{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FJL2FJIBBGTXP2552KLFUPPCPV","short_pith_number":"pith:FJL2FJIB","canonical_record":{"source":{"id":"1410.5401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-10-20T19:28:26Z","cross_cats_sorted":[],"title_canon_sha256":"6a74d2fab1bca245e50f298c71506d15b7c4cc97a4bb0259f2c553b41e08977b","abstract_canon_sha256":"53a93bba96507fc80ece41543b44a5f42898b49b1dc9a9d6c206c597fdf88645"},"schema_version":"1.0"},"canonical_sha256":"2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502","source":{"kind":"arxiv","id":"1410.5401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.5401","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"1410.5401v2","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.5401","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"FJL2FJIBBGTX","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"FJL2FJIBBGTXP255","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"FJL2FJIB","created_at":"2026-07-04T19:15:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FJL2FJIBBGTXP2552KLFUPPCPV","target":"record","payload":{"canonical_record":{"source":{"id":"1410.5401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-10-20T19:28:26Z","cross_cats_sorted":[],"title_canon_sha256":"6a74d2fab1bca245e50f298c71506d15b7c4cc97a4bb0259f2c553b41e08977b","abstract_canon_sha256":"53a93bba96507fc80ece41543b44a5f42898b49b1dc9a9d6c206c597fdf88645"},"schema_version":"1.0"},"canonical_sha256":"2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T19:15:22.838404Z","signature_b64":"mA1jvTMo8p3uYoXO3zfqYWWZUhpakFxG0ENN1qx5OFYGZN1jgHONo8wogxx9a+S8Fch+vGB73W9W47YfcQ+CBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502","last_reissued_at":"2026-07-04T19:15:22.837907Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T19:15:22.837907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1410.5401","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T19:15:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hq9ZBKAXIJ6C3jKWO0jY9fWbQ0+8pgk2QBflCvUYXYZ/LlJMDSTKNKq60J1ExqbX+WrwU7DFvXUj6QD2ukUiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T14:53:13.530494Z"},"content_sha256":"419ad9a2c04a4fd8ec0fd8851a42fe241279fe85ce6071d7e50f79eedd2642b5","schema_version":"1.0","event_id":"sha256:419ad9a2c04a4fd8ec0fd8851a42fe241279fe85ce6071d7e50f79eedd2642b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FJL2FJIBBGTXP2552KLFUPPCPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Turing Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples.","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Alex Graves, Greg Wayne, Ivo Danihelka","submitted_at":"2014-10-20T19:28:26Z","abstract_excerpt":"We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the attentional read and write operations remain stable and trainable with gradient descent without the memory interactions causing vanishing gradients or optimization failure on longer sequences.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural Turing Machines augment neural networks with differentiable external memory to learn algorithmic tasks such as copying, sorting, and associative recall from examples.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5132381d728bf626c322811cd8b5e8156842370f8ae943de04de31abd46db4b0"},"source":{"id":"1410.5401","kind":"arxiv","version":2},"verdict":{"id":"206d44c5-cfd1-4ddd-83db-a0b5420b4abb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T07:29:37.093817Z","strongest_claim":"The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.","one_line_summary":"Neural Turing Machines augment neural networks with differentiable external memory to learn algorithmic tasks such as copying, sorting, and associative recall from examples.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the attentional read and write operations remain stable and trainable with gradient descent without the memory interactions causing vanishing gradients or optimization failure on longer sequences.","pith_extraction_headline":"Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1410.5401/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":42,"sample":[{"doi":"","year":2009,"title":"Baddeley, A., Eysenck, M., and Anderson, M. (2009). Memory . Psychology Press","work_id":"b32036f7-2b87-48df-982b-b112c694d0f2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","ref_index":2,"cited_arxiv_id":"1409.0473","is_internal_anchor":true},{"doi":"","year":2004,"title":"Barrouillet, P., Bernardin, S., and Camos, V. (2004). Time constraints and resource sharing in adults' working memory spans. Journal of Experimental Psychology: General , 133(1):83","work_id":"686165df-07d7-47b7-b026-822761f13899","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1956,"title":"Chomsky, N. (1956). Three models for the description of language. Information Theory, IEEE Transactions on , 2(3):113--124","work_id":"88982e20-22c4-465a-8a9d-cc7b57b778c2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1992,"title":"L., and Sun, G.