{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:57AUUJAEAMMXTZ7IWUHVM3XSAL","short_pith_number":"pith:57AUUJAE","canonical_record":{"source":{"id":"2502.07529","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T13:10:34Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"9e53f7a72f384884a4531cd4b63c7246a2a95065ea0c7e0972312afaffd25816","abstract_canon_sha256":"fc403908c7efc199015d6bd89b7d5fe565d4c174eac1238491602e3a7bbe35dd"},"schema_version":"1.0"},"canonical_sha256":"efc14a2404031979e7e8b50f566ef202eeeb6dcbb1c7db9b7105fdbd73334c2e","source":{"kind":"arxiv","id":"2502.07529","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07529","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07529v2","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07529","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"57AUUJAEAMMX","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"57AUUJAEAMMXTZ7I","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"57AUUJAE","created_at":"2026-05-21T21:14:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:57AUUJAEAMMXTZ7IWUHVM3XSAL","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07529","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T13:10:34Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"9e53f7a72f384884a4531cd4b63c7246a2a95065ea0c7e0972312afaffd25816","abstract_canon_sha256":"fc403908c7efc199015d6bd89b7d5fe565d4c174eac1238491602e3a7bbe35dd"},"schema_version":"1.0"},"canonical_sha256":"efc14a2404031979e7e8b50f566ef202eeeb6dcbb1c7db9b7105fdbd73334c2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T21:14:43.496681Z","signature_b64":"sMhCXS0QIkM3M/qOD7Pbsf0ke7gluGyZGsNhCFIFTT68XGgB4UNGS9z/zbTAg9xXragOh9/V7Yq0/sdrcsH5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc14a2404031979e7e8b50f566ef202eeeb6dcbb1c7db9b7105fdbd73334c2e","last_reissued_at":"2026-05-21T21:14:43.494748Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T21:14:43.494748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07529","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":"2026-05-21T21:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eE8AbC/Ol73CuxJB+/Bg1BzFgMhyarIBcGQ79gse638R0MMDvloKcTDRK4qm/WxCNtj6CIP2odnzJ0ceNoCoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T12:00:59.663630Z"},"content_sha256":"25151fe22ea90c2f805bbaaf3373e2b3a86de7cd230af3335f1cdeb005c96ba4","schema_version":"1.0","event_id":"sha256:25151fe22ea90c2f805bbaaf3373e2b3a86de7cd230af3335f1cdeb005c96ba4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:57AUUJAEAMMXTZ7IWUHVM3XSAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Deep Learning Models with Norm-Constrained LMOs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Antonio Silveti-Falls, Kimon Antonakopoulos, Thomas Pethick, Volkan Cevher, Wanyun Xie, Zhenyu Zhu","submitted_at":"2025-02-11T13:10:34Z","abstract_excerpt":"In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained problems. The resulting update rule unifies several existing optimization methods under a single framework. Furthermore, we propose an explicit choice of norm for deep architectures, which, as a side benefit, leads to the transferability of hyperparameters across model sizes. Experimentally, we demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07529","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/2502.07529/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":"2026-05-21T21:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFnUqKcj/WY9sNbpt1GmZFX5Y7qhQBwGhUDOUM88EImu5eeAaLhB6W4k9IP5gWhcCVgtMG63sVQ2JCn+H+huAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T12:00:59.664353Z"},"content_sha256":"97f8529bcad2a60c10e741c894db629c8275b97eab3c1f8811cf4ba2c776a46f","schema_version":"1.0","event_id":"sha256:97f8529bcad2a60c10e741c894db629c8275b97eab3c1f8811cf4ba2c776a46f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL/bundle.json","state_url":"https://pith.science/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL/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":"2026-05-22T12:00:59Z","links":{"resolver":"https://pith.science/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL","bundle":"https://pith.science/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL/bundle.json","state":"https://pith.science/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57AUUJAEAMMXTZ7IWUHVM3XSAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:57AUUJAEAMMXTZ7IWUHVM3XSAL","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":"fc403908c7efc199015d6bd89b7d5fe565d4c174eac1238491602e3a7bbe35dd","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T13:10:34Z","title_canon_sha256":"9e53f7a72f384884a4531cd4b63c7246a2a95065ea0c7e0972312afaffd25816"},"schema_version":"1.0","source":{"id":"2502.07529","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07529","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07529v2","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07529","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"57AUUJAEAMMX","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"57AUUJAEAMMXTZ7I","created_at":"2026-05-21T21:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"57AUUJAE","created_at":"2026-05-21T21:14:43Z"}],"graph_snapshots":[{"event_id":"sha256:97f8529bcad2a60c10e741c894db629c8275b97eab3c1f8811cf4ba2c776a46f","target":"graph","created_at":"2026-05-21T21:14:43Z","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/2502.07529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained problems. The resulting update rule unifies several existing optimization methods under a single framework. Furthermore, we propose an explicit choice of norm for deep architectures, which, as a side benefit, leads to the transferability of hyperparameters across model sizes. Experimentally, we demonstrat","authors_text":"Antonio Silveti-Falls, Kimon Antonakopoulos, Thomas Pethick, Volkan Cevher, Wanyun Xie, Zhenyu Zhu","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T13:10:34Z","title":"Training Deep Learning Models with Norm-Constrained LMOs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07529","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":"sha256:25151fe22ea90c2f805bbaaf3373e2b3a86de7cd230af3335f1cdeb005c96ba4","target":"record","created_at":"2026-05-21T21:14:43Z","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":"fc403908c7efc199015d6bd89b7d5fe565d4c174eac1238491602e3a7bbe35dd","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T13:10:34Z","title_canon_sha256":"9e53f7a72f384884a4531cd4b63c7246a2a95065ea0c7e0972312afaffd25816"},"schema_version":"1.0","source":{"id":"2502.07529","kind":"arxiv","version":2}},"canonical_sha256":"efc14a2404031979e7e8b50f566ef202eeeb6dcbb1c7db9b7105fdbd73334c2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efc14a2404031979e7e8b50f566ef202eeeb6dcbb1c7db9b7105fdbd73334c2e","first_computed_at":"2026-05-21T21:14:43.494748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T21:14:43.494748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sMhCXS0QIkM3M/qOD7Pbsf0ke7gluGyZGsNhCFIFTT68XGgB4UNGS9z/zbTAg9xXragOh9/V7Yq0/sdrcsH5Dw==","signature_status":"signed_v1","signed_at":"2026-05-21T21:14:43.496681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07529","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25151fe22ea90c2f805bbaaf3373e2b3a86de7cd230af3335f1cdeb005c96ba4","sha256:97f8529bcad2a60c10e741c894db629c8275b97eab3c1f8811cf4ba2c776a46f"],"state_sha256":"8745c171a05d4dbd856afd8f5a7f92d1ccc9ebee345649fb6f56bed907bf735d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+4A9XlDMQcOb/x7B6ndFeNOo82Jop0kWhgZi/4kbyYzz3Qcl3R7fRuhxr16cuI14g7n2dcR6wPZo5SwLYbnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T12:00:59.667902Z","bundle_sha256":"6fecdfbb3e5a1475add9d0405b707cb47cf4cb5ebfd0751841446bc7ce506914"}}