{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A5PLWQVIV6M3SQWSXLXI5PU43V","short_pith_number":"pith:A5PLWQVI","schema_version":"1.0","canonical_sha256":"075ebb42a8af99b942d2baee8ebe9cdd478d6c8820160564cf908fb22c2ffb6a","source":{"kind":"arxiv","id":"2508.06097","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Deep Differentiable Logic Gate Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Plesner, Roger Wattenhofer, Simon B\\\"uhrer, Till Aczel","submitted_at":"2025-08-08T07:49:38Z","abstract_excerpt":"While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementation of Recurrent Deep Differentiable Logic Gate Networks (RDDLGN), combining Boolean operations with recurrent architectures for sequence-to-sequence learning.\n  Evaluated on WMT'14 English-German translation, RDDLGN achieves 5.00 BLEU and 30.9\\% accuracy during training, approaching GRU performance (5.41 BLEU) and graceful degradation (4.39 BLEU) during inference. This work establishes recurrent logic-based neural co"},"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":"2508.06097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-08T07:49:38Z","cross_cats_sorted":[],"title_canon_sha256":"1e46eafe5303a3a34138e2b938b2c4a2951aac767b5d2aa72bfe1bded2a1b039","abstract_canon_sha256":"263e53bdcc05287c365fa276f701607e5c3a8e0c9f0f1727c67de46c5ae00cbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:49.595154Z","signature_b64":"Ck28U8mltrKx3QP1uG1xAqGFHd5HT6MeZ0Xy2CnTAMsXqAuOlzFTtcEDGIt8BM8GBl6hGYJDbyfQ9q6D0wiNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"075ebb42a8af99b942d2baee8ebe9cdd478d6c8820160564cf908fb22c2ffb6a","last_reissued_at":"2026-07-05T11:50:49.594540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:49.594540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Deep Differentiable Logic Gate Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Plesner, Roger Wattenhofer, Simon B\\\"uhrer, Till Aczel","submitted_at":"2025-08-08T07:49:38Z","abstract_excerpt":"While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementation of Recurrent Deep Differentiable Logic Gate Networks (RDDLGN), combining Boolean operations with recurrent architectures for sequence-to-sequence learning.\n  Evaluated on WMT'14 English-German translation, RDDLGN achieves 5.00 BLEU and 30.9\\% accuracy during training, approaching GRU performance (5.41 BLEU) and graceful degradation (4.39 BLEU) during inference. This work establishes recurrent logic-based neural co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06097","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/2508.06097/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":"2508.06097","created_at":"2026-07-05T11:50:49.594639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06097v1","created_at":"2026-07-05T11:50:49.594639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06097","created_at":"2026-07-05T11:50:49.594639+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5PLWQVIV6M3","created_at":"2026-07-05T11:50:49.594639+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5PLWQVIV6M3SQWS","created_at":"2026-07-05T11:50:49.594639+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5PLWQVI","created_at":"2026-07-05T11:50:49.594639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24649","citing_title":"On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V","json":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V.json","graph_json":"https://pith.science/api/pith-number/A5PLWQVIV6M3SQWSXLXI5PU43V/graph.json","events_json":"https://pith.science/api/pith-number/A5PLWQVIV6M3SQWSXLXI5PU43V/events.json","paper":"https://pith.science/paper/A5PLWQVI"},"agent_actions":{"view_html":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V","download_json":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V.json","view_paper":"https://pith.science/paper/A5PLWQVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06097&json=true","fetch_graph":"https://pith.science/api/pith-number/A5PLWQVIV6M3SQWSXLXI5PU43V/graph.json","fetch_events":"https://pith.science/api/pith-number/A5PLWQVIV6M3SQWSXLXI5PU43V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V/action/storage_attestation","attest_author":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V/action/author_attestation","sign_citation":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V/action/citation_signature","submit_replication":"https://pith.science/pith/A5PLWQVIV6M3SQWSXLXI5PU43V/action/replication_record"}},"created_at":"2026-07-05T11:50:49.594639+00:00","updated_at":"2026-07-05T11:50:49.594639+00:00"}