{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E2BHMOXG6MTM7OHVB6G726RUHZ","short_pith_number":"pith:E2BHMOXG","schema_version":"1.0","canonical_sha256":"2682763ae6f326cfb8f50f8dfd7a343e6a77654beb396366203306658beccd9d","source":{"kind":"arxiv","id":"2210.01922","version":2},"attestation_state":"computed","paper":{"title":"Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dan Zhang, Grace Fan, Jin Wang, Ren\\'ee Miller, Yuliang Li","submitted_at":"2022-10-04T21:44:57Z","abstract_excerpt":"Dataset discovery from data lakes is essential in many real application scenarios. In this paper, we propose Starmie, an end-to-end framework for dataset discovery from data lakes (with table union search as the main use case). Our proposed framework features a contrastive learning method to train column encoders from pre-trained language models in a fully unsupervised manner. The column encoder of Starmie captures the rich contextual semantic information within tables by leveraging a contrastive multi-column pre-training strategy. We utilize the cosine similarity between column embedding vect"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.01922","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-10-04T21:44:57Z","cross_cats_sorted":[],"title_canon_sha256":"5c271b3a3848bdb8721a59bbe0bed2f5e7998250604ecf4f426f760f874d0695","abstract_canon_sha256":"35d9f70c53aa027249452541a7c3d620d0943af1d791fa06e1b92f0f1581ee43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:18.899871Z","signature_b64":"4jaT5WJRV7yEQVMEzR2Gn31RREkviQCtfXKccquTvuIq7k/dOrcpir3hBv95Yo3e5hwNmanNF15802o0u5hOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2682763ae6f326cfb8f50f8dfd7a343e6a77654beb396366203306658beccd9d","last_reissued_at":"2026-07-05T05:33:18.899417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:18.899417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dan Zhang, Grace Fan, Jin Wang, Ren\\'ee Miller, Yuliang Li","submitted_at":"2022-10-04T21:44:57Z","abstract_excerpt":"Dataset discovery from data lakes is essential in many real application scenarios. In this paper, we propose Starmie, an end-to-end framework for dataset discovery from data lakes (with table union search as the main use case). Our proposed framework features a contrastive learning method to train column encoders from pre-trained language models in a fully unsupervised manner. The column encoder of Starmie captures the rich contextual semantic information within tables by leveraging a contrastive multi-column pre-training strategy. We utilize the cosine similarity between column embedding vect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01922","kind":"arxiv","version":2},"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/2210.01922/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.01922","created_at":"2026-07-05T05:33:18.899475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01922v2","created_at":"2026-07-05T05:33:18.899475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01922","created_at":"2026-07-05T05:33:18.899475+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2BHMOXG6MTM","created_at":"2026-07-05T05:33:18.899475+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2BHMOXG6MTM7OHV","created_at":"2026-07-05T05:33:18.899475+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2BHMOXG","created_at":"2026-07-05T05:33:18.899475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18971","citing_title":"Rethinking Dataset Discovery with DataScout","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ","json":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ.json","graph_json":"https://pith.science/api/pith-number/E2BHMOXG6MTM7OHVB6G726RUHZ/graph.json","events_json":"https://pith.science/api/pith-number/E2BHMOXG6MTM7OHVB6G726RUHZ/events.json","paper":"https://pith.science/paper/E2BHMOXG"},"agent_actions":{"view_html":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ","download_json":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ.json","view_paper":"https://pith.science/paper/E2BHMOXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01922&json=true","fetch_graph":"https://pith.science/api/pith-number/E2BHMOXG6MTM7OHVB6G726RUHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/E2BHMOXG6MTM7OHVB6G726RUHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/action/storage_attestation","attest_author":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/action/author_attestation","sign_citation":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/action/citation_signature","submit_replication":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/action/replication_record"}},"created_at":"2026-07-05T05:33:18.899475+00:00","updated_at":"2026-07-05T05:33:18.899475+00:00"}