{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DOIZZO4PHT5JZC23UVEPH7WV2W","short_pith_number":"pith:DOIZZO4P","schema_version":"1.0","canonical_sha256":"1b919cbb8f3cfa9c8b5ba548f3fed5d5856c0ea71049127aa80e8e3a3f72f234","source":{"kind":"arxiv","id":"1607.00036","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Kyunghyun Cho, Sarath Chandar, Yoshua Bengio","submitted_at":"2016-06-30T20:45:12Z","abstract_excerpt":"We extend neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing a trainable memory addressing scheme. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies including both linear and nonlinear ones. We implement the D-NTM with both continuous, differentiable and discrete, non-differentiable read/write mechanisms. We investigate the mechanisms and effects of learning to read and write into a memory through experiments on "},"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":"1607.00036","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-30T20:45:12Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"7ce0cbcdb13bfecee95302a406b05bf079a1b4a1efea30c06101c8c1a38480bb","abstract_canon_sha256":"45095f93730d9a98bcc88c2a4bfa426a9afccf7358656a3c6e4e7e1bfbd55856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:32.824902Z","signature_b64":"hKqPC9zRJj1hK9rYKIiunj+4E+Gt14GYTN5Kx9BFntmS5DdYaQYQQ3ZybMf2qeLwFmfIzhp50lmmXgFCG/iYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b919cbb8f3cfa9c8b5ba548f3fed5d5856c0ea71049127aa80e8e3a3f72f234","last_reissued_at":"2026-05-18T00:48:32.824294Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:32.824294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Kyunghyun Cho, Sarath Chandar, Yoshua Bengio","submitted_at":"2016-06-30T20:45:12Z","abstract_excerpt":"We extend neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing a trainable memory addressing scheme. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies including both linear and nonlinear ones. We implement the D-NTM with both continuous, differentiable and discrete, non-differentiable read/write mechanisms. We investigate the mechanisms and effects of learning to read and write into a memory through experiments on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00036","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":"1607.00036","created_at":"2026-05-18T00:48:32.824390+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00036v2","created_at":"2026-05-18T00:48:32.824390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00036","created_at":"2026-05-18T00:48:32.824390+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOIZZO4PHT5J","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOIZZO4PHT5JZC23","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOIZZO4P","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.00820","citing_title":"Understanding Memory Modules on Learning Simple Algorithms","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":271,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W","json":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W.json","graph_json":"https://pith.science/api/pith-number/DOIZZO4PHT5JZC23UVEPH7WV2W/graph.json","events_json":"https://pith.science/api/pith-number/DOIZZO4PHT5JZC23UVEPH7WV2W/events.json","paper":"https://pith.science/paper/DOIZZO4P"},"agent_actions":{"view_html":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W","download_json":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W.json","view_paper":"https://pith.science/paper/DOIZZO4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00036&json=true","fetch_graph":"https://pith.science/api/pith-number/DOIZZO4PHT5JZC23UVEPH7WV2W/graph.json","fetch_events":"https://pith.science/api/pith-number/DOIZZO4PHT5JZC23UVEPH7WV2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W/action/storage_attestation","attest_author":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W/action/author_attestation","sign_citation":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W/action/citation_signature","submit_replication":"https://pith.science/pith/DOIZZO4PHT5JZC23UVEPH7WV2W/action/replication_record"}},"created_at":"2026-05-18T00:48:32.824390+00:00","updated_at":"2026-05-18T00:48:32.824390+00:00"}