{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:72IVGE2BSA2327NFSUWX3RSZKA","short_pith_number":"pith:72IVGE2B","canonical_record":{"source":{"id":"2007.13171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-26T16:29:39Z","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"title_canon_sha256":"8f88a1662eae546555def7057c95ee7fe8adfe9e43a069d74166a2b296276548","abstract_canon_sha256":"3195e90e7a79095875e90d32faf7b1cd933f62384e0f904f47e74f79a07e6550"},"schema_version":"1.0"},"canonical_sha256":"fe915313419035bd7da5952d7dc6595027996a078e8a7c6a17668bcae3530db1","source":{"kind":"arxiv","id":"2007.13171","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13171","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13171v2","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13171","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"72IVGE2BSA23","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"72IVGE2BSA2327NF","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"72IVGE2B","created_at":"2026-07-05T02:33:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:72IVGE2BSA2327NFSUWX3RSZKA","target":"record","payload":{"canonical_record":{"source":{"id":"2007.13171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-26T16:29:39Z","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"title_canon_sha256":"8f88a1662eae546555def7057c95ee7fe8adfe9e43a069d74166a2b296276548","abstract_canon_sha256":"3195e90e7a79095875e90d32faf7b1cd933f62384e0f904f47e74f79a07e6550"},"schema_version":"1.0"},"canonical_sha256":"fe915313419035bd7da5952d7dc6595027996a078e8a7c6a17668bcae3530db1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:19.061787Z","signature_b64":"8AdgC/MlwLgec7cnUj7eAf2DuFYDvcqlYvhAX1wwLg14ZXlz9Ul9AvbPPO5u2taNWxPHC9FcQLcFjGzB5P3DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe915313419035bd7da5952d7dc6595027996a078e8a7c6a17668bcae3530db1","last_reissued_at":"2026-07-05T02:33:19.061364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:19.061364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.13171","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":"2026-07-05T02:33:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvFumFqTVM7O/XUl0eb5MbkvIWd96NkjeWcvbXszY/iaYAPJIxqCrtvUweMip4ay299z5lHDE/1xuxAl71hxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:16:22.764325Z"},"content_sha256":"056ca6e9884395e89ab07b40c46d11c3535116334c3e8e1dd5f840f55a8146aa","schema_version":"1.0","event_id":"sha256:056ca6e9884395e89ab07b40c46d11c3535116334c3e8e1dd5f840f55a8146aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:72IVGE2BSA2327NFSUWX3RSZKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bart van Bloemen Waanders, Elizabeth Newman, Joseph Hart, Lars Ruthotto","submitted_at":"2020-07-26T16:29:39Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and segmentation. The ability of DNNs to efficiently approximate high-dimensional functions has also motivated their use in scientific applications, e.g., to solve partial differential equations (PDE) and to generate surrogate models. In this paper, we consider the supervised training of DNNs, which arises in many of the above applications. We focus on the central problem of optimizing the weights of the given DNN such th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13171","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.13171/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":"2026-07-05T02:33:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlUkn0dSYRPW4XTUYCMeglDvgSJCHPgd60tb6u8COiCl+w5z+XSHziiSRitiJ0uTef5PuBBolM5g1ILkwbauAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:16:22.764829Z"},"content_sha256":"d8e7d7acab80323a891398dc1ae3673cbc646a1e66b37ab616f641865b7f46a7","schema_version":"1.0","event_id":"sha256:d8e7d7acab80323a891398dc1ae3673cbc646a1e66b37ab616f641865b7f46a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72IVGE2BSA2327NFSUWX3RSZKA/bundle.json","state_url":"https://pith.science/pith/72IVGE2BSA2327NFSUWX3RSZKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72IVGE2BSA2327NFSUWX3RSZKA/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":"2026-08-08T09:16:22Z","links":{"resolver":"https://pith.science/pith/72IVGE2BSA2327NFSUWX3RSZKA","bundle":"https://pith.science/pith/72IVGE2BSA2327NFSUWX3RSZKA/bundle.json","state":"https://pith.science/pith/72IVGE2BSA2327NFSUWX3RSZKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72IVGE2BSA2327NFSUWX3RSZKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:72IVGE2BSA2327NFSUWX3RSZKA","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":"3195e90e7a79095875e90d32faf7b1cd933f62384e0f904f47e74f79a07e6550","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-26T16:29:39Z","title_canon_sha256":"8f88a1662eae546555def7057c95ee7fe8adfe9e43a069d74166a2b296276548"},"schema_version":"1.0","source":{"id":"2007.13171","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13171","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13171v2","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13171","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"72IVGE2BSA23","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"72IVGE2BSA2327NF","created_at":"2026-07-05T02:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"72IVGE2B","created_at":"2026-07-05T02:33:19Z"}],"graph_snapshots":[{"event_id":"sha256:d8e7d7acab80323a891398dc1ae3673cbc646a1e66b37ab616f641865b7f46a7","target":"graph","created_at":"2026-07-05T02:33:19Z","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/2007.13171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and segmentation. The ability of DNNs to efficiently approximate high-dimensional functions has also motivated their use in scientific applications, e.g., to solve partial differential equations (PDE) and to generate surrogate models. In this paper, we consider the supervised training of DNNs, which arises in many of the above applications. We focus on the central problem of optimizing the weights of the given DNN such th","authors_text":"Bart van Bloemen Waanders, Elizabeth Newman, Joseph Hart, Lars Ruthotto","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-26T16:29:39Z","title":"Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13171","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":"sha256:056ca6e9884395e89ab07b40c46d11c3535116334c3e8e1dd5f840f55a8146aa","target":"record","created_at":"2026-07-05T02:33:19Z","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":"3195e90e7a79095875e90d32faf7b1cd933f62384e0f904f47e74f79a07e6550","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-26T16:29:39Z","title_canon_sha256":"8f88a1662eae546555def7057c95ee7fe8adfe9e43a069d74166a2b296276548"},"schema_version":"1.0","source":{"id":"2007.13171","kind":"arxiv","version":2}},"canonical_sha256":"fe915313419035bd7da5952d7dc6595027996a078e8a7c6a17668bcae3530db1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe915313419035bd7da5952d7dc6595027996a078e8a7c6a17668bcae3530db1","first_computed_at":"2026-07-05T02:33:19.061364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:19.061364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8AdgC/MlwLgec7cnUj7eAf2DuFYDvcqlYvhAX1wwLg14ZXlz9Ul9AvbPPO5u2taNWxPHC9FcQLcFjGzB5P3DBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:19.061787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.13171","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:056ca6e9884395e89ab07b40c46d11c3535116334c3e8e1dd5f840f55a8146aa","sha256:d8e7d7acab80323a891398dc1ae3673cbc646a1e66b37ab616f641865b7f46a7"],"state_sha256":"4864bcb0fa04f8d40525dc55f942224177cc96be5b167d45753dc108b7c8dcc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iBdM6xihxy3z3n4eYl+YRXmKxkFQRJP4EKL+uaA1yWx7FbTHIp1PFRzqInNqSIgFVEdFscHxjIGQVhWVaok1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:16:22.768598Z","bundle_sha256":"5544c81aa42faa0b269f00b685d071c97e3221af635517975bf0fc21faa20761"}}