{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ZZWD6CG2DYSCWYE7PFZ6XSC6O","short_pith_number":"pith:4ZZWD6CG","schema_version":"1.0","canonical_sha256":"e67361f846d0f1215b04fbcb9f5e42f3b9fabe29aea393394e8062011af34d70","source":{"kind":"arxiv","id":"2505.18728","version":2},"attestation_state":"computed","paper":{"title":"Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessio Gravina, Andrea Ceni, Carola-Bibiane Schonlieb, Claudio Gallicchio, Davide Bacciu, Moshe Eliasof","submitted_at":"2025-05-24T14:53:07Z","abstract_excerpt":"The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, existing GSSMs operate by applying SSM modules to sequences extracted from graphs, often compromising core properties such as permutation equivariance, message-passing compatibility, and computational efficiency. In this paper, we introduce a new perspective by embedding the key principles of modern SSM computation directly into the Message-Passing Neural Network framework, resulting in a unified methodology for both st"},"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":"2505.18728","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T14:53:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f89257b9687a5de84d0790acc9b36e3021fba14b8a59767fdf7712a87e5a177","abstract_canon_sha256":"b43e017616dfdcbfc799abd1c4900cff04c081df5a865f105695536cf5797b5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:34.817894Z","signature_b64":"po007T6tUfva456vhZhX/477bw/86WZEzFK04Sf9MlUAPrqi/n1cB4etbc8rCDiTQ/Pf1uxXV8sxUhv5rVGVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e67361f846d0f1215b04fbcb9f5e42f3b9fabe29aea393394e8062011af34d70","last_reissued_at":"2026-05-27T01:05:34.817298Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:34.817298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessio Gravina, Andrea Ceni, Carola-Bibiane Schonlieb, Claudio Gallicchio, Davide Bacciu, Moshe Eliasof","submitted_at":"2025-05-24T14:53:07Z","abstract_excerpt":"The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, existing GSSMs operate by applying SSM modules to sequences extracted from graphs, often compromising core properties such as permutation equivariance, message-passing compatibility, and computational efficiency. In this paper, we introduce a new perspective by embedding the key principles of modern SSM computation directly into the Message-Passing Neural Network framework, resulting in a unified methodology for both st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18728","kind":"arxiv","version":2},"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/2505.18728/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":"2505.18728","created_at":"2026-05-27T01:05:34.817368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18728v2","created_at":"2026-05-27T01:05:34.817368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18728","created_at":"2026-05-27T01:05:34.817368+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZZWD6CG2DYS","created_at":"2026-05-27T01:05:34.817368+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZZWD6CG2DYSCWYE","created_at":"2026-05-27T01:05:34.817368+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZZWD6CG","created_at":"2026-05-27T01:05:34.817368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O","json":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O.json","graph_json":"https://pith.science/api/pith-number/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/graph.json","events_json":"https://pith.science/api/pith-number/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/events.json","paper":"https://pith.science/paper/4ZZWD6CG"},"agent_actions":{"view_html":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O","download_json":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O.json","view_paper":"https://pith.science/paper/4ZZWD6CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18728&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/action/storage_attestation","attest_author":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/action/author_attestation","sign_citation":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/action/citation_signature","submit_replication":"https://pith.science/pith/4ZZWD6CG2DYSCWYE7PFZ6XSC6O/action/replication_record"}},"created_at":"2026-05-27T01:05:34.817368+00:00","updated_at":"2026-05-27T01:05:34.817368+00:00"}