{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NOXWU5OZJMCMHQO5WZ725FDNKZ","short_pith_number":"pith:NOXWU5OZ","canonical_record":{"source":{"id":"1804.09554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-04-24T13:52:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"48b5c7ebb4a6335a956bfa2e3b4d5f4c3c75b1d59f524fd00caafc938c915733","abstract_canon_sha256":"f1e8dc0aed37c16c071e67ec7ee0cd0873641f38425ae62f3c4ba7798ad6feaf"},"schema_version":"1.0"},"canonical_sha256":"6baf6a75d94b04c3c1ddb67fae946d5652ae9f0499db38f9e65b226a23f952d1","source":{"kind":"arxiv","id":"1804.09554","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09554","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09554v2","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09554","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"pith_short_12","alias_value":"NOXWU5OZJMCM","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NOXWU5OZJMCMHQO5","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NOXWU5OZ","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NOXWU5OZJMCMHQO5WZ725FDNKZ","target":"record","payload":{"canonical_record":{"source":{"id":"1804.09554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-04-24T13:52:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"48b5c7ebb4a6335a956bfa2e3b4d5f4c3c75b1d59f524fd00caafc938c915733","abstract_canon_sha256":"f1e8dc0aed37c16c071e67ec7ee0cd0873641f38425ae62f3c4ba7798ad6feaf"},"schema_version":"1.0"},"canonical_sha256":"6baf6a75d94b04c3c1ddb67fae946d5652ae9f0499db38f9e65b226a23f952d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:09.490825Z","signature_b64":"J34a3zYPWHIxRhBmx3Wvmmmeb+T1Cs+XpY9I6xgiTbn9wv1/FRBgdjwXpQLix5dnCSMslFYqAaE0MbaV0xx6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6baf6a75d94b04c3c1ddb67fae946d5652ae9f0499db38f9e65b226a23f952d1","last_reissued_at":"2026-05-18T00:01:09.490087Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:09.490087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.09554","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":"2026-05-18T00:01:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJXxcy544fD27js/sc2j0iguq9K4Y0HM2JVV8v+Eyuigxn/4UlTfpSUHv/5KwVdFbsYYQxKf14zUINOGGyS7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T10:26:36.668219Z"},"content_sha256":"6ad203823adb807e0f31efa3cdd36b7f7c38e5e6c3e07029b5b670656d9d4780","schema_version":"1.0","event_id":"sha256:6ad203823adb807e0f31efa3cdd36b7f7c38e5e6c3e07029b5b670656d9d4780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NOXWU5OZJMCMHQO5WZ725FDNKZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Amin Karbasi, Aryan Mokhtari, Hamed Hassani","submitted_at":"2018-04-24T13:52:29Z","abstract_excerpt":"This paper considers stochastic optimization problems for a large class of objective functions, including convex and continuous submodular. Stochastic proximal gradient methods have been widely used to solve such problems; however, their applicability remains limited when the problem dimension is large and the projection onto a convex set is costly. Instead, stochastic conditional gradient methods are proposed as an alternative solution relying on (i) Approximating gradients via a simple averaging technique requiring a single stochastic gradient evaluation per iteration; (ii) Solving a linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09554","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":""},"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":"2026-05-18T00:01:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4p5oJg00HBcv7HSA3jt53tLdcMIPekyghj1nskt8vMpdY2PWq4eSQRrzfTXUPqYMH+SEwLpXo37AVwm+IiVgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T10:26:36.668576Z"},"content_sha256":"b6679c11e9105296ed572d01ba5f0e0a86039e7fcf482f1e91d38e459de21023","schema_version":"1.0","event_id":"sha256:b6679c11e9105296ed572d01ba5f0e0a86039e7fcf482f1e91d38e459de21023"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ/bundle.json","state_url":"https://pith.science/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ/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":"2026-06-02T10:26:36Z","links":{"resolver":"https://pith.science/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ","bundle":"https://pith.science/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ/bundle.json","state":"https://pith.science/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOXWU5OZJMCMHQO5WZ725FDNKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NOXWU5OZJMCMHQO5WZ725FDNKZ","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":"f1e8dc0aed37c16c071e67ec7ee0cd0873641f38425ae62f3c4ba7798ad6feaf","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-04-24T13:52:29Z","title_canon_sha256":"48b5c7ebb4a6335a956bfa2e3b4d5f4c3c75b1d59f524fd00caafc938c915733"},"schema_version":"1.0","source":{"id":"1804.09554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09554","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09554v2","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09554","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"pith_short_12","alias_value":"NOXWU5OZJMCM","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NOXWU5OZJMCMHQO5","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NOXWU5OZ","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:b6679c11e9105296ed572d01ba5f0e0a86039e7fcf482f1e91d38e459de21023","target":"graph","created_at":"2026-05-18T00:01:09Z","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"},"paper":{"abstract_excerpt":"This paper considers stochastic optimization problems for a large class of objective functions, including convex and continuous submodular. Stochastic proximal gradient methods have been widely used to solve such problems; however, their applicability remains limited when the problem dimension is large and the projection onto a convex set is costly. Instead, stochastic conditional gradient methods are proposed as an alternative solution relying on (i) Approximating gradients via a simple averaging technique requiring a single stochastic gradient evaluation per iteration; (ii) Solving a linear ","authors_text":"Amin Karbasi, Aryan Mokhtari, Hamed Hassani","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-04-24T13:52:29Z","title":"Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09554","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":"sha256:6ad203823adb807e0f31efa3cdd36b7f7c38e5e6c3e07029b5b670656d9d4780","target":"record","created_at":"2026-05-18T00:01:09Z","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":"f1e8dc0aed37c16c071e67ec7ee0cd0873641f38425ae62f3c4ba7798ad6feaf","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-04-24T13:52:29Z","title_canon_sha256":"48b5c7ebb4a6335a956bfa2e3b4d5f4c3c75b1d59f524fd00caafc938c915733"},"schema_version":"1.0","source":{"id":"1804.09554","kind":"arxiv","version":2}},"canonical_sha256":"6baf6a75d94b04c3c1ddb67fae946d5652ae9f0499db38f9e65b226a23f952d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6baf6a75d94b04c3c1ddb67fae946d5652ae9f0499db38f9e65b226a23f952d1","first_computed_at":"2026-05-18T00:01:09.490087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:09.490087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J34a3zYPWHIxRhBmx3Wvmmmeb+T1Cs+XpY9I6xgiTbn9wv1/FRBgdjwXpQLix5dnCSMslFYqAaE0MbaV0xx6AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:09.490825Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.09554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ad203823adb807e0f31efa3cdd36b7f7c38e5e6c3e07029b5b670656d9d4780","sha256:b6679c11e9105296ed572d01ba5f0e0a86039e7fcf482f1e91d38e459de21023"],"state_sha256":"22203172e86c1fb37cf82962c3920deab214a9b91a070642cb29444d9c59ce32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RiURWfUCPxL/NQWItsDrTVU3PMB8fHwuvRs2K+UjZHV++YPRTJFXPqgD0cq1Wj3gvP5FTRgptzISV8edJU07Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T10:26:36.670368Z","bundle_sha256":"32212b3a752fca1a3fd96b3271e00fd44c639ab60f681eb52b4772325ccc0b7e"}}