{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KNUY5Y7DCKHIJ323JQPHLDYPZ3","short_pith_number":"pith:KNUY5Y7D","canonical_record":{"source":{"id":"2607.00833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-01T11:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"f07321951ed7057b9022e17983ef86fc03f42cbe5a159f2e3a0927b2925911ed","abstract_canon_sha256":"834ca52e39b6ed68745f80e0b99325fba33cd05c30cddccdd4a3110b8650ea19"},"schema_version":"1.0"},"canonical_sha256":"53698ee3e3128e84ef5b4c1e758f0fceccf34191df4d8bcf9956c1826dc71b68","source":{"kind":"arxiv","id":"2607.00833","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00833","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00833v1","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00833","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"KNUY5Y7DCKHI","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"KNUY5Y7DCKHIJ323","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"KNUY5Y7D","created_at":"2026-07-02T01:18:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KNUY5Y7DCKHIJ323JQPHLDYPZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-01T11:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"f07321951ed7057b9022e17983ef86fc03f42cbe5a159f2e3a0927b2925911ed","abstract_canon_sha256":"834ca52e39b6ed68745f80e0b99325fba33cd05c30cddccdd4a3110b8650ea19"},"schema_version":"1.0"},"canonical_sha256":"53698ee3e3128e84ef5b4c1e758f0fceccf34191df4d8bcf9956c1826dc71b68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:20.990917Z","signature_b64":"vqnqY7+Y72Xsd4WnIkwz42mefacOblTcraBs4wv/vSW/3OHwWpvltGRNQ3VOSv+YbaCjlz0GFrqYj4RJfBpLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53698ee3e3128e84ef5b4c1e758f0fceccf34191df4d8bcf9956c1826dc71b68","last_reissued_at":"2026-07-02T01:18:20.990538Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:20.990538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00833","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":"2026-07-02T01:18:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CMzfAeizkXLvuLoa/shs45xN3voTRnnsrXgfQ8frVyGWLJheBsb1bYHoWSa8DMc3Q0e7j/iGoj7qoXsqR9zHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T04:34:57.020107Z"},"content_sha256":"94dd536cca5b8616fc9fa9cc694c4c907712e09871d9f8fa25f990367dca9e4b","schema_version":"1.0","event_id":"sha256:94dd536cca5b8616fc9fa9cc694c4c907712e09871d9f8fa25f990367dca9e4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KNUY5Y7DCKHIJ323JQPHLDYPZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Retrieval for Table Union Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chenhao Ma, Linting Wang, Shulun Zhang, Yingli Zhou, Yuwei Xu","submitted_at":"2026-07-01T11:54:30Z","abstract_excerpt":"Modern data lakes contain heterogeneous tables whose task-relevant information is often scattered across different schemas, sources, and naming conventions. Table union search (TUS) retrieves tables that can be reliably unioned with a query table, supporting data discovery, enrichment, and downstream analytics. Although learning-based TUS methods improve table- or column-level representations, they still follow an encode-search-refine pipeline: candidate retrieval is followed by query-candidate matching or reranking, making quality dependent on candidate-pool recall and incurring growing laten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00833","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/2607.00833/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":"2026-07-02T01:18:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbdoB14MnWzXdKfnLiz7rskmRXJDfKBTBk7sHCm5PQIsZOuog7et8PGNBECPrRuzXb8/2DO+8VOWhC1Tlht1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T04:34:57.020497Z"},"content_sha256":"d35699b00217c3950ae1d5197ced5e27859381e688bfdf7eb15593347e3066df","schema_version":"1.0","event_id":"sha256:d35699b00217c3950ae1d5197ced5e27859381e688bfdf7eb15593347e3066df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3/bundle.json","state_url":"https://pith.science/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3/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":"2026-07-03T04:34:57Z","links":{"resolver":"https://pith.science/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3","bundle":"https://pith.science/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3/bundle.json","state":"https://pith.science/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KNUY5Y7DCKHIJ323JQPHLDYPZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KNUY5Y7DCKHIJ323JQPHLDYPZ3","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":"834ca52e39b6ed68745f80e0b99325fba33cd05c30cddccdd4a3110b8650ea19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-01T11:54:30Z","title_canon_sha256":"f07321951ed7057b9022e17983ef86fc03f42cbe5a159f2e3a0927b2925911ed"},"schema_version":"1.0","source":{"id":"2607.00833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00833","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00833v1","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00833","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"KNUY5Y7DCKHI","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"KNUY5Y7DCKHIJ323","created_at":"2026-07-02T01:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"KNUY5Y7D","created_at":"2026-07-02T01:18:20Z"}],"graph_snapshots":[{"event_id":"sha256:d35699b00217c3950ae1d5197ced5e27859381e688bfdf7eb15593347e3066df","target":"graph","created_at":"2026-07-02T01:18:20Z","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/2607.00833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern data lakes contain heterogeneous tables whose task-relevant information is often scattered across different schemas, sources, and naming conventions. Table union search (TUS) retrieves tables that can be reliably unioned with a query table, supporting data discovery, enrichment, and downstream analytics. Although learning-based TUS methods improve table- or column-level representations, they still follow an encode-search-refine pipeline: candidate retrieval is followed by query-candidate matching or reranking, making quality dependent on candidate-pool recall and incurring growing laten","authors_text":"Chenhao Ma, Linting Wang, Shulun Zhang, Yingli Zhou, Yuwei Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-01T11:54:30Z","title":"Generative Retrieval for Table Union Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00833","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":"sha256:94dd536cca5b8616fc9fa9cc694c4c907712e09871d9f8fa25f990367dca9e4b","target":"record","created_at":"2026-07-02T01:18:20Z","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":"834ca52e39b6ed68745f80e0b99325fba33cd05c30cddccdd4a3110b8650ea19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-01T11:54:30Z","title_canon_sha256":"f07321951ed7057b9022e17983ef86fc03f42cbe5a159f2e3a0927b2925911ed"},"schema_version":"1.0","source":{"id":"2607.00833","kind":"arxiv","version":1}},"canonical_sha256":"53698ee3e3128e84ef5b4c1e758f0fceccf34191df4d8bcf9956c1826dc71b68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53698ee3e3128e84ef5b4c1e758f0fceccf34191df4d8bcf9956c1826dc71b68","first_computed_at":"2026-07-02T01:18:20.990538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:20.990538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vqnqY7+Y72Xsd4WnIkwz42mefacOblTcraBs4wv/vSW/3OHwWpvltGRNQ3VOSv+YbaCjlz0GFrqYj4RJfBpLAQ==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:20.990917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94dd536cca5b8616fc9fa9cc694c4c907712e09871d9f8fa25f990367dca9e4b","sha256:d35699b00217c3950ae1d5197ced5e27859381e688bfdf7eb15593347e3066df"],"state_sha256":"87f1b1e0559dff2298ced1225fdc2a5bdbeae91b6874adafcd1c713d00868994"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dwwoiQEpPJEQQmOKbIHLJMWJ76/YbxIoVRUTdL0rXkzDlqzhsF5uiqz2OFkGrmy042xgZobZy8wtK23uRZTeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T04:34:57.022678Z","bundle_sha256":"5888bd925d020da4ba43187ba468a8f009f4d294c701bb30a5a70209900f7cd8"}}