{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TSUNEJEFCF6I5HW3ACNJIDTZ4M","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":"62309669d9164c4e076a8d831f6cdd888eb246d7492c1852289fc1a38c0c537d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-02-24T03:48:00Z","title_canon_sha256":"0d64280f07a96f82732355bc150f9ac01a6f55bca8648c657e8733966ed3dd06"},"schema_version":"1.0","source":{"id":"2502.16813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16813","created_at":"2026-07-05T10:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16813v1","created_at":"2026-07-05T10:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16813","created_at":"2026-07-05T10:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"TSUNEJEFCF6I","created_at":"2026-07-05T10:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"TSUNEJEFCF6I5HW3","created_at":"2026-07-05T10:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"TSUNEJEF","created_at":"2026-07-05T10:19:00Z"}],"graph_snapshots":[{"event_id":"sha256:7a62bfb495a8bd6a95e07c45af1e6a188d22a8539016849d38d370229bb459fb","target":"graph","created_at":"2026-07-05T10:19:00Z","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/2502.16813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic join discovery, which aims to find columns in a table repository with high semantic joinabilities to a query column, is crucial for dataset discovery. Existing methods can be divided into two categories: cell-level methods and column-level methods. However, neither of them ensures both effectiveness and efficiency simultaneously. Cell-level methods, which compute the joinability by counting cell matches between columns, enjoy ideal effectiveness but suffer poor efficiency. In contrast, column-level methods, which determine joinability only by computing the similarity of column embeddi","authors_text":"Lu Chen, Yunjun Gao, Yuren Mao, Yuxiang Guo, Zhonghao Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-02-24T03:48:00Z","title":"Snoopy: Effective and Efficient Semantic Join Discovery via Proxy Columns"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16813","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:cb484989fdbd95c7a5abb546cc95c21993de78d200cd10517221a5fab05cad24","target":"record","created_at":"2026-07-05T10:19:00Z","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":"62309669d9164c4e076a8d831f6cdd888eb246d7492c1852289fc1a38c0c537d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-02-24T03:48:00Z","title_canon_sha256":"0d64280f07a96f82732355bc150f9ac01a6f55bca8648c657e8733966ed3dd06"},"schema_version":"1.0","source":{"id":"2502.16813","kind":"arxiv","version":1}},"canonical_sha256":"9ca8d22485117c8e9edb009a940e79e30d81ea6b53e6535e964c4ab05d8f929b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ca8d22485117c8e9edb009a940e79e30d81ea6b53e6535e964c4ab05d8f929b","first_computed_at":"2026-07-05T10:19:00.149972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:00.149972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9PsQrzhZQ5MEtTegRnT0KnkECiK6AYNQiCLC+xVs5Q+rmMvH/1B1qHjFSuTbCqN3PRQhqt/ib18hwQ3JSqrrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:00.150363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb484989fdbd95c7a5abb546cc95c21993de78d200cd10517221a5fab05cad24","sha256:7a62bfb495a8bd6a95e07c45af1e6a188d22a8539016849d38d370229bb459fb"],"state_sha256":"4bbdd8a8bb3df5b4e60d69cf4f41962c727f97af22c03fa1dcb1e3137674bec0"}