{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YM7SLPAS55V52VEWGYRASKSASL","short_pith_number":"pith:YM7SLPAS","canonical_record":{"source":{"id":"1511.08228","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T21:17:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c64a500b0abfc121837ba76066388ea47fdcf1872d472233f776f547884c8c7f","abstract_canon_sha256":"f20d600fc239b8b1e14473c8a67830ddf0ff89df548329595237be104e7fdbf6"},"schema_version":"1.0"},"canonical_sha256":"c33f25bc12ef6bdd54963622092a4092e002847a431e16fa6a914edf7de232fa","source":{"kind":"arxiv","id":"1511.08228","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08228","created_at":"2026-05-18T01:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08228v3","created_at":"2026-05-18T01:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08228","created_at":"2026-05-18T01:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"YM7SLPAS55V5","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YM7SLPAS55V52VEW","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YM7SLPAS","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YM7SLPAS55V52VEWGYRASKSASL","target":"record","payload":{"canonical_record":{"source":{"id":"1511.08228","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T21:17:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c64a500b0abfc121837ba76066388ea47fdcf1872d472233f776f547884c8c7f","abstract_canon_sha256":"f20d600fc239b8b1e14473c8a67830ddf0ff89df548329595237be104e7fdbf6"},"schema_version":"1.0"},"canonical_sha256":"c33f25bc12ef6bdd54963622092a4092e002847a431e16fa6a914edf7de232fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:05.483310Z","signature_b64":"9j7XIxBFdqTtB51tgfV5SNMDl/CNXs4SuJQBXAC9q1v2J2ij4/i1RAgDuV8JXWzme84m+OX0T7BIaCkveYLYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c33f25bc12ef6bdd54963622092a4092e002847a431e16fa6a914edf7de232fa","last_reissued_at":"2026-05-18T01:19:05.482763Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:05.482763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.08228","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Htif2LvoBlAX1Btz6iFa8yviDQhT+GIgrFNDGISQEI4tObNifyF1a9RHtfdzfWWqekSPoW6IGjbDXUetQwK/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:09:36.033688Z"},"content_sha256":"bf0f87d92df6d0e1f01a28f15b55ffc6eb0e4b3ec4096e84991dbb79044abf95","schema_version":"1.0","event_id":"sha256:bf0f87d92df6d0e1f01a28f15b55ffc6eb0e4b3ec4096e84991dbb79044abf95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YM7SLPAS55V52VEWGYRASKSASL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural GPUs Learn Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Ilya Sutskever, {\\L}ukasz Kaiser","submitted_at":"2015-11-25T21:17:43Z","abstract_excerpt":"Learning an algorithm from examples is a fundamental problem that has been widely studied. Recently it has been addressed using neural networks, in particular by Neural Turing Machines (NTMs). These are fully differentiable computers that use backpropagation to learn their own programming. Despite their appeal NTMs have a weakness that is caused by their sequential nature: they are not parallel and are are hard to train due to their large depth when unfolded.\n  We present a neural network architecture to address this problem: the Neural GPU. It is based on a type of convolutional gated recurre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08228","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zeu6Y/qg1M6TzVvQMQqUpxtO8jKC/alAVtFEpB+DUEn47pIuxDIq/DtGxkDFZEf2spGpHYguWpmlabWK+YGpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:09:36.034362Z"},"content_sha256":"92f97f30e388c23970b5cd92d6df813e8c41deb475d5049a30e3845ff496d165","schema_version":"1.0","event_id":"sha256:92f97f30e388c23970b5cd92d6df813e8c41deb475d5049a30e3845ff496d165"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YM7SLPAS55V52VEWGYRASKSASL/bundle.json","state_url":"https://pith.science/pith/YM7SLPAS55V52VEWGYRASKSASL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YM7SLPAS55V52VEWGYRASKSASL/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":"2026-05-27T12:09:36Z","links":{"resolver":"https://pith.science/pith/YM7SLPAS55V52VEWGYRASKSASL","bundle":"https://pith.science/pith/YM7SLPAS55V52VEWGYRASKSASL/bundle.json","state":"https://pith.science/pith/YM7SLPAS55V52VEWGYRASKSASL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YM7SLPAS55V52VEWGYRASKSASL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YM7SLPAS55V52VEWGYRASKSASL","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":"f20d600fc239b8b1e14473c8a67830ddf0ff89df548329595237be104e7fdbf6","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T21:17:43Z","title_canon_sha256":"c64a500b0abfc121837ba76066388ea47fdcf1872d472233f776f547884c8c7f"},"schema_version":"1.0","source":{"id":"1511.08228","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08228","created_at":"2026-05-18T01:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08228v3","created_at":"2026-05-18T01:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08228","created_at":"2026-05-18T01:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"YM7SLPAS55V5","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YM7SLPAS55V52VEW","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YM7SLPAS","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:92f97f30e388c23970b5cd92d6df813e8c41deb475d5049a30e3845ff496d165","target":"graph","created_at":"2026-05-18T01:19:05Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Learning an algorithm from examples is a fundamental problem that has been widely studied. Recently it has been addressed using neural networks, in particular by Neural Turing Machines (NTMs). These are fully differentiable computers that use backpropagation to learn their own programming. Despite their appeal NTMs have a weakness that is caused by their sequential nature: they are not parallel and are are hard to train due to their large depth when unfolded.\n  We present a neural network architecture to address this problem: the Neural GPU. It is based on a type of convolutional gated recurre","authors_text":"Ilya Sutskever, {\\L}ukasz Kaiser","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T21:17:43Z","title":"Neural GPUs Learn Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08228","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf0f87d92df6d0e1f01a28f15b55ffc6eb0e4b3ec4096e84991dbb79044abf95","target":"record","created_at":"2026-05-18T01:19:05Z","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":"f20d600fc239b8b1e14473c8a67830ddf0ff89df548329595237be104e7fdbf6","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T21:17:43Z","title_canon_sha256":"c64a500b0abfc121837ba76066388ea47fdcf1872d472233f776f547884c8c7f"},"schema_version":"1.0","source":{"id":"1511.08228","kind":"arxiv","version":3}},"canonical_sha256":"c33f25bc12ef6bdd54963622092a4092e002847a431e16fa6a914edf7de232fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c33f25bc12ef6bdd54963622092a4092e002847a431e16fa6a914edf7de232fa","first_computed_at":"2026-05-18T01:19:05.482763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:05.482763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9j7XIxBFdqTtB51tgfV5SNMDl/CNXs4SuJQBXAC9q1v2J2ij4/i1RAgDuV8JXWzme84m+OX0T7BIaCkveYLYCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:05.483310Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.08228","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0f87d92df6d0e1f01a28f15b55ffc6eb0e4b3ec4096e84991dbb79044abf95","sha256:92f97f30e388c23970b5cd92d6df813e8c41deb475d5049a30e3845ff496d165"],"state_sha256":"8d5eb64b6a18def2e408069fbb22173dff119ef0c9c394bcfbc94e5bc5205697"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4sehl22OENcN0ssYxZnrcJ5TFtOCP8CQLoBIyjx27Ddc+wiazx47Di7SxMChaqDq/jfmwvO1WTo6g7h3H452Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T12:09:36.038085Z","bundle_sha256":"52069faa3607a0890284502877b083c218484462da3788d579d1655320f1c6cb"}}