{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WL3XTVM5Y5WDOY5CP7472BOQ2W","short_pith_number":"pith:WL3XTVM5","canonical_record":{"source":{"id":"2507.11505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-15T17:20:56Z","cross_cats_sorted":[],"title_canon_sha256":"cc3110100998f4def9499486a2ee075e1055005c647ae4590dc04afe460f3bc9","abstract_canon_sha256":"5947a0faa7ee583886aa122e0ee203d41fa4da7d51425791437a402b7be0fbbb"},"schema_version":"1.0"},"canonical_sha256":"b2f779d59dc76c3763a27ff9fd05d0d59fc1b99f89bd29c3b73cad2ab9b8a441","source":{"kind":"arxiv","id":"2507.11505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11505","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11505v1","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11505","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"WL3XTVM5Y5WD","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"WL3XTVM5Y5WDOY5C","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"WL3XTVM5","created_at":"2026-07-05T11:37:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WL3XTVM5Y5WDOY5CP7472BOQ2W","target":"record","payload":{"canonical_record":{"source":{"id":"2507.11505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-15T17:20:56Z","cross_cats_sorted":[],"title_canon_sha256":"cc3110100998f4def9499486a2ee075e1055005c647ae4590dc04afe460f3bc9","abstract_canon_sha256":"5947a0faa7ee583886aa122e0ee203d41fa4da7d51425791437a402b7be0fbbb"},"schema_version":"1.0"},"canonical_sha256":"b2f779d59dc76c3763a27ff9fd05d0d59fc1b99f89bd29c3b73cad2ab9b8a441","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:40.185429Z","signature_b64":"X+aNb5QYTaVVih3b97iPCBDa9SlD0yDzDy8VZH+4jw9vvmjOq6WrjWtPvs0+1lhPE2zJpdyWNZsMQSXcjg/sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f779d59dc76c3763a27ff9fd05d0d59fc1b99f89bd29c3b73cad2ab9b8a441","last_reissued_at":"2026-07-05T11:37:40.184997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:40.184997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.11505","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtBZcRJrMAFvVb1SqorYwGvKr5K2N+D5TUU2jHqJaqE0Ml190yv/wV3UzrDZ6HgBUEy1KEI2KVhy60h/otSFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:23:57.705874Z"},"content_sha256":"3191cd7bec59821a91693a08c70b4bb91c711dadfabb043d94588df5369a9172","schema_version":"1.0","event_id":"sha256:3191cd7bec59821a91693a08c70b4bb91c711dadfabb043d94588df5369a9172"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WL3XTVM5Y5WDOY5CP7472BOQ2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aamod Khatiwada, Haritha Ananthakrishnan, Harsha Kokel, Horst Samulowitz, Kavitha Srinivas, Oktie Hassanzadeh, Tejaswini Pedapati","submitted_at":"2025-07-15T17:20:56Z","abstract_excerpt":"One of the major challenges in enterprise data analysis is the task of finding joinable tables that are conceptually related and provide meaningful insights. Traditionally, joinable tables have been discovered through a search for similar columns, where two columns are considered similar syntactically if there is a set overlap or they are considered similar semantically if either the column embeddings or value embeddings are closer in the embedding space. However, for enterprise data lakes, column similarity is not sufficient to identify joinable columns and tables. The context of the query co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11505","kind":"arxiv","version":1},"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/2507.11505/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":"2026-07-05T11:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v1zhZn96USlwjjqeMG37Kp9IJ8kf4pQIe6oVUFQvyUjXVMeWz9qxKFgXRzTO3THI0iaibdWwq9/OzlMgFnyECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:23:57.706430Z"},"content_sha256":"7587080ccac553969b2b4dc9ea700f304e599b5bc6cca965f35a42ae5b4d9df5","schema_version":"1.0","event_id":"sha256:7587080ccac553969b2b4dc9ea700f304e599b5bc6cca965f35a42ae5b4d9df5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W/bundle.json","state_url":"https://pith.science/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W/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":"2026-08-04T11:23:57Z","links":{"resolver":"https://pith.science/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W","bundle":"https://pith.science/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W/bundle.json","state":"https://pith.science/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WL3XTVM5Y5WDOY5CP7472BOQ2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WL3XTVM5Y5WDOY5CP7472BOQ2W","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":"5947a0faa7ee583886aa122e0ee203d41fa4da7d51425791437a402b7be0fbbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-15T17:20:56Z","title_canon_sha256":"cc3110100998f4def9499486a2ee075e1055005c647ae4590dc04afe460f3bc9"},"schema_version":"1.0","source":{"id":"2507.11505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11505","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11505v1","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11505","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"WL3XTVM5Y5WD","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"WL3XTVM5Y5WDOY5C","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"WL3XTVM5","created_at":"2026-07-05T11:37:40Z"}],"graph_snapshots":[{"event_id":"sha256:7587080ccac553969b2b4dc9ea700f304e599b5bc6cca965f35a42ae5b4d9df5","target":"graph","created_at":"2026-07-05T11:37:40Z","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/2507.11505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the major challenges in enterprise data analysis is the task of finding joinable tables that are conceptually related and provide meaningful insights. Traditionally, joinable tables have been discovered through a search for similar columns, where two columns are considered similar syntactically if there is a set overlap or they are considered similar semantically if either the column embeddings or value embeddings are closer in the embedding space. However, for enterprise data lakes, column similarity is not sufficient to identify joinable columns and tables. The context of the query co","authors_text":"Aamod Khatiwada, Haritha Ananthakrishnan, Harsha Kokel, Horst Samulowitz, Kavitha Srinivas, Oktie Hassanzadeh, Tejaswini Pedapati","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-15T17:20:56Z","title":"TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11505","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":"sha256:3191cd7bec59821a91693a08c70b4bb91c711dadfabb043d94588df5369a9172","target":"record","created_at":"2026-07-05T11:37:40Z","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":"5947a0faa7ee583886aa122e0ee203d41fa4da7d51425791437a402b7be0fbbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-15T17:20:56Z","title_canon_sha256":"cc3110100998f4def9499486a2ee075e1055005c647ae4590dc04afe460f3bc9"},"schema_version":"1.0","source":{"id":"2507.11505","kind":"arxiv","version":1}},"canonical_sha256":"b2f779d59dc76c3763a27ff9fd05d0d59fc1b99f89bd29c3b73cad2ab9b8a441","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2f779d59dc76c3763a27ff9fd05d0d59fc1b99f89bd29c3b73cad2ab9b8a441","first_computed_at":"2026-07-05T11:37:40.184997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:40.184997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X+aNb5QYTaVVih3b97iPCBDa9SlD0yDzDy8VZH+4jw9vvmjOq6WrjWtPvs0+1lhPE2zJpdyWNZsMQSXcjg/sDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:40.185429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3191cd7bec59821a91693a08c70b4bb91c711dadfabb043d94588df5369a9172","sha256:7587080ccac553969b2b4dc9ea700f304e599b5bc6cca965f35a42ae5b4d9df5"],"state_sha256":"e15cf7dcecd8de1bc4ade07415b12bf58fb70fa297b78b5385fcd46cfe7ba825"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h7pYXPFmL9VS+EMoAayd+/SLhpUXG3uQxxokDu2lIgypC63LXtiVEjWS07z7uPt/IUkvtf3YV5B23C/skuONCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:23:57.710212Z","bundle_sha256":"3e2580713832eb75844cd7a3342a368124a758630711f8e90386955f959cae68"}}