{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F2UWWNQEVPG22REU2CTJOPKI6T","short_pith_number":"pith:F2UWWNQE","schema_version":"1.0","canonical_sha256":"2ea96b3604abcdad4494d0a6973d48f4c5c13e42074cb1c8e4c11616a8918093","source":{"kind":"arxiv","id":"2401.09651","version":2},"attestation_state":"computed","paper":{"title":"Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Changyu Gao, Charles Dickens, Connor Pryor, Lise Getoor, Stephen Wright","submitted_at":"2024-01-17T23:45:53Z","abstract_excerpt":"We leverage convex and bilevel optimization techniques to develop a general gradient-based parameter learning framework for neural-symbolic (NeSy) systems. We demonstrate our framework with NeuPSL, a state-of-the-art NeSy architecture. To achieve this, we propose a smooth primal and dual formulation of NeuPSL inference and show learning gradients are functions of the optimal dual variables. Additionally, we develop a dual block coordinate descent algorithm for the new formulation that naturally exploits warm-starts. This leads to over 100x learning runtime improvements over the current best Ne"},"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":"2401.09651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T23:45:53Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"7998a499fdaee61b0f0daae0f568c1198780cefdce8d75fd91fd89c40f803d3e","abstract_canon_sha256":"977fb0e0cd5da269ac2b42ae4fa5f6021aa86b6eb5b09a47d875c13d9d852610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:43.464106Z","signature_b64":"GR4mNBx0IjpzEeHiM5uyDHCuUSn/NrOqEEj3cmmH5GfT5e1KyhDGdMgBMNpowVUIdo4i8TyVATQOiHTpd2SgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea96b3604abcdad4494d0a6973d48f4c5c13e42074cb1c8e4c11616a8918093","last_reissued_at":"2026-07-05T08:26:43.463606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:43.463606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Changyu Gao, Charles Dickens, Connor Pryor, Lise Getoor, Stephen Wright","submitted_at":"2024-01-17T23:45:53Z","abstract_excerpt":"We leverage convex and bilevel optimization techniques to develop a general gradient-based parameter learning framework for neural-symbolic (NeSy) systems. We demonstrate our framework with NeuPSL, a state-of-the-art NeSy architecture. To achieve this, we propose a smooth primal and dual formulation of NeuPSL inference and show learning gradients are functions of the optimal dual variables. Additionally, we develop a dual block coordinate descent algorithm for the new formulation that naturally exploits warm-starts. This leads to over 100x learning runtime improvements over the current best Ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09651","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/2401.09651/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":"2401.09651","created_at":"2026-07-05T08:26:43.463668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09651v2","created_at":"2026-07-05T08:26:43.463668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09651","created_at":"2026-07-05T08:26:43.463668+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2UWWNQEVPG2","created_at":"2026-07-05T08:26:43.463668+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2UWWNQEVPG22REU","created_at":"2026-07-05T08:26:43.463668+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2UWWNQE","created_at":"2026-07-05T08:26:43.463668+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/F2UWWNQEVPG22REU2CTJOPKI6T","json":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T.json","graph_json":"https://pith.science/api/pith-number/F2UWWNQEVPG22REU2CTJOPKI6T/graph.json","events_json":"https://pith.science/api/pith-number/F2UWWNQEVPG22REU2CTJOPKI6T/events.json","paper":"https://pith.science/paper/F2UWWNQE"},"agent_actions":{"view_html":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T","download_json":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T.json","view_paper":"https://pith.science/paper/F2UWWNQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09651&json=true","fetch_graph":"https://pith.science/api/pith-number/F2UWWNQEVPG22REU2CTJOPKI6T/graph.json","fetch_events":"https://pith.science/api/pith-number/F2UWWNQEVPG22REU2CTJOPKI6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T/action/storage_attestation","attest_author":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T/action/author_attestation","sign_citation":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T/action/citation_signature","submit_replication":"https://pith.science/pith/F2UWWNQEVPG22REU2CTJOPKI6T/action/replication_record"}},"created_at":"2026-07-05T08:26:43.463668+00:00","updated_at":"2026-07-05T08:26:43.463668+00:00"}