{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4VHWS3IVXZGK4SE5GTOS7F66Q2","short_pith_number":"pith:4VHWS3IV","schema_version":"1.0","canonical_sha256":"e54f696d15be4cae489d34dd2f97de86a37271f7e4096ca768c551e7045301da","source":{"kind":"arxiv","id":"1511.06392","version":3},"attestation_state":"computed","paper":{"title":"Neural Random-Access Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, Karol Kurach, Marcin Andrychowicz","submitted_at":"2015-11-19T21:36:28Z","abstract_excerpt":"In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine. It can manipulate and dereference pointers to an external variable-size random-access memory. The model is trained from pure input-output examples using backpropagation.\n  We evaluate the new model on a number of simple algorithmic tasks whose solutions require pointer manipulation and dereferencing. Our results show that the proposed model can learn to solve algorithmic tasks of such type and is capable of operating on simple data structures like linked-lists and binary trees. For "},"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":"1511.06392","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T21:36:28Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"045811833a6ca3a484c5b6511e535fba2512328d7e92cd6c6ac3ce3207b0265e","abstract_canon_sha256":"6520da47edaca0d6e85a3474e6436a840361a0a6717276c3bc4bd7000e013aca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:00.783085Z","signature_b64":"OniSQcskUQ4BPTE667dfZpMX2VXO7Xs3dsvL8OpGwmBlxAhnIgO/RzDaONsdpbvDzXAu9OKfyabVd1NLRa3IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e54f696d15be4cae489d34dd2f97de86a37271f7e4096ca768c551e7045301da","last_reissued_at":"2026-05-18T01:21:00.782644Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:00.782644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Random-Access Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, Karol Kurach, Marcin Andrychowicz","submitted_at":"2015-11-19T21:36:28Z","abstract_excerpt":"In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine. It can manipulate and dereference pointers to an external variable-size random-access memory. The model is trained from pure input-output examples using backpropagation.\n  We evaluate the new model on a number of simple algorithmic tasks whose solutions require pointer manipulation and dereferencing. Our results show that the proposed model can learn to solve algorithmic tasks of such type and is capable of operating on simple data structures like linked-lists and binary trees. For "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06392","kind":"arxiv","version":3},"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":"1511.06392","created_at":"2026-05-18T01:21:00.782722+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06392v3","created_at":"2026-05-18T01:21:00.782722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06392","created_at":"2026-05-18T01:21:00.782722+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VHWS3IVXZGK","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VHWS3IVXZGK4SE5","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VHWS3IV","created_at":"2026-05-18T12:29:05.191682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12087","citing_title":"ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18907","citing_title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2","json":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2.json","graph_json":"https://pith.science/api/pith-number/4VHWS3IVXZGK4SE5GTOS7F66Q2/graph.json","events_json":"https://pith.science/api/pith-number/4VHWS3IVXZGK4SE5GTOS7F66Q2/events.json","paper":"https://pith.science/paper/4VHWS3IV"},"agent_actions":{"view_html":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2","download_json":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2.json","view_paper":"https://pith.science/paper/4VHWS3IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06392&json=true","fetch_graph":"https://pith.science/api/pith-number/4VHWS3IVXZGK4SE5GTOS7F66Q2/graph.json","fetch_events":"https://pith.science/api/pith-number/4VHWS3IVXZGK4SE5GTOS7F66Q2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2/action/storage_attestation","attest_author":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2/action/author_attestation","sign_citation":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2/action/citation_signature","submit_replication":"https://pith.science/pith/4VHWS3IVXZGK4SE5GTOS7F66Q2/action/replication_record"}},"created_at":"2026-05-18T01:21:00.782722+00:00","updated_at":"2026-05-18T01:21:00.782722+00:00"}