{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IBBPAYGVCYRNVB3ZOHPFYNXDSY","short_pith_number":"pith:IBBPAYGV","canonical_record":{"source":{"id":"2212.07588","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-12-15T02:40:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"33b75afd16d71c93b539e4025be1a08d90726607c72e346cca1ec5155e7cf383","abstract_canon_sha256":"6e74176b7410735c613dda47a54875377cd97ac58df439a4321d97085ad5a400"},"schema_version":"1.0"},"canonical_sha256":"4042f060d51622da877971de5c36e3960ad4db21b2a630305d6fed096364aabb","source":{"kind":"arxiv","id":"2212.07588","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07588","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07588v2","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07588","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"IBBPAYGVCYRN","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"IBBPAYGVCYRNVB3Z","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"IBBPAYGV","created_at":"2026-07-05T06:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IBBPAYGVCYRNVB3ZOHPFYNXDSY","target":"record","payload":{"canonical_record":{"source":{"id":"2212.07588","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-12-15T02:40:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"33b75afd16d71c93b539e4025be1a08d90726607c72e346cca1ec5155e7cf383","abstract_canon_sha256":"6e74176b7410735c613dda47a54875377cd97ac58df439a4321d97085ad5a400"},"schema_version":"1.0"},"canonical_sha256":"4042f060d51622da877971de5c36e3960ad4db21b2a630305d6fed096364aabb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:57.431476Z","signature_b64":"SyEBngKI5yMTAMc7WcKF4sXXhWvkVSmi3/UWDmgz8K5lD/vY/R5UDqgKmk0psFhhV/kv/TuG8mTtIssaZLUZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4042f060d51622da877971de5c36e3960ad4db21b2a630305d6fed096364aabb","last_reissued_at":"2026-07-05T06:23:57.431051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:57.431051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.07588","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":"2026-07-05T06:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BghjG/mFD3HzG2gSa9WAFBunrzvfPOUL69fdK+kVnAZgIpxZI7r8l0HftEdPQt53V7E+NbhNOyg1mEBTntHoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:54.188331Z"},"content_sha256":"57552271e222886033d114cc726f7b77b070167bf67c60eeb504ec516d146ed1","schema_version":"1.0","event_id":"sha256:57552271e222886033d114cc726f7b77b070167bf67c60eeb504ec516d146ed1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IBBPAYGVCYRNVB3ZOHPFYNXDSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepJoin: Joinable Table Discovery with Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Chuan Xiao, Masafumi Enomoto, Masafumi Oyamada, Takuma Nozawa, Yuyang Dong","submitted_at":"2022-12-15T02:40:57Z","abstract_excerpt":"Due to the usefulness in data enrichment for data analysis tasks, joinable table discovery has become an important operation in data lake management. Existing approaches target equi-joins, the most common way of combining tables for creating a unified view, or semantic joins, which tolerate misspellings and different formats to deliver more join results. They are either exact solutions whose running time is linear in the sizes of query column and target table repository or approximate solutions lacking precision. In this paper, we propose Deepjoin, a deep learning model for accurate and effici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07588","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/2212.07588/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":"2026-07-05T06:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svq4XHNBqCu0TPJtW1alFLtFbqMPyntWv1SuNnw3h84j8Sa8kD0BPQciMhoOHcaSN+7N/X0H2roYRDUhqlvDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:54.189983Z"},"content_sha256":"231ed51f0452a020908aa6fd349d55fea9ecc1653c64701ab026b40db64afef6","schema_version":"1.0","event_id":"sha256:231ed51f0452a020908aa6fd349d55fea9ecc1653c64701ab026b40db64afef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY/bundle.json","state_url":"https://pith.science/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY/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":"2026-08-07T15:45:54Z","links":{"resolver":"https://pith.science/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY","bundle":"https://pith.science/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY/bundle.json","state":"https://pith.science/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBBPAYGVCYRNVB3ZOHPFYNXDSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IBBPAYGVCYRNVB3ZOHPFYNXDSY","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":"6e74176b7410735c613dda47a54875377cd97ac58df439a4321d97085ad5a400","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-12-15T02:40:57Z","title_canon_sha256":"33b75afd16d71c93b539e4025be1a08d90726607c72e346cca1ec5155e7cf383"},"schema_version":"1.0","source":{"id":"2212.07588","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07588","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07588v2","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07588","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"IBBPAYGVCYRN","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"IBBPAYGVCYRNVB3Z","created_at":"2026-07-05T06:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"IBBPAYGV","created_at":"2026-07-05T06:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:231ed51f0452a020908aa6fd349d55fea9ecc1653c64701ab026b40db64afef6","target":"graph","created_at":"2026-07-05T06:23:57Z","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/2212.07588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the usefulness in data enrichment for data analysis tasks, joinable table discovery has become an important operation in data lake management. Existing approaches target equi-joins, the most common way of combining tables for creating a unified view, or semantic joins, which tolerate misspellings and different formats to deliver more join results. They are either exact solutions whose running time is linear in the sizes of query column and target table repository or approximate solutions lacking precision. In this paper, we propose Deepjoin, a deep learning model for accurate and effici","authors_text":"Chuan Xiao, Masafumi Enomoto, Masafumi Oyamada, Takuma Nozawa, Yuyang Dong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-12-15T02:40:57Z","title":"DeepJoin: Joinable Table Discovery with Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07588","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":"sha256:57552271e222886033d114cc726f7b77b070167bf67c60eeb504ec516d146ed1","target":"record","created_at":"2026-07-05T06:23:57Z","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":"6e74176b7410735c613dda47a54875377cd97ac58df439a4321d97085ad5a400","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-12-15T02:40:57Z","title_canon_sha256":"33b75afd16d71c93b539e4025be1a08d90726607c72e346cca1ec5155e7cf383"},"schema_version":"1.0","source":{"id":"2212.07588","kind":"arxiv","version":2}},"canonical_sha256":"4042f060d51622da877971de5c36e3960ad4db21b2a630305d6fed096364aabb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4042f060d51622da877971de5c36e3960ad4db21b2a630305d6fed096364aabb","first_computed_at":"2026-07-05T06:23:57.431051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:57.431051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SyEBngKI5yMTAMc7WcKF4sXXhWvkVSmi3/UWDmgz8K5lD/vY/R5UDqgKmk0psFhhV/kv/TuG8mTtIssaZLUZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:57.431476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.07588","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57552271e222886033d114cc726f7b77b070167bf67c60eeb504ec516d146ed1","sha256:231ed51f0452a020908aa6fd349d55fea9ecc1653c64701ab026b40db64afef6"],"state_sha256":"426edecce2666020556a281dc97c0570bd5d274e645ba8330feb80979fe242d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCEP2JPsXJarEQ0HEeA98/eV33FwIF8i//A0m94D1DhvsFhqcF3P/UuXnQgpB2nUdgfn/XhpPgqQhFZuBiE4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:45:54.209463Z","bundle_sha256":"5552559c136e973344fb56dca62b8e5304a1e67d9e529ab48eed50c469326155"}}