{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7CSZ2IL3SK6MJDOPSXJZEWOKKY","short_pith_number":"pith:7CSZ2IL3","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"},"canonical_sha256":"f8a59d217b92bcc48dcf95d39259ca5605f8bfb144deccccfd768aa4c2686d72","source":{"kind":"arxiv","id":"2006.14371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14371","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14371v1","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14371","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"7CSZ2IL3SK6M","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"7CSZ2IL3SK6MJDOP","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"7CSZ2IL3","created_at":"2026-07-05T01:13:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7CSZ2IL3SK6MJDOPSXJZEWOKKY","target":"record","payload":{"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"},"canonical_sha256":"f8a59d217b92bcc48dcf95d39259ca5605f8bfb144deccccfd768aa4c2686d72","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"},"source_kind":"arxiv","source_id":"2006.14371","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":"2026-07-05T01:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DIUho0Mt0sBqU3aiUXLKuqe2R4/ZsKnaI+mrtH0CFt6l6Csno/Ry6tGQ7TauFuOrZyeyLA6Mg/nmG1Z8COJ1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:19:54.751652Z"},"content_sha256":"835b9aa8617713f0415b4c757b8e327a97dfe9c9afeea4f433ab1e2a0afd6538","schema_version":"1.0","event_id":"sha256:835b9aa8617713f0415b4c757b8e327a97dfe9c9afeea4f433ab1e2a0afd6538"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7CSZ2IL3SK6MJDOPSXJZEWOKKY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2i82yUzviPGcdQWqqzt7zDEg973cBjMtbwf2aoRIXHaEzF1uWpR3QDg/Ot/uU4L22tKF19vIoDIBwlmUVQt8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:19:54.752024Z"},"content_sha256":"5733a8b07270196adef02891ad12230d1e0fb85e4a7e6da197ac65483b6878a6","schema_version":"1.0","event_id":"sha256:5733a8b07270196adef02891ad12230d1e0fb85e4a7e6da197ac65483b6878a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/bundle.json","state_url":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/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":"2026-07-07T10:19:54Z","links":{"resolver":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY","bundle":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/bundle.json","state":"https://pith.science/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CSZ2IL3SK6MJDOPSXJZEWOKKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7CSZ2IL3SK6MJDOPSXJZEWOKKY","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":"f0895121da49a51b5edfa734fc8c3ce786bdd2f58313797a36f2ba37c929fda9","cross_cats_sorted":["cs.CE","eess.SP","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T22:59:55Z","title_canon_sha256":"80326c0ec17897b1bea4761a6681a484290ab03589c5008f873bd1dfb4717ab5"},"schema_version":"1.0","source":{"id":"2006.14371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14371","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14371v1","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14371","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"7CSZ2IL3SK6M","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"7CSZ2IL3SK6MJDOP","created_at":"2026-07-05T01:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"7CSZ2IL3","created_at":"2026-07-05T01:13:31Z"}],"graph_snapshots":[{"event_id":"sha256:5733a8b07270196adef02891ad12230d1e0fb85e4a7e6da197ac65483b6878a6","target":"graph","created_at":"2026-07-05T01:13:31Z","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/2006.14371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gavin D. Portwood, Jean C. Ragusa, Mauricio E. Tano","cross_cats":["cs.CE","eess.SP","physics.comp-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T22:59:55Z","title":"Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14371","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":"sha256:835b9aa8617713f0415b4c757b8e327a97dfe9c9afeea4f433ab1e2a0afd6538","target":"record","created_at":"2026-07-05T01:13:31Z","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":"f0895121da49a51b5edfa734fc8c3ce786bdd2f58313797a36f2ba37c929fda9","cross_cats_sorted":["cs.CE","eess.SP","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T22:59:55Z","title_canon_sha256":"80326c0ec17897b1bea4761a6681a484290ab03589c5008f873bd1dfb4717ab5"},"schema_version":"1.0","source":{"id":"2006.14371","kind":"arxiv","version":1}},"canonical_sha256":"f8a59d217b92bcc48dcf95d39259ca5605f8bfb144deccccfd768aa4c2686d72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8a59d217b92bcc48dcf95d39259ca5605f8bfb144deccccfd768aa4c2686d72","first_computed_at":"2026-07-05T01:13:31.871108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:13:31.871108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NptxQO3EKMbeUYEdDbDlLNPuUOX7FSbLLj5/RVYsaR0yC0BGUc91f4LvUkuq7a9iaSCVxg+JNtjgMo/E+9jtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:13:31.871505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.14371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:835b9aa8617713f0415b4c757b8e327a97dfe9c9afeea4f433ab1e2a0afd6538","sha256:5733a8b07270196adef02891ad12230d1e0fb85e4a7e6da197ac65483b6878a6"],"state_sha256":"f73978ea0d58ef7e6fbe4972cba52f61753f0a88b368a96b40158c2f5c6d9f41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1AmtwtfxQ679zDK3GGWp3wj+WANGV+4Q3Fv+oOXxdTpauxStUfCIepljkzXaAY2HSpEns2EaQ1iiuOU4H4KDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:19:54.757124Z","bundle_sha256":"0e6baa8e58c80e81d68fbfee12902e7a8062191c9d233911fc01b1dddd420b80"}}