{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VWGYKXXPX6FRLHMOI62D6XAEGK","short_pith_number":"pith:VWGYKXXP","canonical_record":{"source":{"id":"1805.10842","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T09:40:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0adfa7688995c5337f0256d1d9d553e3d3602f6b809002d8a7d853f564a51648","abstract_canon_sha256":"0101f1fe1846b23d27ca8c1c878528303f532c1e08ccf7c23bce85e0bf9ce2f4"},"schema_version":"1.0"},"canonical_sha256":"ad8d855eefbf8b159d8e47b43f5c0432801c97fa3041a8d658a0de2f2805537d","source":{"kind":"arxiv","id":"1805.10842","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10842","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10842v2","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10842","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"VWGYKXXPX6FR","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VWGYKXXPX6FRLHMO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VWGYKXXP","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VWGYKXXPX6FRLHMOI62D6XAEGK","target":"record","payload":{"canonical_record":{"source":{"id":"1805.10842","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T09:40:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0adfa7688995c5337f0256d1d9d553e3d3602f6b809002d8a7d853f564a51648","abstract_canon_sha256":"0101f1fe1846b23d27ca8c1c878528303f532c1e08ccf7c23bce85e0bf9ce2f4"},"schema_version":"1.0"},"canonical_sha256":"ad8d855eefbf8b159d8e47b43f5c0432801c97fa3041a8d658a0de2f2805537d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:59.202567Z","signature_b64":"zOmH7KURfetucKp9WIiZvJGpgZE80dVdc7hHpxW21KwUtBG+AFQsMdI3Ea9flcMG89qKwwsenttxtdy3liA9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad8d855eefbf8b159d8e47b43f5c0432801c97fa3041a8d658a0de2f2805537d","last_reissued_at":"2026-05-17T23:58:59.202013Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:59.202013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.10842","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":"2026-05-17T23:58:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75KJLOmB4jFm+KEwI8JFCwN8tasHNQlYwUuj3xe+oV8u7d0SkgYORmbDzbqKsyh5td3xltQ3XayBWI2xOyuiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:39:08.234848Z"},"content_sha256":"0dc94af3629145e636ac9a0e3f116f2cb0b79cea9ccd15fbad31ec15405d53f7","schema_version":"1.0","event_id":"sha256:0dc94af3629145e636ac9a0e3f116f2cb0b79cea9ccd15fbad31ec15405d53f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VWGYKXXPX6FRLHMOI62D6XAEGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximating Real-Time Recurrent Learning with Random Kronecker Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Angelika Steger, Asier Mujika, Florian Meier","submitted_at":"2018-05-28T09:40:04Z","abstract_excerpt":"Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the truncation bias, which drastically limits its ability to learn long-term dependencies.The Real-Time Recurrent Learning algorithm (RTRL) addresses this issue, but its high computational requirements make it infeasible in practice. The Unbiased Online Recurrent Optimization algorithm (UORO) approximates RTRL with a smaller runtime and memory cost, but with the d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10842","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":"2026-05-17T23:58:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EtRzL6Ft5D70jY+hpFxhqcWk5wnmPDzqd2sCrraAsi007QWVt2LIHnpJhvaZQX0EhDDu/Gf6vis4YD/iURfiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:39:08.235335Z"},"content_sha256":"da498c8d7d9ad3135c903c5abf3943222084957f72f45243100d57fefaa5588e","schema_version":"1.0","event_id":"sha256:da498c8d7d9ad3135c903c5abf3943222084957f72f45243100d57fefaa5588e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWGYKXXPX6FRLHMOI62D6XAEGK/bundle.json","state_url":"https://pith.science/pith/VWGYKXXPX6FRLHMOI62D6XAEGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWGYKXXPX6FRLHMOI62D6XAEGK/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":"2026-08-22T07:39:08Z","links":{"resolver":"https://pith.science/pith/VWGYKXXPX6FRLHMOI62D6XAEGK","bundle":"https://pith.science/pith/VWGYKXXPX6FRLHMOI62D6XAEGK/bundle.json","state":"https://pith.science/pith/VWGYKXXPX6FRLHMOI62D6XAEGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWGYKXXPX6FRLHMOI62D6XAEGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VWGYKXXPX6FRLHMOI62D6XAEGK","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":"0101f1fe1846b23d27ca8c1c878528303f532c1e08ccf7c23bce85e0bf9ce2f4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T09:40:04Z","title_canon_sha256":"0adfa7688995c5337f0256d1d9d553e3d3602f6b809002d8a7d853f564a51648"},"schema_version":"1.0","source":{"id":"1805.10842","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10842","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10842v2","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10842","created_at":"2026-05-17T23:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"VWGYKXXPX6FR","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VWGYKXXPX6FRLHMO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VWGYKXXP","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:da498c8d7d9ad3135c903c5abf3943222084957f72f45243100d57fefaa5588e","target":"graph","created_at":"2026-05-17T23:58:59Z","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":"Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the truncation bias, which drastically limits its ability to learn long-term dependencies.The Real-Time Recurrent Learning algorithm (RTRL) addresses this issue, but its high computational requirements make it infeasible in practice. The Unbiased Online Recurrent Optimization algorithm (UORO) approximates RTRL with a smaller runtime and memory cost, but with the d","authors_text":"Angelika Steger, Asier Mujika, Florian Meier","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T09:40:04Z","title":"Approximating Real-Time Recurrent Learning with Random Kronecker Factors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10842","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":"sha256:0dc94af3629145e636ac9a0e3f116f2cb0b79cea9ccd15fbad31ec15405d53f7","target":"record","created_at":"2026-05-17T23:58:59Z","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":"0101f1fe1846b23d27ca8c1c878528303f532c1e08ccf7c23bce85e0bf9ce2f4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T09:40:04Z","title_canon_sha256":"0adfa7688995c5337f0256d1d9d553e3d3602f6b809002d8a7d853f564a51648"},"schema_version":"1.0","source":{"id":"1805.10842","kind":"arxiv","version":2}},"canonical_sha256":"ad8d855eefbf8b159d8e47b43f5c0432801c97fa3041a8d658a0de2f2805537d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad8d855eefbf8b159d8e47b43f5c0432801c97fa3041a8d658a0de2f2805537d","first_computed_at":"2026-05-17T23:58:59.202013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:59.202013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zOmH7KURfetucKp9WIiZvJGpgZE80dVdc7hHpxW21KwUtBG+AFQsMdI3Ea9flcMG89qKwwsenttxtdy3liA9AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:59.202567Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10842","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dc94af3629145e636ac9a0e3f116f2cb0b79cea9ccd15fbad31ec15405d53f7","sha256:da498c8d7d9ad3135c903c5abf3943222084957f72f45243100d57fefaa5588e"],"state_sha256":"c8cf0dbae45a3c765aeacb8c3873db8f436938d67b084782ad8e3e74dbb68add"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A7g9w8XrcIALaNpdx2zIVNEf1SFD0RqDNHlzZyrFh3eRl+59lw/vR9iSe+IFNUjBjlwhPgPX0AOi0ObXK8OSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:39:08.240646Z","bundle_sha256":"1376c104fb8deb9704fd81def4876be146399e65c5709dbc59a5b50a4c9e6cb3"}}