{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PXLGNDAIOUO7GY3FDEEIH4RZRJ","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":"d8ef6cbbe72a7a36ae007607af8df854bf9f6ef5e0851564d6b5852fbfcd11d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-17T20:45:03Z","title_canon_sha256":"1683a2fd38ea073e49a1e9679d2359ba736b0dd2e9bef830a1e27d289a64e7eb"},"schema_version":"1.0","source":{"id":"1802.06290","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06290","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06290v1","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06290","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"PXLGNDAIOUO7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PXLGNDAIOUO7GY3F","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PXLGNDAI","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:ac0b4bc80c99b4faef38dfc49bd1dd6faf50a058dc826f3551286fac912189cc","target":"graph","created_at":"2026-05-18T00:23:03Z","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":"There are hundreds of millions of tables in Web pages that contain useful information for many applications. Leveraging data within these tables is difficult because of the wide variety of structures, formats and data encoded in these tables. TabVec is an unsupervised method to embed tables into a vector space to support classification of tables into categories (entity, relational, matrix, list, and non-data) with minimal user intervention. TabVec deploys syntax and semantics of table cells, and embeds the structure of tables in a table vector space. This enables superior classification of tab","authors_text":"Majid Ghasemi-Gol, Pedro Szekely","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-17T20:45:03Z","title":"TabVec: Table Vectors for Classification of Web Tables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06290","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":"sha256:7cf51e385c65cce22bf5d0a3307a4712b2b4067d0d3c9a59c729dfc3ba50adcc","target":"record","created_at":"2026-05-18T00:23:03Z","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":"d8ef6cbbe72a7a36ae007607af8df854bf9f6ef5e0851564d6b5852fbfcd11d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-17T20:45:03Z","title_canon_sha256":"1683a2fd38ea073e49a1e9679d2359ba736b0dd2e9bef830a1e27d289a64e7eb"},"schema_version":"1.0","source":{"id":"1802.06290","kind":"arxiv","version":1}},"canonical_sha256":"7dd6668c08751df36365190883f2398a6255c209c10a5953d62349b75966b50d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dd6668c08751df36365190883f2398a6255c209c10a5953d62349b75966b50d","first_computed_at":"2026-05-18T00:23:03.769778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:03.769778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MoxyDIL52SRSdEl11VXg59SMWO58zjE8OCA9AA40tJ/w7yIC1yKVcAe8ebzD9we/FAl5q7zZ7MUcntHHwQSXBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:03.770482Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06290","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cf51e385c65cce22bf5d0a3307a4712b2b4067d0d3c9a59c729dfc3ba50adcc","sha256:ac0b4bc80c99b4faef38dfc49bd1dd6faf50a058dc826f3551286fac912189cc"],"state_sha256":"a33c85e2eb83133659151ce5c271ae58339d6ad949a81b1d8cc7527aa431b936"}