{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7CSZ2IL3SK6MJDOPSXJZEWOKKY","short_pith_number":"pith:7CSZ2IL3","schema_version":"1.0","canonical_sha256":"f8a59d217b92bcc48dcf95d39259ca5605f8bfb144deccccfd768aa4c2686d72","source":{"kind":"arxiv","id":"2006.14371","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","eess.SP","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Gavin D. Portwood, Jean C. Ragusa, Mauricio E. Tano","submitted_at":"2020-06-18T22:59:55Z","abstract_excerpt":"Training of deep neural networks (DNNs) frequently involves optimizing several millions or even billions of parameters. Even with modern computing architectures, the computational expense of DNN training can inhibit, for instance, network architecture design optimization, hyper-parameter studies, and integration into scientific research cycles. The key factor limiting performance is that both the feed-forward evaluation and the back-propagation rule are needed for each weight during optimization in the update rule. In this work, we propose a method to decouple the evaluation of the update rule"},"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":"2006.14371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T22:59:55Z","cross_cats_sorted":["cs.CE","eess.SP","physics.comp-ph"],"title_canon_sha256":"80326c0ec17897b1bea4761a6681a484290ab03589c5008f873bd1dfb4717ab5","abstract_canon_sha256":"f0895121da49a51b5edfa734fc8c3ce786bdd2f58313797a36f2ba37c929fda9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:31.871505Z","signature_b64":"NptxQO3EKMbeUYEdDbDlLNPuUOX7FSbLLj5/RVYsaR0yC0BGUc91f4LvUkuq7a9iaSCVxg+JNtjgMo/E+9jtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a59d217b92bcc48dcf95d39259ca5605f8bfb144deccccfd768aa4c2686d72","last_reissued_at":"2026-07-05T01:13:31.871108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:31.871108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","eess.SP","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Gavin D. Portwood, Jean C. Ragusa, Mauricio E. Tano","submitted_at":"2020-06-18T22:59:55Z","abstract_excerpt":"Training of deep neural networks (DNNs) frequently involves optimizing several millions or even billions of parameters. Even with modern computing architectures, the computational expense of DNN training can inhibit, for instance, network architecture design optimization, hyper-parameter studies, and integration into scientific research cycles. The key factor limiting performance is that both the feed-forward evaluation and the back-propagation rule are needed for each weight during optimization in the update rule. In this work, we propose a method to decouple the evaluation of the update rule"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14371","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/2006.14371/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.14371","created_at":"2026-07-05T01:13:31.871164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14371v1","created_at":"2026-07-05T01:13:31.871164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14371","created_at":"2026-07-05T01:13:31.871164+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CSZ2IL3SK6M","created_at":"2026-07-05T01:13:31.871164+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CSZ2IL3SK6MJDOP","created_at":"2026-07-05T01:13:31.871164+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CSZ2IL3","created_at":"2026-07-05T01:13:31.871164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY","json":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY.json","graph_json":"https://pith.science/api/pith-number/7CSZ2IL3SK6MJDOPSXJZEWOKKY/graph.json","events_json":"https://pith.science/api/pith-number/7CSZ2IL3SK6MJDOPSXJZEWOKKY/events.json","paper":"https://pith.science/paper/7CSZ2IL3"},"agent_actions":{"view_html":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY","download_json":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY.json","view_paper":"https://pith.science/paper/7CSZ2IL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14371&json=true","fetch_graph":"https://pith.science/api/pith-number/7CSZ2IL3SK6MJDOPSXJZEWOKKY/graph.json","fetch_events":"https://pith.science/api/pith-number/7CSZ2IL3SK6MJDOPSXJZEWOKKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/action/storage_attestation","attest_author":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/action/author_attestation","sign_citation":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/action/citation_signature","submit_replication":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/action/replication_record"}},"created_at":"2026-07-05T01:13:31.871164+00:00","updated_at":"2026-07-05T01:13:31.871164+00:00"}