{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DL2O75ZZ7YG3A4C6OQSVAIJWVE","short_pith_number":"pith:DL2O75ZZ","schema_version":"1.0","canonical_sha256":"1af4eff739fe0db0705e7425502136a9149a4da74ff93e64c5ff5ed8e0c51a44","source":{"kind":"arxiv","id":"2606.17882","version":1},"attestation_state":"computed","paper":{"title":"Structural Preservation and the Logical Expressiveness of Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bernardo Cuenca Grau, Przemys{\\l}aw Andrzej Wa{\\l}\\k{e}ga","submitted_at":"2026-06-16T12:57:50Z","abstract_excerpt":"Bridges between graph neural networks (GNNs) and logical formalisms have been established by fixing architectural choices, such as the types of aggregation, combination, and activation functions. These choices define restricted classes of GNNs for which tight correspondences with logical formalisms can be obtained, by showing that logical formulae can be translated into equivalent GNNs and, conversely, that GNNs can be translated into equivalent formulae.\n  In this paper we take a semantic perspective by establishing the logical expressiveness of classes of GNN classifiers that are preserved u"},"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":"2606.17882","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T12:57:50Z","cross_cats_sorted":[],"title_canon_sha256":"a55844b88b74fd98da76c280d99bf2c940e3af66d9224f82ba63a3824debb04b","abstract_canon_sha256":"d4e46cc2859a62dc06d47a0983adbe0f8abb97271b6b7b695265e9cf68a7481f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:42.596619Z","signature_b64":"m2nd/A5n3krkLaxlkJEi5ZUn/E4ZCDLW2Fl82drOGS1sGhUZ5egbMuU8Yqmu8+eL00Kx8ZzdnZ0w8g/M6H4uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1af4eff739fe0db0705e7425502136a9149a4da74ff93e64c5ff5ed8e0c51a44","last_reissued_at":"2026-06-19T16:10:42.596204Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:42.596204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structural Preservation and the Logical Expressiveness of Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bernardo Cuenca Grau, Przemys{\\l}aw Andrzej Wa{\\l}\\k{e}ga","submitted_at":"2026-06-16T12:57:50Z","abstract_excerpt":"Bridges between graph neural networks (GNNs) and logical formalisms have been established by fixing architectural choices, such as the types of aggregation, combination, and activation functions. These choices define restricted classes of GNNs for which tight correspondences with logical formalisms can be obtained, by showing that logical formulae can be translated into equivalent GNNs and, conversely, that GNNs can be translated into equivalent formulae.\n  In this paper we take a semantic perspective by establishing the logical expressiveness of classes of GNN classifiers that are preserved u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17882","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/2606.17882/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":"2606.17882","created_at":"2026-06-19T16:10:42.596269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17882v1","created_at":"2026-06-19T16:10:42.596269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17882","created_at":"2026-06-19T16:10:42.596269+00:00"},{"alias_kind":"pith_short_12","alias_value":"DL2O75ZZ7YG3","created_at":"2026-06-19T16:10:42.596269+00:00"},{"alias_kind":"pith_short_16","alias_value":"DL2O75ZZ7YG3A4C6","created_at":"2026-06-19T16:10:42.596269+00:00"},{"alias_kind":"pith_short_8","alias_value":"DL2O75ZZ","created_at":"2026-06-19T16:10:42.596269+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/DL2O75ZZ7YG3A4C6OQSVAIJWVE","json":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE.json","graph_json":"https://pith.science/api/pith-number/DL2O75ZZ7YG3A4C6OQSVAIJWVE/graph.json","events_json":"https://pith.science/api/pith-number/DL2O75ZZ7YG3A4C6OQSVAIJWVE/events.json","paper":"https://pith.science/paper/DL2O75ZZ"},"agent_actions":{"view_html":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE","download_json":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE.json","view_paper":"https://pith.science/paper/DL2O75ZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17882&json=true","fetch_graph":"https://pith.science/api/pith-number/DL2O75ZZ7YG3A4C6OQSVAIJWVE/graph.json","fetch_events":"https://pith.science/api/pith-number/DL2O75ZZ7YG3A4C6OQSVAIJWVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE/action/storage_attestation","attest_author":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE/action/author_attestation","sign_citation":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE/action/citation_signature","submit_replication":"https://pith.science/pith/DL2O75ZZ7YG3A4C6OQSVAIJWVE/action/replication_record"}},"created_at":"2026-06-19T16:10:42.596269+00:00","updated_at":"2026-06-19T16:10:42.596269+00:00"}