{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:S3ZGCQPELGJRR7KFYK6QH476AV","short_pith_number":"pith:S3ZGCQPE","schema_version":"1.0","canonical_sha256":"96f26141e4599318fd45c2bd03f3fe0566fb26e7289be2ab581413bfeef4724b","source":{"kind":"arxiv","id":"1505.00521","version":3},"attestation_state":"computed","paper":{"title":"Reinforcement Learning Neural Turing Machines - Revised","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, Wojciech Zaremba","submitted_at":"2015-05-04T04:14:54Z","abstract_excerpt":"The Neural Turing Machine (NTM) is more expressive than all previously considered models because of its external memory. It can be viewed as a broader effort to use abstract external Interfaces and to learn a parametric model that interacts with them.\n  The capabilities of a model can be extended by providing it with proper Interfaces that interact with the world. These external Interfaces include memory, a database, a search engine, or a piece of software such as a theorem verifier. Some of these Interfaces are provided by the developers of the model. However, many important existing Interfac"},"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":"1505.00521","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-05-04T04:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"d6ccc37c97d435b9e252b1f28dee782e308b240017cb889a2ef24cbe03888af6","abstract_canon_sha256":"9329f68a37e5ddffba8f0ad3a9eb5175dceee34affa5ba901d599401e9a68cc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:04.053591Z","signature_b64":"Nbop6NsmiiH27i6osuITD1BwSiJzmcDP2E2Zh8kI80CooUubJMzbFB13sjkpq0wKbOztr3e2hWtDYTQvvffJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96f26141e4599318fd45c2bd03f3fe0566fb26e7289be2ab581413bfeef4724b","last_reissued_at":"2026-05-18T01:23:04.053095Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:04.053095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning Neural Turing Machines - Revised","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, Wojciech Zaremba","submitted_at":"2015-05-04T04:14:54Z","abstract_excerpt":"The Neural Turing Machine (NTM) is more expressive than all previously considered models because of its external memory. It can be viewed as a broader effort to use abstract external Interfaces and to learn a parametric model that interacts with them.\n  The capabilities of a model can be extended by providing it with proper Interfaces that interact with the world. These external Interfaces include memory, a database, a search engine, or a piece of software such as a theorem verifier. Some of these Interfaces are provided by the developers of the model. However, many important existing Interfac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00521","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":"1505.00521","created_at":"2026-05-18T01:23:04.053167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.00521v3","created_at":"2026-05-18T01:23:04.053167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00521","created_at":"2026-05-18T01:23:04.053167+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3ZGCQPELGJR","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3ZGCQPELGJRR7KF","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3ZGCQPE","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2201.02177","citing_title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV","json":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV.json","graph_json":"https://pith.science/api/pith-number/S3ZGCQPELGJRR7KFYK6QH476AV/graph.json","events_json":"https://pith.science/api/pith-number/S3ZGCQPELGJRR7KFYK6QH476AV/events.json","paper":"https://pith.science/paper/S3ZGCQPE"},"agent_actions":{"view_html":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV","download_json":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV.json","view_paper":"https://pith.science/paper/S3ZGCQPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.00521&json=true","fetch_graph":"https://pith.science/api/pith-number/S3ZGCQPELGJRR7KFYK6QH476AV/graph.json","fetch_events":"https://pith.science/api/pith-number/S3ZGCQPELGJRR7KFYK6QH476AV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV/action/storage_attestation","attest_author":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV/action/author_attestation","sign_citation":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV/action/citation_signature","submit_replication":"https://pith.science/pith/S3ZGCQPELGJRR7KFYK6QH476AV/action/replication_record"}},"created_at":"2026-05-18T01:23:04.053167+00:00","updated_at":"2026-05-18T01:23:04.053167+00:00"}