{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L7XWXO2BGGCT53H35AXW5DK2AJ","short_pith_number":"pith:L7XWXO2B","schema_version":"1.0","canonical_sha256":"5fef6bbb4131853eecfbe82f6e8d5a024865545beea3528b3956d63da4814530","source":{"kind":"arxiv","id":"2508.10651","version":3},"attestation_state":"computed","paper":{"title":"Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antti Kuusisto, Magdalena Ortiz, Mantas \\v{S}imkus, Matias Selin, Reijo Jaakkola, Tomi Janhunen","submitted_at":"2025-08-14T13:47:50Z","abstract_excerpt":"We present a novel approach for graph classification based on tabularizing graph data via new variants of the Weisfeiler-Leman algorithm and then applying methods for tabular data. The variants are obtained by modifying the underlying logical framework, and we establish a precise theoretical characterization of their expressive power using a novel generalization of the bisimulation game for generalized quantifiers. We then test our method on 14 datasets that span a range of application domains. The experiments demonstrate that on datasets with up to 40 000 samples, our approach generally match"},"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":"2508.10651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T13:47:50Z","cross_cats_sorted":[],"title_canon_sha256":"7f36ef98f18a3f289b741409694d62d44673f917b4d700bfa53dec114e01bf9c","abstract_canon_sha256":"e1bbab058a85156d9a5325bb49f6f3ae5c8a37b3fd31c403b743ac33e5bb4f3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:06.012707Z","signature_b64":"dfKoxVVdDkSUekcXUldM6SIeuQn+tBUWsApmXS6wU2UCJjfhJs44FYStIuBN+MTvwxNUgAnaGL2ZjNFp7J5yAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fef6bbb4131853eecfbe82f6e8d5a024865545beea3528b3956d63da4814530","last_reissued_at":"2026-05-25T02:01:06.011766Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:06.011766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antti Kuusisto, Magdalena Ortiz, Mantas \\v{S}imkus, Matias Selin, Reijo Jaakkola, Tomi Janhunen","submitted_at":"2025-08-14T13:47:50Z","abstract_excerpt":"We present a novel approach for graph classification based on tabularizing graph data via new variants of the Weisfeiler-Leman algorithm and then applying methods for tabular data. The variants are obtained by modifying the underlying logical framework, and we establish a precise theoretical characterization of their expressive power using a novel generalization of the bisimulation game for generalized quantifiers. We then test our method on 14 datasets that span a range of application domains. The experiments demonstrate that on datasets with up to 40 000 samples, our approach generally match"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10651","kind":"arxiv","version":3},"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/2508.10651/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":"2508.10651","created_at":"2026-05-25T02:01:06.011897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10651v3","created_at":"2026-05-25T02:01:06.011897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10651","created_at":"2026-05-25T02:01:06.011897+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7XWXO2BGGCT","created_at":"2026-05-25T02:01:06.011897+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7XWXO2BGGCT53H3","created_at":"2026-05-25T02:01:06.011897+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7XWXO2B","created_at":"2026-05-25T02:01:06.011897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21170","citing_title":"Model Comparison Games for Generalized Quantifiers","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10393","citing_title":"The Polynomial Counting Capabilities of Message Passing Neural Networks","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ","json":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ.json","graph_json":"https://pith.science/api/pith-number/L7XWXO2BGGCT53H35AXW5DK2AJ/graph.json","events_json":"https://pith.science/api/pith-number/L7XWXO2BGGCT53H35AXW5DK2AJ/events.json","paper":"https://pith.science/paper/L7XWXO2B"},"agent_actions":{"view_html":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ","download_json":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ.json","view_paper":"https://pith.science/paper/L7XWXO2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10651&json=true","fetch_graph":"https://pith.science/api/pith-number/L7XWXO2BGGCT53H35AXW5DK2AJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L7XWXO2BGGCT53H35AXW5DK2AJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ/action/storage_attestation","attest_author":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ/action/author_attestation","sign_citation":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ/action/citation_signature","submit_replication":"https://pith.science/pith/L7XWXO2BGGCT53H35AXW5DK2AJ/action/replication_record"}},"created_at":"2026-05-25T02:01:06.011897+00:00","updated_at":"2026-05-25T02:01:06.011897+00:00"}