{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:E2BHMOXG6MTM7OHVB6G726RUHZ","short_pith_number":"pith:E2BHMOXG","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"},"canonical_sha256":"2682763ae6f326cfb8f50f8dfd7a343e6a77654beb396366203306658beccd9d","source":{"kind":"arxiv","id":"2210.01922","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01922","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01922v2","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01922","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"pith_short_12","alias_value":"E2BHMOXG6MTM","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"E2BHMOXG6MTM7OHV","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"E2BHMOXG","created_at":"2026-07-05T05:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:E2BHMOXG6MTM7OHVB6G726RUHZ","target":"record","payload":{"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"},"canonical_sha256":"2682763ae6f326cfb8f50f8dfd7a343e6a77654beb396366203306658beccd9d","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"},"source_kind":"arxiv","source_id":"2210.01922","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:33:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2M3F33WTJnYzWy6nMi5fVC5BgXZy/bIrCiTy3LSx1rPHkZfx1SlMkcD1HXUW/pcW3r+8A2es2dROya6KyPXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:21:05.663249Z"},"content_sha256":"16e129594b546653247f7d640aaf99592b138cf6668886f554ed9aacff72ef81","schema_version":"1.0","event_id":"sha256:16e129594b546653247f7d640aaf99592b138cf6668886f554ed9aacff72ef81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:E2BHMOXG6MTM7OHVB6G726RUHZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:33:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FMKhuLCq7hWwqoKZQyB0DUGZ06ME9UF0avfci6j62CvVwd1O8mq+qJJRaJpoNwa5uUrZv7BUiIvsonrFvtxoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:21:05.663767Z"},"content_sha256":"09a67a9704fffd82e9aa5c84174e3f00b278b5551e97a382f99eff9e7efb0814","schema_version":"1.0","event_id":"sha256:09a67a9704fffd82e9aa5c84174e3f00b278b5551e97a382f99eff9e7efb0814"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/bundle.json","state_url":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/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":"2026-08-22T12:21:05Z","links":{"resolver":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ","bundle":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/bundle.json","state":"https://pith.science/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E2BHMOXG6MTM7OHVB6G726RUHZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E2BHMOXG6MTM7OHVB6G726RUHZ","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":"35d9f70c53aa027249452541a7c3d620d0943af1d791fa06e1b92f0f1581ee43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-10-04T21:44:57Z","title_canon_sha256":"5c271b3a3848bdb8721a59bbe0bed2f5e7998250604ecf4f426f760f874d0695"},"schema_version":"1.0","source":{"id":"2210.01922","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01922","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01922v2","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01922","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"pith_short_12","alias_value":"E2BHMOXG6MTM","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"E2BHMOXG6MTM7OHV","created_at":"2026-07-05T05:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"E2BHMOXG","created_at":"2026-07-05T05:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:09a67a9704fffd82e9aa5c84174e3f00b278b5551e97a382f99eff9e7efb0814","target":"graph","created_at":"2026-07-05T05:33:18Z","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/2210.01922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dan Zhang, Grace Fan, Jin Wang, Ren\\'ee Miller, Yuliang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-10-04T21:44:57Z","title":"Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01922","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":"sha256:16e129594b546653247f7d640aaf99592b138cf6668886f554ed9aacff72ef81","target":"record","created_at":"2026-07-05T05:33:18Z","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":"35d9f70c53aa027249452541a7c3d620d0943af1d791fa06e1b92f0f1581ee43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-10-04T21:44:57Z","title_canon_sha256":"5c271b3a3848bdb8721a59bbe0bed2f5e7998250604ecf4f426f760f874d0695"},"schema_version":"1.0","source":{"id":"2210.01922","kind":"arxiv","version":2}},"canonical_sha256":"2682763ae6f326cfb8f50f8dfd7a343e6a77654beb396366203306658beccd9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2682763ae6f326cfb8f50f8dfd7a343e6a77654beb396366203306658beccd9d","first_computed_at":"2026-07-05T05:33:18.899417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:18.899417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4jaT5WJRV7yEQVMEzR2Gn31RREkviQCtfXKccquTvuIq7k/dOrcpir3hBv95Yo3e5hwNmanNF15802o0u5hOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:18.899871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01922","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16e129594b546653247f7d640aaf99592b138cf6668886f554ed9aacff72ef81","sha256:09a67a9704fffd82e9aa5c84174e3f00b278b5551e97a382f99eff9e7efb0814"],"state_sha256":"4cca15e57536ca360e775a0726c017044a3bd95a02b9c89ffeb176d3a9dce6f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a5QjfOWZ2sGGuPQsuvYUTiEB10bP8QMZ7U2HsVTwC6JafDeYloiCxXrjnV/pYFco8ZnGURbS4pO7RnSs3QtcBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:21:05.668717Z","bundle_sha256":"57cb09ab491f97d1c3572002f600ab1e567603efb8493a484fed8f3aef44aebc"}}