf00cf91f5a2","target":"record","created_at":"2026-07-05T01:32:41Z","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":"0405f4859e847d0711b797a5eb25f6ee140c2c6011da626b18121e60d8fb309d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-09-03T12:45:02Z","title_canon_sha256":"7b19159513610cbd54fcba46597f6f6510a592243d45e8196d90f4d342c71a86"},"schema_version":"1.0","source":{"id":"1909.01120","kind":"arxiv","version":2}},"canonical_sha256":"2503da69bfb155d14a517e1355b8af2b537d3f390150073f4e8e51c037cdcfb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2503da69bfb155d14a517e1355b8af2b537d3f390150073f4e8e51c037cdcfb7","first_computed_at":"2026-07-05T01:32:41.683095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:32:41.683095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48IZb1VfchRNgR0hEM5DBvC56u1rtFnvYstlqlwdqKqqnfLc0fCVF42j45rud2H/CID9qmEl0khsKF32aBpzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:32:41.683491Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff3ced72f4d23829d6cab2568c01dda78ade8a0d75c7182538f5cf00cf91f5a2","sha256:7e06942053d6fb5ac21ad2ac7ed6d9d348bd0ea24b9ca75feb78c9055e490276"],"state_sha256":"d5dc35d55abda7a661cad63feaade5f2441924486183630a6c07212aa5df571c"}