{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:23NXLZJNQV3RGEUMSPN7JSVJFG","short_pith_number":"pith:23NXLZJN","schema_version":"1.0","canonical_sha256":"d6db75e52d857713128c93dbf4caa9298cae4d99262899385a4d2f859a155707","source":{"kind":"arxiv","id":"1611.00736","version":2},"attestation_state":"computed","paper":{"title":"Extensions and Limitations of the Neural GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Eric Price, Ilya Sutskever, Wojciech Zaremba","submitted_at":"2016-11-02T19:18:17Z","abstract_excerpt":"The Neural GPU is a recent model that can learn algorithms such as multi-digit binary addition and binary multiplication in a way that generalizes to inputs of arbitrary length. We show that there are two simple ways of improving the performance of the Neural GPU: by carefully designing a curriculum, and by increasing model size. The latter requires a memory efficient implementation, as a naive implementation of the Neural GPU is memory intensive. We find that these techniques increase the set of algorithmic problems that can be solved by the Neural GPU: we have been able to learn to perform a"},"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":"1611.00736","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-02T19:18:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ad64b50aef66c3f4f3ba5c6651916add301281932b1ab33e17c5b7ca9ed9167","abstract_canon_sha256":"81d90cef5e6817a6e3e916e7ce9d31a217d1456efe8c7efa81fb6a99a2e7e6ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:05.164248Z","signature_b64":"aORvZU4X+fYw3h1z1uyFgmXZy6RtfWpxpiEe7+5By6va7xHOIu4P5WlnFiEsLY6KxW0SXQoehM74cRFm7fX7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6db75e52d857713128c93dbf4caa9298cae4d99262899385a4d2f859a155707","last_reissued_at":"2026-05-18T01:00:05.163693Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:05.163693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extensions and Limitations of the Neural GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Eric Price, Ilya Sutskever, Wojciech Zaremba","submitted_at":"2016-11-02T19:18:17Z","abstract_excerpt":"The Neural GPU is a recent model that can learn algorithms such as multi-digit binary addition and binary multiplication in a way that generalizes to inputs of arbitrary length. We show that there are two simple ways of improving the performance of the Neural GPU: by carefully designing a curriculum, and by increasing model size. The latter requires a memory efficient implementation, as a naive implementation of the Neural GPU is memory intensive. We find that these techniques increase the set of algorithmic problems that can be solved by the Neural GPU: we have been able to learn to perform a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00736","kind":"arxiv","version":2},"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":"1611.00736","created_at":"2026-05-18T01:00:05.163769+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00736v2","created_at":"2026-05-18T01:00:05.163769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00736","created_at":"2026-05-18T01:00:05.163769+00:00"},{"alias_kind":"pith_short_12","alias_value":"23NXLZJNQV3R","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"23NXLZJNQV3RGEUM","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"23NXLZJN","created_at":"2026-05-18T12:29:52.810259+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/23NXLZJNQV3RGEUMSPN7JSVJFG","json":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG.json","graph_json":"https://pith.science/api/pith-number/23NXLZJNQV3RGEUMSPN7JSVJFG/graph.json","events_json":"https://pith.science/api/pith-number/23NXLZJNQV3RGEUMSPN7JSVJFG/events.json","paper":"https://pith.science/paper/23NXLZJN"},"agent_actions":{"view_html":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG","download_json":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG.json","view_paper":"https://pith.science/paper/23NXLZJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00736&json=true","fetch_graph":"https://pith.science/api/pith-number/23NXLZJNQV3RGEUMSPN7JSVJFG/graph.json","fetch_events":"https://pith.science/api/pith-number/23NXLZJNQV3RGEUMSPN7JSVJFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG/action/storage_attestation","attest_author":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG/action/author_attestation","sign_citation":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG/action/citation_signature","submit_replication":"https://pith.science/pith/23NXLZJNQV3RGEUMSPN7JSVJFG/action/replication_record"}},"created_at":"2026-05-18T01:00:05.163769+00:00","updated_at":"2026-05-18T01:00:05.163769+00:00"}