{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IP5N4KAVZKPWM3Y6OS3W4WJ3G6","short_pith_number":"pith:IP5N4KAV","canonical_record":{"source":{"id":"2301.04901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-12T09:51:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f4436c9ac0cb2cf24966e28611ccfaa5054028362367ad80bc1428d05d213f98","abstract_canon_sha256":"4a620925e73a94144fbbe77a44e95a1af1f3a5d9194b49a04137eca8dc2fbebc"},"schema_version":"1.0"},"canonical_sha256":"43fade2815ca9f666f1e74b76e593b3792617e3688191417fa7e47ed90b0e803","source":{"kind":"arxiv","id":"2301.04901","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04901","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04901v2","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04901","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"IP5N4KAVZKPW","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"IP5N4KAVZKPWM3Y6","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"IP5N4KAV","created_at":"2026-07-05T05:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IP5N4KAVZKPWM3Y6OS3W4WJ3G6","target":"record","payload":{"canonical_record":{"source":{"id":"2301.04901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-12T09:51:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f4436c9ac0cb2cf24966e28611ccfaa5054028362367ad80bc1428d05d213f98","abstract_canon_sha256":"4a620925e73a94144fbbe77a44e95a1af1f3a5d9194b49a04137eca8dc2fbebc"},"schema_version":"1.0"},"canonical_sha256":"43fade2815ca9f666f1e74b76e593b3792617e3688191417fa7e47ed90b0e803","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:50.584053Z","signature_b64":"eTyozqVVIhVTUhPTrRlKhQ+3BiFIqFbiJJI6KNTIc0z7DplPjP4x6hC0l0mzqlc1ztrXg9R6eKCLLeysuEszAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43fade2815ca9f666f1e74b76e593b3792617e3688191417fa7e47ed90b0e803","last_reissued_at":"2026-07-05T05:32:50.583664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:50.583664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.04901","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":"2026-07-05T05:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EbF2XSujzovX9p3yTUh2duf+wPhkofsuA15AoTpUUGZuHDa2xuGIk/8o9blOfX58I56ubZVab/bqxrIaNJxlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:43:21.368271Z"},"content_sha256":"4ba3873f9c35052b610513770c83e92d9b2c4ee731f5a6e404b83affb562e92a","schema_version":"1.0","event_id":"sha256:4ba3873f9c35052b610513770c83e92d9b2c4ee731f5a6e404b83affb562e92a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IP5N4KAVZKPWM3Y6OS3W4WJ3G6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pylon: Semantic Table Union Search in Data Lakes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Fatemeh Nargesian, H. V. Jagadish, Tianji Cong","submitted_at":"2023-01-12T09:51:48Z","abstract_excerpt":"The large size and fast growth of data repositories, such as data lakes, has spurred the need for data discovery to help analysts find related data. The problem has become challenging as (i) a user typically does not know what datasets exist in an enormous data repository; and (ii) there is usually a lack of a unified data model to capture the interrelationships between heterogeneous datasets from disparate sources. In this work, we address one important class of discovery needs: finding union-able tables.\n  The task is to find tables in a data lake that can be unioned with a given query table"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04901","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/2301.04901/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":"2026-07-05T05:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxMG1n36XoC/ptPBp1sRQLsqchslQO05T42W0qD0CIZZr736ECwgnf+GVKlSPL5Q8YNeExjlfWQqrVUyvK18Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:43:21.368768Z"},"content_sha256":"308908e8ed0eadf8bbc76ab6a7fa02bf34176c59dacad4e233a04d6625727e7e","schema_version":"1.0","event_id":"sha256:308908e8ed0eadf8bbc76ab6a7fa02bf34176c59dacad4e233a04d6625727e7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6/bundle.json","state_url":"https://pith.science/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6/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":"2026-08-08T11:43:21Z","links":{"resolver":"https://pith.science/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6","bundle":"https://pith.science/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6/bundle.json","state":"https://pith.science/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IP5N4KAVZKPWM3Y6OS3W4WJ3G6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IP5N4KAVZKPWM3Y6OS3W4WJ3G6","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":"4a620925e73a94144fbbe77a44e95a1af1f3a5d9194b49a04137eca8dc2fbebc","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-12T09:51:48Z","title_canon_sha256":"f4436c9ac0cb2cf24966e28611ccfaa5054028362367ad80bc1428d05d213f98"},"schema_version":"1.0","source":{"id":"2301.04901","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04901","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04901v2","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04901","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"IP5N4KAVZKPW","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"IP5N4KAVZKPWM3Y6","created_at":"2026-07-05T05:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"IP5N4KAV","created_at":"2026-07-05T05:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:308908e8ed0eadf8bbc76ab6a7fa02bf34176c59dacad4e233a04d6625727e7e","target":"graph","created_at":"2026-07-05T05:32:50Z","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/2301.04901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large size and fast growth of data repositories, such as data lakes, has spurred the need for data discovery to help analysts find related data. The problem has become challenging as (i) a user typically does not know what datasets exist in an enormous data repository; and (ii) there is usually a lack of a unified data model to capture the interrelationships between heterogeneous datasets from disparate sources. In this work, we address one important class of discovery needs: finding union-able tables.\n  The task is to find tables in a data lake that can be unioned with a given query table","authors_text":"Fatemeh Nargesian, H. V. Jagadish, Tianji Cong","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-12T09:51:48Z","title":"Pylon: Semantic Table Union Search in Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04901","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":"sha256:4ba3873f9c35052b610513770c83e92d9b2c4ee731f5a6e404b83affb562e92a","target":"record","created_at":"2026-07-05T05:32:50Z","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":"4a620925e73a94144fbbe77a44e95a1af1f3a5d9194b49a04137eca8dc2fbebc","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-12T09:51:48Z","title_canon_sha256":"f4436c9ac0cb2cf24966e28611ccfaa5054028362367ad80bc1428d05d213f98"},"schema_version":"1.0","source":{"id":"2301.04901","kind":"arxiv","version":2}},"canonical_sha256":"43fade2815ca9f666f1e74b76e593b3792617e3688191417fa7e47ed90b0e803","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43fade2815ca9f666f1e74b76e593b3792617e3688191417fa7e47ed90b0e803","first_computed_at":"2026-07-05T05:32:50.583664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:50.583664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTyozqVVIhVTUhPTrRlKhQ+3BiFIqFbiJJI6KNTIc0z7DplPjP4x6hC0l0mzqlc1ztrXg9R6eKCLLeysuEszAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:50.584053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.04901","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ba3873f9c35052b610513770c83e92d9b2c4ee731f5a6e404b83affb562e92a","sha256:308908e8ed0eadf8bbc76ab6a7fa02bf34176c59dacad4e233a04d6625727e7e"],"state_sha256":"f90d512586f55cfb552eaa827371bcd5cb676d90b52a389224948b25fc92ffd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QVYlM7WrTX2+y+ujA1HBxf4ogjY2ZsmFMyb1PnleQ9V5iKu4I8K4q3YX0eCuQp5eu3sgyZP9GkD6bf8ovvutCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:43:21.373571Z","bundle_sha256":"a6fea8025469fcb9113bbe214735b2c911aaee3741b1cd6476aea0a54210e57a"}}