{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R3AGOSIOQWSLQN3KGRJNT2QQJR","short_pith_number":"pith:R3AGOSIO","schema_version":"1.0","canonical_sha256":"8ec067490e85a4b8376a3452d9ea104c58701ea1084d20e01f7e7bc98fafa06d","source":{"kind":"arxiv","id":"2607.09399","version":1},"attestation_state":"computed","paper":{"title":"Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lars Keuninckx, Matthias Hartmann, Piet Wambacq, Werner van Leekwijck, Wout Mommen","submitted_at":"2026-07-10T13:24:26Z","abstract_excerpt":"We introduce a novel method for both partial and full optimization of the connections in deep differentiable logic gate networks (LGNs) and lookup table networks (LUTNs). Our training method utilizes a probability distribution over a set of connections per gate/lookup table (LUT) input pin, selecting the connection with highest merit, all whilst the optimal gate types or LUT-entries are learned in parallel. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST Handwritten Digits and Fashion-MNIST benchmarks, while requiring only a fraction "},"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":"2607.09399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T13:24:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1417ecdc71fc22ae1c44236580cbd793a18309d5a5edd312e970b265a1ef4dfb","abstract_canon_sha256":"950d636ea3ff37a8581fd4d6f5394618d02f55158203e25ed96af1d1a6ea6355"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:09.846208Z","signature_b64":"APvR8F+X1yXRT2/SyZxVBuFid9TstJturicoNqmP/EdtkQxecbnvHkMIwd4KPcQqpukVC9BFiuVBJjwosJ94Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec067490e85a4b8376a3452d9ea104c58701ea1084d20e01f7e7bc98fafa06d","last_reissued_at":"2026-07-13T01:19:09.844782Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:09.844782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lars Keuninckx, Matthias Hartmann, Piet Wambacq, Werner van Leekwijck, Wout Mommen","submitted_at":"2026-07-10T13:24:26Z","abstract_excerpt":"We introduce a novel method for both partial and full optimization of the connections in deep differentiable logic gate networks (LGNs) and lookup table networks (LUTNs). Our training method utilizes a probability distribution over a set of connections per gate/lookup table (LUT) input pin, selecting the connection with highest merit, all whilst the optimal gate types or LUT-entries are learned in parallel. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST Handwritten Digits and Fashion-MNIST benchmarks, while requiring only a fraction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09399","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/2607.09399/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":"2607.09399","created_at":"2026-07-13T01:19:09.845526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09399v1","created_at":"2026-07-13T01:19:09.845526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09399","created_at":"2026-07-13T01:19:09.845526+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3AGOSIOQWSL","created_at":"2026-07-13T01:19:09.845526+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3AGOSIOQWSLQN3K","created_at":"2026-07-13T01:19:09.845526+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3AGOSIO","created_at":"2026-07-13T01:19:09.845526+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/R3AGOSIOQWSLQN3KGRJNT2QQJR","json":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR.json","graph_json":"https://pith.science/api/pith-number/R3AGOSIOQWSLQN3KGRJNT2QQJR/graph.json","events_json":"https://pith.science/api/pith-number/R3AGOSIOQWSLQN3KGRJNT2QQJR/events.json","paper":"https://pith.science/paper/R3AGOSIO"},"agent_actions":{"view_html":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR","download_json":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR.json","view_paper":"https://pith.science/paper/R3AGOSIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09399&json=true","fetch_graph":"https://pith.science/api/pith-number/R3AGOSIOQWSLQN3KGRJNT2QQJR/graph.json","fetch_events":"https://pith.science/api/pith-number/R3AGOSIOQWSLQN3KGRJNT2QQJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR/action/storage_attestation","attest_author":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR/action/author_attestation","sign_citation":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR/action/citation_signature","submit_replication":"https://pith.science/pith/R3AGOSIOQWSLQN3KGRJNT2QQJR/action/replication_record"}},"created_at":"2026-07-13T01:19:09.845526+00:00","updated_at":"2026-07-13T01:19:09.845526+00:00"}