{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JH7TE4QKA7B5BKGAPBQ45GN645","short_pith_number":"pith:JH7TE4QK","canonical_record":{"source":{"id":"2005.01209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-03T23:41:35Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5584a894798eea5e5b3c24f39cf1beccd7746ab9b0ca34c0d4e28dcc32be08ab","abstract_canon_sha256":"cb6f31f1cb28ec943e8d0e3b0e3b146e0791c17746080026dbe85709e917c47a"},"schema_version":"1.0"},"canonical_sha256":"49ff32720a07c3d0a8c07861ce99bee7665f858526da2e837f1eaecfafd3c4b3","source":{"kind":"arxiv","id":"2005.01209","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01209","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01209v2","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01209","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"JH7TE4QKA7B5","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"JH7TE4QKA7B5BKGA","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"JH7TE4QK","created_at":"2026-07-05T04:06:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JH7TE4QKA7B5BKGAPBQ45GN645","target":"record","payload":{"canonical_record":{"source":{"id":"2005.01209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-03T23:41:35Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5584a894798eea5e5b3c24f39cf1beccd7746ab9b0ca34c0d4e28dcc32be08ab","abstract_canon_sha256":"cb6f31f1cb28ec943e8d0e3b0e3b146e0791c17746080026dbe85709e917c47a"},"schema_version":"1.0"},"canonical_sha256":"49ff32720a07c3d0a8c07861ce99bee7665f858526da2e837f1eaecfafd3c4b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:39.968697Z","signature_b64":"Rmv1aRdAqJsv8DweyJshzLgw87pQBc53eeIDujCg5xYsw8ULX+Qd5G3U2bN1nqUMHYuHjXe9Az4ZwclKScweDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49ff32720a07c3d0a8c07861ce99bee7665f858526da2e837f1eaecfafd3c4b3","last_reissued_at":"2026-07-05T04:06:39.968261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:39.968261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.01209","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":"2026-07-05T04:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CD0hPwEH+JWHjeUiVQOtZ4BNqejX1dlixxzAw4Nch9xWSQXumDu6vtSi611D0MdK8xaQ7ESwnnUr3e3tfOqNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:30:05.283276Z"},"content_sha256":"75725aa036f6ad8142f20bf623654d1d1124385cfed5084e051424652ce73646","schema_version":"1.0","event_id":"sha256:75725aa036f6ad8142f20bf623654d1d1124385cfed5084e051424652ce73646"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JH7TE4QKA7B5BKGAPBQ45GN645","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Bokun Wang, Lingzhou Xue, Shiqian Ma","submitted_at":"2020-05-03T23:41:35Z","abstract_excerpt":"Riemannian optimization has drawn a lot of attention due to its wide applications in practice. Riemannian stochastic first-order algorithms have been studied in the literature to solve large-scale machine learning problems over Riemannian manifolds. However, most of the existing Riemannian stochastic algorithms require the objective function to be differentiable, and they do not apply to the case where the objective function is nonsmooth. In this paper, we present two Riemannian stochastic proximal gradient methods for minimizing nonsmooth function over the Stiefel manifold. The two methods, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01209","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/2005.01209/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":"2026-07-05T04:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SCC6GFZFooNv5RpN4g7dLJQfjX6zBydu6XDQt3GXcm5dFaPJh5IWfs3NSAqTqlcBYsw4T4yTHa8r6WNQtGqvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:30:05.284227Z"},"content_sha256":"4abf38514886043cc213b7091150607c77892cfc9573f137e4530790bce2bf28","schema_version":"1.0","event_id":"sha256:4abf38514886043cc213b7091150607c77892cfc9573f137e4530790bce2bf28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JH7TE4QKA7B5BKGAPBQ45GN645/bundle.json","state_url":"https://pith.science/pith/JH7TE4QKA7B5BKGAPBQ45GN645/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JH7TE4QKA7B5BKGAPBQ45GN645/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":"2026-08-04T22:30:05Z","links":{"resolver":"https://pith.science/pith/JH7TE4QKA7B5BKGAPBQ45GN645","bundle":"https://pith.science/pith/JH7TE4QKA7B5BKGAPBQ45GN645/bundle.json","state":"https://pith.science/pith/JH7TE4QKA7B5BKGAPBQ45GN645/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JH7TE4QKA7B5BKGAPBQ45GN645/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JH7TE4QKA7B5BKGAPBQ45GN645","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":"cb6f31f1cb28ec943e8d0e3b0e3b146e0791c17746080026dbe85709e917c47a","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-03T23:41:35Z","title_canon_sha256":"5584a894798eea5e5b3c24f39cf1beccd7746ab9b0ca34c0d4e28dcc32be08ab"},"schema_version":"1.0","source":{"id":"2005.01209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01209","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01209v2","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01209","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"JH7TE4QKA7B5","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"JH7TE4QKA7B5BKGA","created_at":"2026-07-05T04:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"JH7TE4QK","created_at":"2026-07-05T04:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:4abf38514886043cc213b7091150607c77892cfc9573f137e4530790bce2bf28","target":"graph","created_at":"2026-07-05T04:06:39Z","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/2005.01209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Riemannian optimization has drawn a lot of attention due to its wide applications in practice. Riemannian stochastic first-order algorithms have been studied in the literature to solve large-scale machine learning problems over Riemannian manifolds. However, most of the existing Riemannian stochastic algorithms require the objective function to be differentiable, and they do not apply to the case where the objective function is nonsmooth. In this paper, we present two Riemannian stochastic proximal gradient methods for minimizing nonsmooth function over the Stiefel manifold. The two methods, n","authors_text":"Bokun Wang, Lingzhou Xue, Shiqian Ma","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-03T23:41:35Z","title":"Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01209","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":"sha256:75725aa036f6ad8142f20bf623654d1d1124385cfed5084e051424652ce73646","target":"record","created_at":"2026-07-05T04:06:39Z","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":"cb6f31f1cb28ec943e8d0e3b0e3b146e0791c17746080026dbe85709e917c47a","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-03T23:41:35Z","title_canon_sha256":"5584a894798eea5e5b3c24f39cf1beccd7746ab9b0ca34c0d4e28dcc32be08ab"},"schema_version":"1.0","source":{"id":"2005.01209","kind":"arxiv","version":2}},"canonical_sha256":"49ff32720a07c3d0a8c07861ce99bee7665f858526da2e837f1eaecfafd3c4b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49ff32720a07c3d0a8c07861ce99bee7665f858526da2e837f1eaecfafd3c4b3","first_computed_at":"2026-07-05T04:06:39.968261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:39.968261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rmv1aRdAqJsv8DweyJshzLgw87pQBc53eeIDujCg5xYsw8ULX+Qd5G3U2bN1nqUMHYuHjXe9Az4ZwclKScweDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:39.968697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.01209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75725aa036f6ad8142f20bf623654d1d1124385cfed5084e051424652ce73646","sha256:4abf38514886043cc213b7091150607c77892cfc9573f137e4530790bce2bf28"],"state_sha256":"676f1ec8d801e2e340b296d3bb4629d7f135897fbd670c870fbc108ecaab49d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EW1EsR5RURtWVvwRC3MEwymcUV6g3smTLMWC7tpju+DRQRHY+sZ5Vip+ZA3rpMaTQ1Ta1WBPoxwZ2fJsNa8VAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:30:05.289438Z","bundle_sha256":"5a25013a4332d920bb598bf0a10c026791562544e51344b6b3deea824e206491"}}