{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EY2IL36XBABX3RHECJQ52TCN3K","short_pith_number":"pith:EY2IL36X","schema_version":"1.0","canonical_sha256":"263485efd708037dc4e41261dd4c4ddaaa6ed27f7b61514c2c793e6d05db82fe","source":{"kind":"arxiv","id":"2608.11431","version":1},"attestation_state":"computed","paper":{"title":"AutoGrable: What Is a Good Graph for a Table?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Floris Geerts, Tamara Cucumides","submitted_at":"2026-08-11T20:53:42Z","abstract_excerpt":"Graph learning presupposes a graph, and tables and relational databases do not come with one. Applying a GNN to them requires deciding which entities become nodes, which of them to connect, and through which relations---a decision made by hand, by schema heuristics, or by training a model on every candidate graph and keeping the best. We give a criterion that requires no trained graph model. In the minimal table-to-graph abstraction each row is a node, so a message-passing GNN, bounded by 1-WL, sees a construction only as a partition of the rows into colour-refinement classes: a construction i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.11431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T20:53:42Z","cross_cats_sorted":[],"title_canon_sha256":"95a6e237f3fde411c00c95793b25d76f7a362d22113bf39d1f112acf020dce32","abstract_canon_sha256":"39026918760a6c2095b0b2ce8ff059a7e48b388743869eb7ac2369498c10e2b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:21:50.447922Z","signature_b64":"1exz33cRpJYsKAIIlgLgxyswTicIhO9FRwtOHxOCBorItlCHON02wIXTakYJyx7MG1g8T6eegpmPqwshZ7AJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"263485efd708037dc4e41261dd4c4ddaaa6ed27f7b61514c2c793e6d05db82fe","last_reissued_at":"2026-08-13T00:21:50.446455Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:21:50.446455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoGrable: What Is a Good Graph for a Table?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Floris Geerts, Tamara Cucumides","submitted_at":"2026-08-11T20:53:42Z","abstract_excerpt":"Graph learning presupposes a graph, and tables and relational databases do not come with one. Applying a GNN to them requires deciding which entities become nodes, which of them to connect, and through which relations---a decision made by hand, by schema heuristics, or by training a model on every candidate graph and keeping the best. We give a criterion that requires no trained graph model. In the minimal table-to-graph abstraction each row is a node, so a message-passing GNN, bounded by 1-WL, sees a construction only as a partition of the rows into colour-refinement classes: a construction i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11431","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/2608.11431/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.11431","created_at":"2026-08-13T00:21:50.446765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11431v1","created_at":"2026-08-13T00:21:50.446765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11431","created_at":"2026-08-13T00:21:50.446765+00:00"},{"alias_kind":"pith_short_12","alias_value":"EY2IL36XBABX","created_at":"2026-08-13T00:21:50.446765+00:00"},{"alias_kind":"pith_short_16","alias_value":"EY2IL36XBABX3RHE","created_at":"2026-08-13T00:21:50.446765+00:00"},{"alias_kind":"pith_short_8","alias_value":"EY2IL36X","created_at":"2026-08-13T00:21:50.446765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K","json":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K.json","graph_json":"https://pith.science/api/pith-number/EY2IL36XBABX3RHECJQ52TCN3K/graph.json","events_json":"https://pith.science/api/pith-number/EY2IL36XBABX3RHECJQ52TCN3K/events.json","paper":"https://pith.science/paper/EY2IL36X"},"agent_actions":{"view_html":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K","download_json":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K.json","view_paper":"https://pith.science/paper/EY2IL36X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11431&json=true","fetch_graph":"https://pith.science/api/pith-number/EY2IL36XBABX3RHECJQ52TCN3K/graph.json","fetch_events":"https://pith.science/api/pith-number/EY2IL36XBABX3RHECJQ52TCN3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K/action/storage_attestation","attest_author":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K/action/author_attestation","sign_citation":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K/action/citation_signature","submit_replication":"https://pith.science/pith/EY2IL36XBABX3RHECJQ52TCN3K/action/replication_record"}},"created_at":"2026-08-13T00:21:50.446765+00:00","updated_at":"2026-08-13T00:21:50.446765+00:00"}