{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SURUM3K5FF3VHHA4RD3SA25TQ3","short_pith_number":"pith:SURUM3K5","schema_version":"1.0","canonical_sha256":"9523466d5d2977539c1c88f7206bb386cf75734db2c9b3f909d946572ae4497f","source":{"kind":"arxiv","id":"2505.23615","version":1},"attestation_state":"computed","paper":{"title":"Learning Interpretable Differentiable Logic Networks for Tabular Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Yue, Niraj K. Jha","submitted_at":"2025-05-29T16:24:18Z","abstract_excerpt":"Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed Differentiable Logic Networks (DLNs) to address these issues for tabular classification based on relaxing discrete logic into a differentiable form, thereby enabling gradient-based learning of networks built from binary logic operations. DLNs offer interpretable reasoning and substantially lower inference cost.\n  We extend the DLN framework to supervised tabular r"},"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":"2505.23615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T16:24:18Z","cross_cats_sorted":[],"title_canon_sha256":"660f35c0380cfe4683a7e8479650cf02e847a8faff3522b56b9ae44689a772b5","abstract_canon_sha256":"d3cf45a9b234e07cd5e042c2fc6b690475da6d73890d024d27582557aefe47e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:04.769458Z","signature_b64":"b7xjDN70UWNJzbyN8mEbA/59D6QuqqzgNwQCLRNdhnefV6JgI1ghskpi0N9XMWW1LCnkTf96d2ThBkDyD0o/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9523466d5d2977539c1c88f7206bb386cf75734db2c9b3f909d946572ae4497f","last_reissued_at":"2026-07-05T11:12:04.768731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:04.768731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Interpretable Differentiable Logic Networks for Tabular Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Yue, Niraj K. Jha","submitted_at":"2025-05-29T16:24:18Z","abstract_excerpt":"Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed Differentiable Logic Networks (DLNs) to address these issues for tabular classification based on relaxing discrete logic into a differentiable form, thereby enabling gradient-based learning of networks built from binary logic operations. DLNs offer interpretable reasoning and substantially lower inference cost.\n  We extend the DLN framework to supervised tabular r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23615","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/2505.23615/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":"2505.23615","created_at":"2026-07-05T11:12:04.768828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23615v1","created_at":"2026-07-05T11:12:04.768828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23615","created_at":"2026-07-05T11:12:04.768828+00:00"},{"alias_kind":"pith_short_12","alias_value":"SURUM3K5FF3V","created_at":"2026-07-05T11:12:04.768828+00:00"},{"alias_kind":"pith_short_16","alias_value":"SURUM3K5FF3VHHA4","created_at":"2026-07-05T11:12:04.768828+00:00"},{"alias_kind":"pith_short_8","alias_value":"SURUM3K5","created_at":"2026-07-05T11:12:04.768828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.12340","citing_title":"LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3","json":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3.json","graph_json":"https://pith.science/api/pith-number/SURUM3K5FF3VHHA4RD3SA25TQ3/graph.json","events_json":"https://pith.science/api/pith-number/SURUM3K5FF3VHHA4RD3SA25TQ3/events.json","paper":"https://pith.science/paper/SURUM3K5"},"agent_actions":{"view_html":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3","download_json":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3.json","view_paper":"https://pith.science/paper/SURUM3K5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23615&json=true","fetch_graph":"https://pith.science/api/pith-number/SURUM3K5FF3VHHA4RD3SA25TQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/SURUM3K5FF3VHHA4RD3SA25TQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3/action/storage_attestation","attest_author":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3/action/author_attestation","sign_citation":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3/action/citation_signature","submit_replication":"https://pith.science/pith/SURUM3K5FF3VHHA4RD3SA25TQ3/action/replication_record"}},"created_at":"2026-07-05T11:12:04.768828+00:00","updated_at":"2026-07-05T11:12:04.768828+00:00"}