{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMWGC72CW2CFFGUD6IBMS5PM3Z","short_pith_number":"pith:IMWGC72C","schema_version":"1.0","canonical_sha256":"432c617f42b684529a83f202c975ecde5e6d8964242e9dedff0219756d250ea8","source":{"kind":"arxiv","id":"2507.11127","version":1},"attestation_state":"computed","paper":{"title":"Defining neurosymbolic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lennert De Smet, Luc De Raedt","submitted_at":"2025-07-15T09:23:22Z","abstract_excerpt":"Neurosymbolic AI focuses on integrating learning and reasoning, in particular, on unifying logical and neural representations. Despite the existence of an alphabet soup of neurosymbolic AI systems, the field is lacking a generally accepted formal definition of what neurosymbolic models and inference really are. We introduce a formal definition for neurosymbolic AI that makes abstraction of its key ingredients. More specifically, we define neurosymbolic inference as the computation of an integral over a product of a logical and a belief function. We show that our neurosymbolic AI definition mak"},"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":"2507.11127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-15T09:23:22Z","cross_cats_sorted":[],"title_canon_sha256":"f43df7fe9bf429693d7930d6e3be0e3618c06828433fe40bc38b11cd1c0f0a44","abstract_canon_sha256":"ff4894331007c3b1b8c60261e64294dc7feb150e0b742667fab862d186e5c1e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:32.900713Z","signature_b64":"ZZ1LSwbLfOTK1WYSJqmjoYooyvEeBdNK56UwnoWBbAoyggZkZ/UKMziYt/yunH7WWj0tpVOR6N3OOpiRoHZjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"432c617f42b684529a83f202c975ecde5e6d8964242e9dedff0219756d250ea8","last_reissued_at":"2026-07-05T11:37:32.900173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:32.900173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defining neurosymbolic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lennert De Smet, Luc De Raedt","submitted_at":"2025-07-15T09:23:22Z","abstract_excerpt":"Neurosymbolic AI focuses on integrating learning and reasoning, in particular, on unifying logical and neural representations. Despite the existence of an alphabet soup of neurosymbolic AI systems, the field is lacking a generally accepted formal definition of what neurosymbolic models and inference really are. We introduce a formal definition for neurosymbolic AI that makes abstraction of its key ingredients. More specifically, we define neurosymbolic inference as the computation of an integral over a product of a logical and a belief function. We show that our neurosymbolic AI definition mak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11127","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/2507.11127/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":"2507.11127","created_at":"2026-07-05T11:37:32.900237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11127v1","created_at":"2026-07-05T11:37:32.900237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11127","created_at":"2026-07-05T11:37:32.900237+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMWGC72CW2CF","created_at":"2026-07-05T11:37:32.900237+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMWGC72CW2CFFGUD","created_at":"2026-07-05T11:37:32.900237+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMWGC72C","created_at":"2026-07-05T11:37:32.900237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11113","citing_title":"A Neurosymbolic Prolog Skill for LLM-Driven Service Placement","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10279","citing_title":"DeepLog: A Software Framework for Modular Neurosymbolic AI","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17967","citing_title":"A Sugeno Integral View of Binarized Neural Network Inference","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z","json":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z.json","graph_json":"https://pith.science/api/pith-number/IMWGC72CW2CFFGUD6IBMS5PM3Z/graph.json","events_json":"https://pith.science/api/pith-number/IMWGC72CW2CFFGUD6IBMS5PM3Z/events.json","paper":"https://pith.science/paper/IMWGC72C"},"agent_actions":{"view_html":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z","download_json":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z.json","view_paper":"https://pith.science/paper/IMWGC72C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11127&json=true","fetch_graph":"https://pith.science/api/pith-number/IMWGC72CW2CFFGUD6IBMS5PM3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/IMWGC72CW2CFFGUD6IBMS5PM3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z/action/storage_attestation","attest_author":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z/action/author_attestation","sign_citation":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z/action/citation_signature","submit_replication":"https://pith.science/pith/IMWGC72CW2CFFGUD6IBMS5PM3Z/action/replication_record"}},"created_at":"2026-07-05T11:37:32.900237+00:00","updated_at":"2026-07-05T11:37:32.900237+00:00"}