{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:II6OMB3PIQZ7DA7PDXYM7FKEH4","short_pith_number":"pith:II6OMB3P","schema_version":"1.0","canonical_sha256":"423ce6076f4433f183ef1df0cf95443f253483081465b7c54c30787c1b198f4b","source":{"kind":"arxiv","id":"1902.03993","version":2},"attestation_state":"computed","paper":{"title":"Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Martinsson, Angelika Steger, Asier Mujika, Frederik Benzing, Marcelo Matheus Gauy","submitted_at":"2019-02-11T16:51:12Z","abstract_excerpt":"One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids learning dependencies beyond the truncation horizon. In contrast, the online training algorithm Real Time Recurrent Learning (RTRL) provides untruncated gradients, with the disadvantage of impractically large computational costs. Recently published approaches reduce these costs by providing noisy approximations of RTRL. We present a new approximation algorithm of "},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1902.03993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-11T16:51:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f416c06a700e8b23076dd98188ed395ec998cbee876af958f2826b50571951a8","abstract_canon_sha256":"b6200332086eaf7c4bf2f6772d6c0a063b85f41f2e57fd0feeeb070b50fa699e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:56.472702Z","signature_b64":"1xAMKZRD7HwyzgDcOGuXRXOJdTMeruSTPywmoiMzz7h7Z6CT+9xq7epKjjcgHpfTWBMyxUC5z/n4/Tr8eOOwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"423ce6076f4433f183ef1df0cf95443f253483081465b7c54c30787c1b198f4b","last_reissued_at":"2026-05-17T23:45:56.472207Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:56.472207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Martinsson, Angelika Steger, Asier Mujika, Frederik Benzing, Marcelo Matheus Gauy","submitted_at":"2019-02-11T16:51:12Z","abstract_excerpt":"One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids learning dependencies beyond the truncation horizon. In contrast, the online training algorithm Real Time Recurrent Learning (RTRL) provides untruncated gradients, with the disadvantage of impractically large computational costs. Recently published approaches reduce these costs by providing noisy approximations of RTRL. We present a new approximation algorithm of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03993","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1902.03993","created_at":"2026-05-17T23:45:56.472279+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.03993v2","created_at":"2026-05-17T23:45:56.472279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03993","created_at":"2026-05-17T23:45:56.472279+00:00"},{"alias_kind":"pith_short_12","alias_value":"II6OMB3PIQZ7","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"II6OMB3PIQZ7DA7P","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"II6OMB3P","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02649","citing_title":"A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4","json":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4.json","graph_json":"https://pith.science/api/pith-number/II6OMB3PIQZ7DA7PDXYM7FKEH4/graph.json","events_json":"https://pith.science/api/pith-number/II6OMB3PIQZ7DA7PDXYM7FKEH4/events.json","paper":"https://pith.science/paper/II6OMB3P"},"agent_actions":{"view_html":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4","download_json":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4.json","view_paper":"https://pith.science/paper/II6OMB3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.03993&json=true","fetch_graph":"https://pith.science/api/pith-number/II6OMB3PIQZ7DA7PDXYM7FKEH4/graph.json","fetch_events":"https://pith.science/api/pith-number/II6OMB3PIQZ7DA7PDXYM7FKEH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4/action/storage_attestation","attest_author":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4/action/author_attestation","sign_citation":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4/action/citation_signature","submit_replication":"https://pith.science/pith/II6OMB3PIQZ7DA7PDXYM7FKEH4/action/replication_record"}},"created_at":"2026-05-17T23:45:56.472279+00:00","updated_at":"2026-05-17T23:45:56.472279+00:00"}