{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EKY753PVOJG4LSX4E2VKRCQ4ZX","short_pith_number":"pith:EKY753PV","schema_version":"1.0","canonical_sha256":"22b1feedf5724dc5cafc26aaa88a1ccde8725d202c3dd5e4f5e30c82488a3c21","source":{"kind":"arxiv","id":"1808.00508","version":1},"attestation_state":"computed","paper":{"title":"Neural Arithmetic Logic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Andrew Trask, Chris Dyer, Felix Hill, Jack Rae, Phil Blunsom, Scott Reed","submitted_at":"2018-08-01T18:58:53Z","abstract_excerpt":"Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates. We call this module a neural arithmetic logic unit (NALU), by analogy to the arithmetic logic unit in traditional processors. Experiments show that NALU-enhanced neural networks can learn to t"},"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":"1808.00508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-08-01T18:58:53Z","cross_cats_sorted":[],"title_canon_sha256":"f0c9edc4247c43d9d2f3fe3f257d8cbae657452b6e6fd378c1c5fb4c66e20758","abstract_canon_sha256":"ada6201558491c4133aa0726a1db999d820783b5d48a4d80ecf9448f851f7bcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:05.131504Z","signature_b64":"LQ+WJj+CBngDFWHaumX8qu26ndpJYJFv0OjulirjvZCpf+EhuTF9d1/DkIkL90ylmn+fWny3Q/tfbOPM8JRvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22b1feedf5724dc5cafc26aaa88a1ccde8725d202c3dd5e4f5e30c82488a3c21","last_reissued_at":"2026-05-18T00:09:05.130801Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:05.130801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Arithmetic Logic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Andrew Trask, Chris Dyer, Felix Hill, Jack Rae, Phil Blunsom, Scott Reed","submitted_at":"2018-08-01T18:58:53Z","abstract_excerpt":"Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates. We call this module a neural arithmetic logic unit (NALU), by analogy to the arithmetic logic unit in traditional processors. Experiments show that NALU-enhanced neural networks can learn to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00508","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":""},"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":"1808.00508","created_at":"2026-05-18T00:09:05.130911+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.00508v1","created_at":"2026-05-18T00:09:05.130911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00508","created_at":"2026-05-18T00:09:05.130911+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKY753PVOJG4","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKY753PVOJG4LSX4","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKY753PV","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX","json":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX.json","graph_json":"https://pith.science/api/pith-number/EKY753PVOJG4LSX4E2VKRCQ4ZX/graph.json","events_json":"https://pith.science/api/pith-number/EKY753PVOJG4LSX4E2VKRCQ4ZX/events.json","paper":"https://pith.science/paper/EKY753PV"},"agent_actions":{"view_html":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX","download_json":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX.json","view_paper":"https://pith.science/paper/EKY753PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.00508&json=true","fetch_graph":"https://pith.science/api/pith-number/EKY753PVOJG4LSX4E2VKRCQ4ZX/graph.json","fetch_events":"https://pith.science/api/pith-number/EKY753PVOJG4LSX4E2VKRCQ4ZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX/action/storage_attestation","attest_author":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX/action/author_attestation","sign_citation":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX/action/citation_signature","submit_replication":"https://pith.science/pith/EKY753PVOJG4LSX4E2VKRCQ4ZX/action/replication_record"}},"created_at":"2026-05-18T00:09:05.130911+00:00","updated_at":"2026-05-18T00:09:05.130911+00:00"}