{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KIPDR7BY5P3I3FWFXFPFHGE2XK","short_pith_number":"pith:KIPDR7BY","canonical_record":{"source":{"id":"1702.08727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-28T10:19:51Z","cross_cats_sorted":[],"title_canon_sha256":"4c0d7c8efab73a55f7b61b14df72bf37b1b911aa850a5abe98fb1121c7bef203","abstract_canon_sha256":"edef720cb64c356ea067a0277def1299f4552897df2263c4c94b96913d00ca5d"},"schema_version":"1.0"},"canonical_sha256":"521e38fc38ebf68d96c5b95e53989aba8e83b1da5b37d27ee7fcb4e5f6aa8870","source":{"kind":"arxiv","id":"1702.08727","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08727","created_at":"2026-05-18T00:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08727v2","created_at":"2026-05-18T00:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08727","created_at":"2026-05-18T00:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"KIPDR7BY5P3I","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KIPDR7BY5P3I3FWF","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KIPDR7BY","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KIPDR7BY5P3I3FWFXFPFHGE2XK","target":"record","payload":{"canonical_record":{"source":{"id":"1702.08727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-28T10:19:51Z","cross_cats_sorted":[],"title_canon_sha256":"4c0d7c8efab73a55f7b61b14df72bf37b1b911aa850a5abe98fb1121c7bef203","abstract_canon_sha256":"edef720cb64c356ea067a0277def1299f4552897df2263c4c94b96913d00ca5d"},"schema_version":"1.0"},"canonical_sha256":"521e38fc38ebf68d96c5b95e53989aba8e83b1da5b37d27ee7fcb4e5f6aa8870","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:24.197226Z","signature_b64":"0taERr36J0fIYoY/IG9Nx80PqN4AYJT1Rl9mrC391QDSaEVp/sksadW1NbpbVFK90sByDuySE2W/b3IPx+h4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"521e38fc38ebf68d96c5b95e53989aba8e83b1da5b37d27ee7fcb4e5f6aa8870","last_reissued_at":"2026-05-18T00:05:24.196670Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:24.196670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.08727","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":"2026-05-18T00:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClTkfbHB+yhtnIUzrGlpiQzxh0AFVwz6ixaiIMUhi88V3z8sDyBr+XkLJWAo1sCfdAIEDFHDLS4A6N3bUgl3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:43:57.914934Z"},"content_sha256":"2f02ac9d64426c98e6995098ed730b355ec5d8ea65e1f8a193035b453799fd03","schema_version":"1.0","event_id":"sha256:2f02ac9d64426c98e6995098ed730b355ec5d8ea65e1f8a193035b453799fd03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KIPDR7BY5P3I3FWFXFPFHGE2XK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving the Neural GPU Architecture for Algorithm Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Karlis Freivalds, Renars Liepins","submitted_at":"2017-02-28T10:19:51Z","abstract_excerpt":"Algorithm learning is a core problem in artificial intelligence with significant implications on automation level that can be achieved by machines. Recently deep learning methods are emerging for synthesizing an algorithm from its input-output examples, the most successful being the Neural GPU, capable of learning multiplication. We present several improvements to the Neural GPU that substantially reduces training time and improves generalization. We introduce a new technique - hard nonlinearities with saturation costs- that has general applicability. We also introduce a technique of diagonal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08727","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0iTnGQBbxkmSkQCOgiLAaXAig8ZYsXpVrbw+ThfqXcbs0OdBw7bDWCsO1yE6UiM+fOkrGTZyhmy8oOe2R2ABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:43:57.915476Z"},"content_sha256":"364c56637a02be9d28618bbdd9664b98f6daa3573ebd4243f3f42a581896af52","schema_version":"1.0","event_id":"sha256:364c56637a02be9d28618bbdd9664b98f6daa3573ebd4243f3f42a581896af52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK/bundle.json","state_url":"https://pith.science/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK/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":"2026-06-29T22:43:57Z","links":{"resolver":"https://pith.science/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK","bundle":"https://pith.science/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK/bundle.json","state":"https://pith.science/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KIPDR7BY5P3I3FWFXFPFHGE2XK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KIPDR7BY5P3I3FWFXFPFHGE2XK","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":"edef720cb64c356ea067a0277def1299f4552897df2263c4c94b96913d00ca5d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-28T10:19:51Z","title_canon_sha256":"4c0d7c8efab73a55f7b61b14df72bf37b1b911aa850a5abe98fb1121c7bef203"},"schema_version":"1.0","source":{"id":"1702.08727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08727","created_at":"2026-05-18T00:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08727v2","created_at":"2026-05-18T00:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08727","created_at":"2026-05-18T00:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"KIPDR7BY5P3I","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KIPDR7BY5P3I3FWF","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KIPDR7BY","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:364c56637a02be9d28618bbdd9664b98f6daa3573ebd4243f3f42a581896af52","target":"graph","created_at":"2026-05-18T00:05:24Z","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":"Algorithm learning is a core problem in artificial intelligence with significant implications on automation level that can be achieved by machines. Recently deep learning methods are emerging for synthesizing an algorithm from its input-output examples, the most successful being the Neural GPU, capable of learning multiplication. We present several improvements to the Neural GPU that substantially reduces training time and improves generalization. We introduce a new technique - hard nonlinearities with saturation costs- that has general applicability. We also introduce a technique of diagonal ","authors_text":"Karlis Freivalds, Renars Liepins","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-28T10:19:51Z","title":"Improving the Neural GPU Architecture for Algorithm Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08727","kind":"arxiv","version":2},"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":"sha256:2f02ac9d64426c98e6995098ed730b355ec5d8ea65e1f8a193035b453799fd03","target":"record","created_at":"2026-05-18T00:05:24Z","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":"edef720cb64c356ea067a0277def1299f4552897df2263c4c94b96913d00ca5d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-28T10:19:51Z","title_canon_sha256":"4c0d7c8efab73a55f7b61b14df72bf37b1b911aa850a5abe98fb1121c7bef203"},"schema_version":"1.0","source":{"id":"1702.08727","kind":"arxiv","version":2}},"canonical_sha256":"521e38fc38ebf68d96c5b95e53989aba8e83b1da5b37d27ee7fcb4e5f6aa8870","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"521e38fc38ebf68d96c5b95e53989aba8e83b1da5b37d27ee7fcb4e5f6aa8870","first_computed_at":"2026-05-18T00:05:24.196670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:24.196670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0taERr36J0fIYoY/IG9Nx80PqN4AYJT1Rl9mrC391QDSaEVp/sksadW1NbpbVFK90sByDuySE2W/b3IPx+h4CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:24.197226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.08727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f02ac9d64426c98e6995098ed730b355ec5d8ea65e1f8a193035b453799fd03","sha256:364c56637a02be9d28618bbdd9664b98f6daa3573ebd4243f3f42a581896af52"],"state_sha256":"88397d59392dbc888e7b4f2304c6603c5fcd30e34b192fc722db508d27cfbd87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WBSnoGAzTORel1lbJyzz5qV4Y0gdSejLqeGuM2Ddp8WQZez9vu9yZYWBhpQgeHvJYg8l+dGIunkLOvlKPgp+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T22:43:57.917734Z","bundle_sha256":"64702c4a61a6a0a7bb1ef653ae2a8ff708bc4b89747b289b7f6e497b7cd67a43"}}