{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:FJL2FJIBBGTXP2552KLFUPPCPV","short_pith_number":"pith:FJL2FJIB","schema_version":"1.0","canonical_sha256":"2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502","source":{"kind":"arxiv","id":"1410.5401","version":2},"attestation_state":"computed","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."},"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":true,"formal_links_present":true},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1410.5401","created_at":"2026-07-04T19:15:22.837965+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.5401v2","created_at":"2026-07-04T19:15:22.837965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.5401","created_at":"2026-07-04T19:15:22.837965+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJL2FJIBBGTX","created_at":"2026-07-04T19:15:22.837965+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJL2FJIBBGTXP255","created_at":"2026-07-04T19:15:22.837965+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJL2FJIB","created_at":"2026-07-04T19:15:22.837965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":75,"internal_anchor_count":75,"sample":[{"citing_arxiv_id":"2607.06269","citing_title":"From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25224","citing_title":"Spatio-Temporal Retrieval-based Priors for Adaptive Computational Teaching in Driving","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25136","citing_title":"Memory Retrieval in Visuomotor Policies for Long-Horizon Robot Control","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22447","citing_title":"A Differentiable Atari VCS:A Complex, Fully Known Ground Truth for Explainable AI","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21398","citing_title":"BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21562","citing_title":"Compressing Observation History into Agent Memory: Distilling Transformers into Recurrent Transformers","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20737","citing_title":"Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18206","citing_title":"Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12979","citing_title":"EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10435","citing_title":"Parallel Causal Associative Fields: Gated Sparse Memory for Long-Context Language Modeling","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07720","citing_title":"Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06479","citing_title":"Pretraining Recurrent Networks without Recurrence","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02054","citing_title":"eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31163","citing_title":"Memory by Design: Probabilistic Sequence Layers","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28112","citing_title":"BiDeMem: Bidirectional Degradation Memory for Explainable Image Restoration","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14685","citing_title":"Spontaneous symmetry breaking and Goldstone modes for deep information propagation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05201","citing_title":"State commitment learning: training language models to distinguish computation from memory","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27686","citing_title":"Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31075","citing_title":"Task-Focused Memorization for Multimodal Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"1906.12087","citing_title":"ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00462","citing_title":"Inter and Intra Document Attention for Depression Risk Assessment","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00820","citing_title":"Understanding Memory Modules on Learning Simple Algorithms","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01470","citing_title":"Augmenting Self-attention with Persistent Memory","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV","json":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV.json","graph_json":"https://pith.science/api/pith-number/FJL2FJIBBGTXP2552KLFUPPCPV/graph.json","events_json":"https://pith.science/api/pith-number/FJL2FJIBBGTXP2552KLFUPPCPV/events.json","paper":"https://pith.science/paper/FJL2FJIB"},"agent_actions":{"view_html":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV","download_json":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV.json","view_paper":"https://pith.science/paper/FJL2FJIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.5401&json=true","fetch_graph":"https://pith.science/api/pith-number/FJL2FJIBBGTXP2552KLFUPPCPV/graph.json","fetch_events":"https://pith.science/api/pith-number/FJL2FJIBBGTXP2552KLFUPPCPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/action/storage_attestation","attest_author":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/action/author_attestation","sign_citation":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/action/citation_signature","submit_replication":"https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV/action/replication_record"}},"created_at":"2026-07-04T19:15:22.837965+00:00","updated_at":"2026-07-04T19:15:22.837965+00:00"}