{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2UWWNQEVPG22REU2CTJOPKI6T","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"977fb0e0cd5da269ac2b42ae4fa5f6021aa86b6eb5b09a47d875c13d9d852610","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T23:45:53Z","title_canon_sha256":"7998a499fdaee61b0f0daae0f568c1198780cefdce8d75fd91fd89c40f803d3e"},"schema_version":"1.0","source":{"id":"2401.09651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09651","created_at":"2026-07-05T08:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09651v2","created_at":"2026-07-05T08:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09651","created_at":"2026-07-05T08:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"F2UWWNQEVPG2","created_at":"2026-07-05T08:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"F2UWWNQEVPG22REU","created_at":"2026-07-05T08:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"F2UWWNQE","created_at":"2026-07-05T08:26:43Z"}],"graph_snapshots":[{"event_id":"sha256:640ea8b7ccf75d70dc3a09c880d4c15c8efca33362849de8c7800c7e0b47ce44","target":"graph","created_at":"2026-07-05T08:26:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.09651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changyu Gao, Charles Dickens, Connor Pryor, Lise Getoor, Stephen Wright","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T23:45:53Z","title":"Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09651","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:43cee8f688bf3d47c24e5af4656e98d6ccda0511a4d02a77b0a983181c362471","target":"record","created_at":"2026-07-05T08:26:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"977fb0e0cd5da269ac2b42ae4fa5f6021aa86b6eb5b09a47d875c13d9d852610","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T23:45:53Z","title_canon_sha256":"7998a499fdaee61b0f0daae0f568c1198780cefdce8d75fd91fd89c40f803d3e"},"schema_version":"1.0","source":{"id":"2401.09651","kind":"arxiv","version":2}},"canonical_sha256":"2ea96b3604abcdad4494d0a6973d48f4c5c13e42074cb1c8e4c11616a8918093","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ea96b3604abcdad4494d0a6973d48f4c5c13e42074cb1c8e4c11616a8918093","first_computed_at":"2026-07-05T08:26:43.463606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:43.463606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GR4mNBx0IjpzEeHiM5uyDHCuUSn/NrOqEEj3cmmH5GfT5e1KyhDGdMgBMNpowVUIdo4i8TyVATQOiHTpd2SgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:43.464106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43cee8f688bf3d47c24e5af4656e98d6ccda0511a4d02a77b0a983181c362471","sha256:640ea8b7ccf75d70dc3a09c880d4c15c8efca33362849de8c7800c7e0b47ce44"],"state_sha256":"9e8dcd4ff45083920d3c3a9b6ffd347971952efc15145f9187c83651f2a94fb0"}