{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4VOQX6F66KBTAC2V5SS7M4VHXR","short_pith_number":"pith:4VOQX6F6","canonical_record":{"source":{"id":"2010.07243","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T17:03:58Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c49336177e681a8d470f1a2fb515298f9bcf9f48e0f6759ee8defdfbb175aa12","abstract_canon_sha256":"e71d119ba76b21df08277ba5b488d8a56d14f50588c87dde88a6d840ad94006e"},"schema_version":"1.0"},"canonical_sha256":"e55d0bf8bef283300b55eca5f672a7bc47b5625dd90c1d4c5dd136d4cf45808b","source":{"kind":"arxiv","id":"2010.07243","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07243","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07243v2","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07243","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"4VOQX6F66KBT","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"4VOQX6F66KBTAC2V","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"4VOQX6F6","created_at":"2026-07-05T01:44:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4VOQX6F66KBTAC2V5SS7M4VHXR","target":"record","payload":{"canonical_record":{"source":{"id":"2010.07243","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T17:03:58Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c49336177e681a8d470f1a2fb515298f9bcf9f48e0f6759ee8defdfbb175aa12","abstract_canon_sha256":"e71d119ba76b21df08277ba5b488d8a56d14f50588c87dde88a6d840ad94006e"},"schema_version":"1.0"},"canonical_sha256":"e55d0bf8bef283300b55eca5f672a7bc47b5625dd90c1d4c5dd136d4cf45808b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:51.252245Z","signature_b64":"Sjk4iQTHhza1WLQHzyXCWHctnFMyMxMaZXNpCPpGpl3uSaAeTbuPCNO9IM+/cGA2gdRWGrM/t7U1qvGz73SnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e55d0bf8bef283300b55eca5f672a7bc47b5625dd90c1d4c5dd136d4cf45808b","last_reissued_at":"2026-07-05T01:44:51.251829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:51.251829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.07243","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":"2026-07-05T01:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybcdnMeXBjHBSSlMIJVMXMgCH/tVya4gQ6X+SfpyKubCJ89jBP4P50Z5dSr7ojH7vNsrj4eJd1/gSpMs53LPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:10:17.998263Z"},"content_sha256":"2ee9fd110f2cad6c7384b4eb119336a4e8db7ecb1c845cf620417fd845628b27","schema_version":"1.0","event_id":"sha256:2ee9fd110f2cad6c7384b4eb119336a4e8db7ecb1c845cf620417fd845628b27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4VOQX6F66KBTAC2V5SS7M4VHXR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Neural Network Training with Frank-Wolfe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Christoph Spiegel, Max Zimmer, Sebastian Pokutta","submitted_at":"2020-10-14T17:03:58Z","abstract_excerpt":"This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw comparisons both to current state-of-the-art stochastic Gradient Descent methods as well as across different variants of stochastic Conditional Gradients. In particular, we show the general feasibility of training Neural Networks whose parameters are constrained by a convex feasible region using Frank-Wolfe algorithms and compare different stochastic variants. We th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07243","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/2010.07243/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":"2026-07-05T01:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0N8uF3wI8sQmbhcIDrw6vd2pH6g0gRV9+vkQgjmpFuN9wNWyBc2fP47tdMhVzsB4vbt1AbjtoR4QhkVjIDgkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:10:18.000201Z"},"content_sha256":"00db2b3c3a055f2eefb6aa2be998ea1ff357a4fb4c05d47bcb8cfdf0d4999764","schema_version":"1.0","event_id":"sha256:00db2b3c3a055f2eefb6aa2be998ea1ff357a4fb4c05d47bcb8cfdf0d4999764"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VOQX6F66KBTAC2V5SS7M4VHXR/bundle.json","state_url":"https://pith.science/pith/4VOQX6F66KBTAC2V5SS7M4VHXR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VOQX6F66KBTAC2V5SS7M4VHXR/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":"2026-08-04T18:10:18Z","links":{"resolver":"https://pith.science/pith/4VOQX6F66KBTAC2V5SS7M4VHXR","bundle":"https://pith.science/pith/4VOQX6F66KBTAC2V5SS7M4VHXR/bundle.json","state":"https://pith.science/pith/4VOQX6F66KBTAC2V5SS7M4VHXR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VOQX6F66KBTAC2V5SS7M4VHXR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4VOQX6F66KBTAC2V5SS7M4VHXR","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":"e71d119ba76b21df08277ba5b488d8a56d14f50588c87dde88a6d840ad94006e","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T17:03:58Z","title_canon_sha256":"c49336177e681a8d470f1a2fb515298f9bcf9f48e0f6759ee8defdfbb175aa12"},"schema_version":"1.0","source":{"id":"2010.07243","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07243","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07243v2","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07243","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"4VOQX6F66KBT","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"4VOQX6F66KBTAC2V","created_at":"2026-07-05T01:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"4VOQX6F6","created_at":"2026-07-05T01:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:00db2b3c3a055f2eefb6aa2be998ea1ff357a4fb4c05d47bcb8cfdf0d4999764","target":"graph","created_at":"2026-07-05T01:44:51Z","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/2010.07243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw comparisons both to current state-of-the-art stochastic Gradient Descent methods as well as across different variants of stochastic Conditional Gradients. In particular, we show the general feasibility of training Neural Networks whose parameters are constrained by a convex feasible region using Frank-Wolfe algorithms and compare different stochastic variants. We th","authors_text":"Christoph Spiegel, Max Zimmer, Sebastian Pokutta","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T17:03:58Z","title":"Deep Neural Network Training with Frank-Wolfe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07243","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":"sha256:2ee9fd110f2cad6c7384b4eb119336a4e8db7ecb1c845cf620417fd845628b27","target":"record","created_at":"2026-07-05T01:44:51Z","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":"e71d119ba76b21df08277ba5b488d8a56d14f50588c87dde88a6d840ad94006e","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T17:03:58Z","title_canon_sha256":"c49336177e681a8d470f1a2fb515298f9bcf9f48e0f6759ee8defdfbb175aa12"},"schema_version":"1.0","source":{"id":"2010.07243","kind":"arxiv","version":2}},"canonical_sha256":"e55d0bf8bef283300b55eca5f672a7bc47b5625dd90c1d4c5dd136d4cf45808b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e55d0bf8bef283300b55eca5f672a7bc47b5625dd90c1d4c5dd136d4cf45808b","first_computed_at":"2026-07-05T01:44:51.251829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:51.251829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sjk4iQTHhza1WLQHzyXCWHctnFMyMxMaZXNpCPpGpl3uSaAeTbuPCNO9IM+/cGA2gdRWGrM/t7U1qvGz73SnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:51.252245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07243","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ee9fd110f2cad6c7384b4eb119336a4e8db7ecb1c845cf620417fd845628b27","sha256:00db2b3c3a055f2eefb6aa2be998ea1ff357a4fb4c05d47bcb8cfdf0d4999764"],"state_sha256":"8a7d0ac2cfde2f82fefe11163d45677f7b3716ced6f2ade75d142a7c3cfe3d5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PA1q1sBHJ49hAoiCbuw4PChteO4v9kKA33meunir+IkfmipAfT+llEV5vNwvUdKZrc5Fdq1+bWDi0vs/hjSeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:10:18.006826Z","bundle_sha256":"b993165121c3b69bf0fda789d52363df8282cefc4451184a2e417dd414b7008f"}}