{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDFDWJYL53ADV2FVFBTWS2DHI4","short_pith_number":"pith:UDFDWJYL","schema_version":"1.0","canonical_sha256":"a0ca3b270beec03ae8b52867696867472152a724ef2d437ed5f891dd68df38d0","source":{"kind":"arxiv","id":"2503.19466","version":3},"attestation_state":"computed","paper":{"title":"A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Passerini, Antonio Vergari, Leander Kurscheidt, Paolo Morettin, Roberto Sebastiani","submitted_at":"2025-03-25T08:58:04Z","abstract_excerpt":"In safety-critical applications, guaranteeing the satisfaction of constraints over continuous environments is crucial, e.g., an autonomous agent should never crash into obstacles or go off-road. Neural models struggle in the presence of these constraints, especially when they involve intricate algebraic relationships. To address this, we introduce a differentiable probabilistic layer that guarantees the satisfaction of non-convex algebraic constraints over continuous variables. This probabilistic algebraic layer (PAL) can be seamlessly plugged into any neural architecture and trained via maxim"},"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":"2503.19466","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T08:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"1f2fb3e389ff59b9035c59c54a9adb6d4cce69fa2cee4c03436d444aec0369d8","abstract_canon_sha256":"f1dcae60bc63989d5b08f3f66c385ae5d0815e72845e9ee47690b990883d4869"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:44.693604Z","signature_b64":"bmFibr0xlH1CE8E07yUC28ZZ5u7Ga5HazxOTy8HyfhMfGX1S55JrayOGcCYUTsazqWv9ppnrvbivm+a5KmemDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0ca3b270beec03ae8b52867696867472152a724ef2d437ed5f891dd68df38d0","last_reissued_at":"2026-07-05T11:21:44.693050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:44.693050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Passerini, Antonio Vergari, Leander Kurscheidt, Paolo Morettin, Roberto Sebastiani","submitted_at":"2025-03-25T08:58:04Z","abstract_excerpt":"In safety-critical applications, guaranteeing the satisfaction of constraints over continuous environments is crucial, e.g., an autonomous agent should never crash into obstacles or go off-road. Neural models struggle in the presence of these constraints, especially when they involve intricate algebraic relationships. To address this, we introduce a differentiable probabilistic layer that guarantees the satisfaction of non-convex algebraic constraints over continuous variables. This probabilistic algebraic layer (PAL) can be seamlessly plugged into any neural architecture and trained via maxim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19466","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/2503.19466/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":"2503.19466","created_at":"2026-07-05T11:21:44.693121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19466v3","created_at":"2026-07-05T11:21:44.693121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19466","created_at":"2026-07-05T11:21:44.693121+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDFDWJYL53AD","created_at":"2026-07-05T11:21:44.693121+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDFDWJYL53ADV2FV","created_at":"2026-07-05T11:21:44.693121+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDFDWJYL","created_at":"2026-07-05T11:21:44.693121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13845","citing_title":"Quantitative Linear Logic for Neuro-Symbolic Learning and Verification","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13845","citing_title":"Quantitative Linear Logic for Neuro-Symbolic Learning and Verification","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16714","citing_title":"How to Approximate Inference with Subtractive Mixture Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4","json":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4.json","graph_json":"https://pith.science/api/pith-number/UDFDWJYL53ADV2FVFBTWS2DHI4/graph.json","events_json":"https://pith.science/api/pith-number/UDFDWJYL53ADV2FVFBTWS2DHI4/events.json","paper":"https://pith.science/paper/UDFDWJYL"},"agent_actions":{"view_html":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4","download_json":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4.json","view_paper":"https://pith.science/paper/UDFDWJYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19466&json=true","fetch_graph":"https://pith.science/api/pith-number/UDFDWJYL53ADV2FVFBTWS2DHI4/graph.json","fetch_events":"https://pith.science/api/pith-number/UDFDWJYL53ADV2FVFBTWS2DHI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4/action/storage_attestation","attest_author":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4/action/author_attestation","sign_citation":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4/action/citation_signature","submit_replication":"https://pith.science/pith/UDFDWJYL53ADV2FVFBTWS2DHI4/action/replication_record"}},"created_at":"2026-07-05T11:21:44.693121+00:00","updated_at":"2026-07-05T11:21:44.693121+00:00"}