{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DFNYPMUO4IFQMEPHPLGFWZK6XJ","short_pith_number":"pith:DFNYPMUO","schema_version":"1.0","canonical_sha256":"195b87b28ee20b0611e77acc5b655eba47b5cf33a0c58f36295bb282b5bed980","source":{"kind":"arxiv","id":"2507.21873","version":1},"attestation_state":"computed","paper":{"title":"A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrea Passerini, Kim G. Larsen, Manfred Jaeger, Raffaele Pojer","submitted_at":"2025-07-29T14:43:25Z","abstract_excerpt":"Graph neural networks (GNNs) excel at predictive tasks on graph-structured data but often lack the ability to incorporate symbolic domain knowledge and perform general reasoning. Relational Bayesian Networks (RBNs), in contrast, enable fully generative probabilistic modeling over graph-like structures and support rich symbolic knowledge and probabilistic inference. This paper presents a neuro-symbolic framework that seamlessly integrates GNNs into RBNs, combining the learning strength of GNNs with the flexible reasoning capabilities of RBNs.\n  We develop two implementations of this integration"},"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":"2507.21873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T14:43:25Z","cross_cats_sorted":[],"title_canon_sha256":"aa5a2de952c093b83f44132da75867dd229acfbde01281678fb960e690135397","abstract_canon_sha256":"3fc20047b1a6c12058900040a63f10f0fea9e2c1ef13c21b33a535a8a5b02b40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:09.173645Z","signature_b64":"RA7o9H92MTQ7s3CBOfzHwyJPff7fbmG3qGeDgegN1GWzLQS7u6ws5yLfcWB7idTgjYcFPqVuQyfaR/gl6X26Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"195b87b28ee20b0611e77acc5b655eba47b5cf33a0c58f36295bb282b5bed980","last_reissued_at":"2026-07-05T11:45:09.173055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:09.173055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrea Passerini, Kim G. Larsen, Manfred Jaeger, Raffaele Pojer","submitted_at":"2025-07-29T14:43:25Z","abstract_excerpt":"Graph neural networks (GNNs) excel at predictive tasks on graph-structured data but often lack the ability to incorporate symbolic domain knowledge and perform general reasoning. Relational Bayesian Networks (RBNs), in contrast, enable fully generative probabilistic modeling over graph-like structures and support rich symbolic knowledge and probabilistic inference. This paper presents a neuro-symbolic framework that seamlessly integrates GNNs into RBNs, combining the learning strength of GNNs with the flexible reasoning capabilities of RBNs.\n  We develop two implementations of this integration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21873","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/2507.21873/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":"2507.21873","created_at":"2026-07-05T11:45:09.173117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21873v1","created_at":"2026-07-05T11:45:09.173117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21873","created_at":"2026-07-05T11:45:09.173117+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFNYPMUO4IFQ","created_at":"2026-07-05T11:45:09.173117+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFNYPMUO4IFQMEPH","created_at":"2026-07-05T11:45:09.173117+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFNYPMUO","created_at":"2026-07-05T11:45:09.173117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.10485","citing_title":"Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ","json":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ.json","graph_json":"https://pith.science/api/pith-number/DFNYPMUO4IFQMEPHPLGFWZK6XJ/graph.json","events_json":"https://pith.science/api/pith-number/DFNYPMUO4IFQMEPHPLGFWZK6XJ/events.json","paper":"https://pith.science/paper/DFNYPMUO"},"agent_actions":{"view_html":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ","download_json":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ.json","view_paper":"https://pith.science/paper/DFNYPMUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21873&json=true","fetch_graph":"https://pith.science/api/pith-number/DFNYPMUO4IFQMEPHPLGFWZK6XJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DFNYPMUO4IFQMEPHPLGFWZK6XJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ/action/storage_attestation","attest_author":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ/action/author_attestation","sign_citation":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ/action/citation_signature","submit_replication":"https://pith.science/pith/DFNYPMUO4IFQMEPHPLGFWZK6XJ/action/replication_record"}},"created_at":"2026-07-05T11:45:09.173117+00:00","updated_at":"2026-07-05T11:45:09.173117+00:00"}