-Z","work_id":"3b183480-0d60-4040-9940-1ce5ec546652","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"229b3a52068def3b995ac32eb527912327f412a2441e87bb450dd7bbcb621f46","internal_anchors":1},"formal_canon":{"evidence_count":1,"snapshot_sha256":"7c609aa9ad3c6da09a261708b2f96fa4a6eb54f13babf44aa0639ebe676f4560"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"206d44c5-cfd1-4ddd-83db-a0b5420b4abb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T19:15:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBgsoMVHRA2SrGksizX5ruWXKVVDA0/MGtsPLutxcw9uccNjr0v1z+Cume9H6gOm7qToMXJJ70JqYzfejreDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T14:53:13.531334Z"},"content_sha256":"02be0dee98285df892820f1bbb0f2255081541e2788821da974339049926b1b0","schema_version":"1.0","event_id":"sha256:02be0dee98285df892820f1bbb0f2255081541e2788821da974339049926b1b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/bundle.json","state_url":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJL2FJIBBGTXP2552KLFUPPCPV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-10T14:53:13Z","links":{"resolver":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV","bundle":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/bundle.json","state":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJL2FJIBBGTXP2552KLFUPPCPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FJL2FJIBBGTXP2552KLFUPPCPV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"53a93bba96507fc80ece41543b44a5f42898b49b1dc9a9d6c206c597fdf88645","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-10-20T19:28:26Z","title_canon_sha256":"6a74d2fab1bca245e50f298c71506d15b7c4cc97a4bb0259f2c553b41e08977b"},"schema_version":"1.0","source":{"id":"1410.5401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.5401","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"1410.5401v2","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.5401","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"FJL2FJIBBGTX","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"FJL2FJIBBGTXP255","created_at":"2026-07-04T19:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"FJL2FJIB","created_at":"2026-07-04T19:15:22Z"}],"graph_snapshots":[{"event_id":"sha256:02be0dee98285df892820f1bbb0f2255081541e2788821da974339049926b1b0","target":"graph","created_at":"2026-07-04T19:15:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the attentional read and write operations remain stable and trainable with gradient descent without the memory interactions causing vanishing gradients or optimization failure on longer sequences."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Neural Turing Machines augment neural networks with differentiable external memory to learn algorithmic tasks such as copying, sorting, and associative recall from examples."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples."}],"snapshot_sha256":"5132381d728bf626c322811cd8b5e8156842370f8ae943de04de31abd46db4b0"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"7c609aa9ad3c6da09a261708b2f96fa4a6eb54f13babf44aa0639ebe676f4560"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1410.5401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.","authors_text":"Alex Graves, Greg Wayne, Ivo Danihelka","cross_cats":[],"headline":"Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-10-20T19:28:26Z","title":"Neural Turing Machines"},"references":{"count":42,"internal_anchors":1,"resolved_work":42,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Baddeley, A., Eysenck, M., and Anderson, M. (2009). Memory . Psychology Press","work_id":"b32036f7-2b87-48df-982b-b112c694d0f2","year":2009},{"cited_arxiv_id":"1409.0473","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Barrouillet, P., Bernardin, S., and Camos, V. (2004). Time constraints and resource sharing in adults' working memory spans. Journal of Experimental Psychology: General , 133(1):83","work_id":"686165df-07d7-47b7-b026-822761f13899","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Chomsky, N. (1956). Three models for the description of language. Information Theory, IEEE Transactions on , 2(3):113--124","work_id":"88982e20-22c4-465a-8a9d-cc7b57b778c2","year":1956},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"L., and Sun, G.-Z","work_id":"3b183480-0d60-4040-9940-1ce5ec546652","year":1992}],"snapshot_sha256":"229b3a52068def3b995ac32eb527912327f412a2441e87bb450dd7bbcb621f46"},"source":{"id":"1410.5401","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T07:29:37.093817Z","id":"206d44c5-cfd1-4ddd-83db-a0b5420b4abb","model_set":{"reader":"grok-4.3"},"one_line_summary":"Neural Turing Machines augment neural networks with differentiable external memory to learn algorithmic tasks such as copying, sorting, and associative recall from examples.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples.","strongest_claim":"The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.","weakest_assumption":"That the attentional read and write operations remain stable and trainable with gradient descent without the memory interactions causing vanishing gradients or optimization failure on longer sequences."}},"verdict_id":"206d44c5-cfd1-4ddd-83db-a0b5420b4abb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:419ad9a2c04a4fd8ec0fd8851a42fe241279fe85ce6071d7e50f79eedd2642b5","target":"record","created_at":"2026-07-04T19:15:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"53a93bba96507fc80ece41543b44a5f42898b49b1dc9a9d6c206c597fdf88645","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-10-20T19:28:26Z","title_canon_sha256":"6a74d2fab1bca245e50f298c71506d15b7c4cc97a4bb0259f2c553b41e08977b"},"schema_version":"1.0","source":{"id":"1410.5401","kind":"arxiv","version":2}},"canonical_sha256":"2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502","first_computed_at":"2026-07-04T19:15:22.837907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T19:15:22.837907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mA1jvTMo8p3uYoXO3zfqYWWZUhpakFxG0ENN1qx5OFYGZN1jgHONo8wogxx9a+S8Fch+vGB73W9W47YfcQ+CBw==","signature_status":"signed_v1","signed_at":"2026-07-04T19:15:22.838404Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.5401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:419ad9a2c04a4fd8ec0fd8851a42fe241279fe85ce6071d7e50f79eedd2642b5","sha256:02be0dee98285df892820f1bbb0f2255081541e2788821da974339049926b1b0"],"state_sha256":"33fa9c46eb3c4a1db3d6e9d830200ecdf7c7bd6a1999a4004c81a15a89252a2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlDpINgloInP8g1jKgBOX/OjhK7sij+JuHynZ5otKeRMaJ54/uXC5JOZzhhhL+7k727gwkUcGoz8y/RujBFDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T14:53:13.533834Z","bundle_sha256":"5668fb834782947e8bc186a87e3c0fb668aa46ee202a0cd93520e632f80b2914"}}