{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:A2HEXN3QEIV2P5D23LUZ2JTZZG","short_pith_number":"pith:A2HEXN3Q","canonical_record":{"source":{"id":"1911.06311","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-14T18:51:59Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a46e8272f3be3481560dfc4a876251922923ae469c1eb3492b92ebd00ad75c37","abstract_canon_sha256":"fe17c6cfbe88c534dfe3d27d573389c006c96f9a8f784c95b2b6d0c7d5684914"},"schema_version":"1.0"},"canonical_sha256":"068e4bb770222ba7f47adae99d2679c9be1c396b88f4653ff8b70c0e195147c1","source":{"kind":"arxiv","id":"1911.06311","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06311","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06311v3","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06311","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"A2HEXN3QEIV2","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"A2HEXN3QEIV2P5D2","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"A2HEXN3Q","created_at":"2026-07-05T01:07:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:A2HEXN3QEIV2P5D23LUZ2JTZZG","target":"record","payload":{"canonical_record":{"source":{"id":"1911.06311","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-14T18:51:59Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a46e8272f3be3481560dfc4a876251922923ae469c1eb3492b92ebd00ad75c37","abstract_canon_sha256":"fe17c6cfbe88c534dfe3d27d573389c006c96f9a8f784c95b2b6d0c7d5684914"},"schema_version":"1.0"},"canonical_sha256":"068e4bb770222ba7f47adae99d2679c9be1c396b88f4653ff8b70c0e195147c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:38.311124Z","signature_b64":"vxAH71RgE6tL/IRyxJ8kURiR1hp4/o/b7PpPkgcFETmyzx4WATamE3fRVS92Kem/KkPENhrw/Jo2qlxK3bSDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"068e4bb770222ba7f47adae99d2679c9be1c396b88f4653ff8b70c0e195147c1","last_reissued_at":"2026-07-05T01:07:38.310622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:38.310622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.06311","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9KmDRPslKPvQVB1cQPttWYumyv/jShH8N/MSHl2xlHXPZ1DyqPw5zgR2eUelSInkcibiKRb2+9aTi1gzWOBkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T02:51:49.162062Z"},"content_sha256":"2c57d00e06d0599c535ce76bd305cb82689ed2fa51b15341b10d4b60b2573248","schema_version":"1.0","event_id":"sha256:2c57d00e06d0599c535ce76bd305cb82689ed2fa51b15341b10d4b60b2573248"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:A2HEXN3QEIV2P5D23LUZ2JTZZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sato: Contextual Semantic Type Detection in Tables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"\\c{C}a\\u{g}atay Demiralp, Dan Zhang, Jinfeng Li, Madelon Hulsebos, Wang-Chiew Tan, Yoshihiko Suhara","submitted_at":"2019-11-14T18:51:59Z","abstract_excerpt":"Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search. However, existing detection approaches either perform poorly with dirty data, support only a limited number of semantic types, fail to incorporate the table context of columns or rely on large sample sizes for training data. We introduce Sato, a hybrid machine learning model to automatically detect the semantic types of columns in tables, exploiting the signals from the context as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06311","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.06311/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtu+FcfJzK4wNz8FAMzD1ljYKqYXO2xxeLfXaoyNgutt3FohcnD2JYgqt7N16YL96neI+7Cv0/s/gq1Y9yjjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T02:51:49.162460Z"},"content_sha256":"1fb1b3d33e369a21961e9210412315dfb7318a2c4856d04701b9ebe19d990db2","schema_version":"1.0","event_id":"sha256:1fb1b3d33e369a21961e9210412315dfb7318a2c4856d04701b9ebe19d990db2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG/bundle.json","state_url":"https://pith.science/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T02:51:49Z","links":{"resolver":"https://pith.science/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG","bundle":"https://pith.science/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG/bundle.json","state":"https://pith.science/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2HEXN3QEIV2P5D23LUZ2JTZZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:A2HEXN3QEIV2P5D23LUZ2JTZZG","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":"fe17c6cfbe88c534dfe3d27d573389c006c96f9a8f784c95b2b6d0c7d5684914","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-14T18:51:59Z","title_canon_sha256":"a46e8272f3be3481560dfc4a876251922923ae469c1eb3492b92ebd00ad75c37"},"schema_version":"1.0","source":{"id":"1911.06311","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06311","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06311v3","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06311","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"A2HEXN3QEIV2","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"A2HEXN3QEIV2P5D2","created_at":"2026-07-05T01:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"A2HEXN3Q","created_at":"2026-07-05T01:07:38Z"}],"graph_snapshots":[{"event_id":"sha256:1fb1b3d33e369a21961e9210412315dfb7318a2c4856d04701b9ebe19d990db2","target":"graph","created_at":"2026-07-05T01:07:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.06311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search. However, existing detection approaches either perform poorly with dirty data, support only a limited number of semantic types, fail to incorporate the table context of columns or rely on large sample sizes for training data. We introduce Sato, a hybrid machine learning model to automatically detect the semantic types of columns in tables, exploiting the signals from the context as","authors_text":"\\c{C}a\\u{g}atay Demiralp, Dan Zhang, Jinfeng Li, Madelon Hulsebos, Wang-Chiew Tan, Yoshihiko Suhara","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-14T18:51:59Z","title":"Sato: Contextual Semantic Type Detection in Tables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06311","kind":"arxiv","version":3},"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":"sha256:2c57d00e06d0599c535ce76bd305cb82689ed2fa51b15341b10d4b60b2573248","target":"record","created_at":"2026-07-05T01:07:38Z","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":"fe17c6cfbe88c534dfe3d27d573389c006c96f9a8f784c95b2b6d0c7d5684914","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-14T18:51:59Z","title_canon_sha256":"a46e8272f3be3481560dfc4a876251922923ae469c1eb3492b92ebd00ad75c37"},"schema_version":"1.0","source":{"id":"1911.06311","kind":"arxiv","version":3}},"canonical_sha256":"068e4bb770222ba7f47adae99d2679c9be1c396b88f4653ff8b70c0e195147c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"068e4bb770222ba7f47adae99d2679c9be1c396b88f4653ff8b70c0e195147c1","first_computed_at":"2026-07-05T01:07:38.310622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:38.310622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vxAH71RgE6tL/IRyxJ8kURiR1hp4/o/b7PpPkgcFETmyzx4WATamE3fRVS92Kem/KkPENhrw/Jo2qlxK3bSDDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:38.311124Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.06311","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c57d00e06d0599c535ce76bd305cb82689ed2fa51b15341b10d4b60b2573248","sha256:1fb1b3d33e369a21961e9210412315dfb7318a2c4856d04701b9ebe19d990db2"],"state_sha256":"d992c2d19bc2d4999c335de4186ba51ade9a41b33a1148c6099405005e0bbd2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bO4ZfLu4vxSICsYw981kROJdv3Xuqe6Dvp++BUYJpra7n5Hx/V6Ay/8/wmwMh1qdgRRmVMLHeuyg6lGT+pwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T02:51:49.164950Z","bundle_sha256":"26af6727e8bf8a9a72d7dd8734d7fa649323429cfde0b29a64e26a3b3dc95e6c"}}