{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AQK7XYIKU75JEN74KYA2GDQ4HY","short_pith_number":"pith:AQK7XYIK","canonical_record":{"source":{"id":"2006.07232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:38:15Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"b61abfc64fae49c7e9fa592499f34b19896b010eb8bc2687ea8aedeeb871bc2b","abstract_canon_sha256":"2ed67a195912de3aff3871fdf0db2f051347a1be68643aa78fde0977591f0ebb"},"schema_version":"1.0"},"canonical_sha256":"0415fbe10aa7fa9237fc5601a30e1c3e1df6591f1ee6416e4f76222fb083decb","source":{"kind":"arxiv","id":"2006.07232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07232","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07232v1","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07232","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"AQK7XYIKU75J","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"AQK7XYIKU75JEN74","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"AQK7XYIK","created_at":"2026-07-05T01:09:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AQK7XYIKU75JEN74KYA2GDQ4HY","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:38:15Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"b61abfc64fae49c7e9fa592499f34b19896b010eb8bc2687ea8aedeeb871bc2b","abstract_canon_sha256":"2ed67a195912de3aff3871fdf0db2f051347a1be68643aa78fde0977591f0ebb"},"schema_version":"1.0"},"canonical_sha256":"0415fbe10aa7fa9237fc5601a30e1c3e1df6591f1ee6416e4f76222fb083decb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:51.180397Z","signature_b64":"L+Fb8AAnhIScz5yCpMe8xxCsChjRL8DpzZ1ve10qYgY///ozGd5m3yIR1Ey0XAEhjeCZmk64lU0WGWlvVAu1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0415fbe10aa7fa9237fc5601a30e1c3e1df6591f1ee6416e4f76222fb083decb","last_reissued_at":"2026-07-05T01:09:51.179911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:51.179911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07232","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jzNY3COOOim3UG0M7ZM56dW45a+i2ZA07daj3H6ciitOgPoGeC54NBd59Je//gKVmLwbYAHY6KS5bJXaR6bgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:38:31.288464Z"},"content_sha256":"ed322472b3ec24c64cbed62ea2c57e0dd8320c7d49bb12b87454d1386a67e491","schema_version":"1.0","event_id":"sha256:ed322472b3ec24c64cbed62ea2c57e0dd8320c7d49bb12b87454d1386a67e491"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AQK7XYIKU75JEN74KYA2GDQ4HY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Practical Sparse Approximation for Real Time Recurrent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Graves, Erich Elsen, Jacob Menick, Karen Simonyan, Simon Osindero, Utku Evci","submitted_at":"2020-06-12T14:38:15Z","abstract_excerpt":"Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every timestep). Real Time Recurrent Learning (RTRL) eliminates the need for history storage and allows for online weight updates, but does so at the expense of computational costs that are quartic in the state size. This renders RTRL training intractable for all but the smallest networks, even ones that are made highly sparse.\n  We introduce the Sparse n-step Approximation (SnAp) to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07232","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07232/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUUAMeC3w+ruOKoCAwPPCsGfG9DafqJMM1ZGJjhJnCX9ZsMVHEi25MlZ7htZ3YJx2cZ4uNZFizUotU7Q8blcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:38:31.288930Z"},"content_sha256":"a27227f7aa8d6334360baab75b25a3af89cba689c47a03fdae1332123b32da12","schema_version":"1.0","event_id":"sha256:a27227f7aa8d6334360baab75b25a3af89cba689c47a03fdae1332123b32da12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQK7XYIKU75JEN74KYA2GDQ4HY/bundle.json","state_url":"https://pith.science/pith/AQK7XYIKU75JEN74KYA2GDQ4HY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQK7XYIKU75JEN74KYA2GDQ4HY/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":"2026-08-05T18:38:31Z","links":{"resolver":"https://pith.science/pith/AQK7XYIKU75JEN74KYA2GDQ4HY","bundle":"https://pith.science/pith/AQK7XYIKU75JEN74KYA2GDQ4HY/bundle.json","state":"https://pith.science/pith/AQK7XYIKU75JEN74KYA2GDQ4HY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQK7XYIKU75JEN74KYA2GDQ4HY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AQK7XYIKU75JEN74KYA2GDQ4HY","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":"2ed67a195912de3aff3871fdf0db2f051347a1be68643aa78fde0977591f0ebb","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:38:15Z","title_canon_sha256":"b61abfc64fae49c7e9fa592499f34b19896b010eb8bc2687ea8aedeeb871bc2b"},"schema_version":"1.0","source":{"id":"2006.07232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07232","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07232v1","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07232","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"AQK7XYIKU75J","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"AQK7XYIKU75JEN74","created_at":"2026-07-05T01:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"AQK7XYIK","created_at":"2026-07-05T01:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:a27227f7aa8d6334360baab75b25a3af89cba689c47a03fdae1332123b32da12","target":"graph","created_at":"2026-07-05T01:09:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.07232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every timestep). Real Time Recurrent Learning (RTRL) eliminates the need for history storage and allows for online weight updates, but does so at the expense of computational costs that are quartic in the state size. This renders RTRL training intractable for all but the smallest networks, even ones that are made highly sparse.\n  We introduce the Sparse n-step Approximation (SnAp) to the","authors_text":"Alex Graves, Erich Elsen, Jacob Menick, Karen Simonyan, Simon Osindero, Utku Evci","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:38:15Z","title":"A Practical Sparse Approximation for Real Time Recurrent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07232","kind":"arxiv","version":1},"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:ed322472b3ec24c64cbed62ea2c57e0dd8320c7d49bb12b87454d1386a67e491","target":"record","created_at":"2026-07-05T01:09:51Z","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":"2ed67a195912de3aff3871fdf0db2f051347a1be68643aa78fde0977591f0ebb","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:38:15Z","title_canon_sha256":"b61abfc64fae49c7e9fa592499f34b19896b010eb8bc2687ea8aedeeb871bc2b"},"schema_version":"1.0","source":{"id":"2006.07232","kind":"arxiv","version":1}},"canonical_sha256":"0415fbe10aa7fa9237fc5601a30e1c3e1df6591f1ee6416e4f76222fb083decb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0415fbe10aa7fa9237fc5601a30e1c3e1df6591f1ee6416e4f76222fb083decb","first_computed_at":"2026-07-05T01:09:51.179911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:51.179911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+Fb8AAnhIScz5yCpMe8xxCsChjRL8DpzZ1ve10qYgY///ozGd5m3yIR1Ey0XAEhjeCZmk64lU0WGWlvVAu1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:51.180397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed322472b3ec24c64cbed62ea2c57e0dd8320c7d49bb12b87454d1386a67e491","sha256:a27227f7aa8d6334360baab75b25a3af89cba689c47a03fdae1332123b32da12"],"state_sha256":"44356a1bf2bddaf4e8a0e80cd3f39e295075844474b6576d351841e47e333c30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCaidSmRieCLTmgwXjTg6vETJD7AVCVVtr2mZ/y8iibHZsBeuHPcT8OsH+PkdmHhrPYihkvVoPkIFtmDBPhjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:38:31.292443Z","bundle_sha256":"304b07406b904de29b4a5b297cb9ada17ac92ff139bcc6676890fc6fbb90dbcb"}}