{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:A5I6KUZULWVVHARJXWNF5KWYP3","short_pith_number":"pith:A5I6KUZU","canonical_record":{"source":{"id":"1807.03545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-10T09:24:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2f5c68caafe94173a4c0e07feb4d5afce041feaddb13665c7f3737ae6ad7384","abstract_canon_sha256":"1acd5f7119aa306694d746993b892797f6ac047cecf2cf5ad9997d7d2d810900"},"schema_version":"1.0"},"canonical_sha256":"0751e553345dab538229bd9a5eaad87ed69c0361b8ec124c0bf50281a68a6435","source":{"kind":"arxiv","id":"1807.03545","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03545","created_at":"2026-05-17T23:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03545v2","created_at":"2026-05-17T23:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03545","created_at":"2026-05-17T23:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"A5I6KUZULWVV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A5I6KUZULWVVHARJ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A5I6KUZU","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:A5I6KUZULWVVHARJXWNF5KWYP3","target":"record","payload":{"canonical_record":{"source":{"id":"1807.03545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-10T09:24:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2f5c68caafe94173a4c0e07feb4d5afce041feaddb13665c7f3737ae6ad7384","abstract_canon_sha256":"1acd5f7119aa306694d746993b892797f6ac047cecf2cf5ad9997d7d2d810900"},"schema_version":"1.0"},"canonical_sha256":"0751e553345dab538229bd9a5eaad87ed69c0361b8ec124c0bf50281a68a6435","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:14.088828Z","signature_b64":"MQ4hlgoC35UkZO8pYgbXcj8RMuYrUr/LuInTHlaDuCBkkP/TL3Q8+K5Znz1tW+jTGhkV0QWHbDhJZJWOtAbtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0751e553345dab538229bd9a5eaad87ed69c0361b8ec124c0bf50281a68a6435","last_reissued_at":"2026-05-17T23:58:14.088260Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:14.088260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.03545","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":"2026-05-17T23:58:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jc6OpucK/Vfv821NKfTb2a456SrgkxdPWQcMdUBehvC2JQ/ataWQVxgiwZGipr5Rygpg8Jb3qgZ4Z9y9bB6rAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:55:31.618182Z"},"content_sha256":"32ed722a685ef3f49a77d619ab75ea3d244c97fc47b28b8bae63b7cb3b903ac9","schema_version":"1.0","event_id":"sha256:32ed722a685ef3f49a77d619ab75ea3d244c97fc47b28b8bae63b7cb3b903ac9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:A5I6KUZULWVVHARJXWNF5KWYP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual optimization for convex constrained objectives without the gradient-Lipschitz assumption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emmanuel Bacry, Martin Bompaire, St\\'ephane Ga\\\"iffas","submitted_at":"2018-07-10T09:24:06Z","abstract_excerpt":"The minimization of convex objectives coming from linear supervised learning problems, such as penalized generalized linear models, can be formulated as finite sums of convex functions. For such problems, a large set of stochastic first-order solvers based on the idea of variance reduction are available and combine both computational efficiency and sound theoretical guarantees (linear convergence rates). Such rates are obtained under both gradient-Lipschitz and strong convexity assumptions. Motivated by learning problems that do not meet the gradient-Lipschitz assumption, such as linear Poisso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03545","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":"2026-05-17T23:58:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8/RsYg3hb20OV54dzTAAV4uFCaiD9D2nE8T6nARteY53KtVbk8vXEIPcE8xfTq19vtOQZ5oRiIyKdgX4c+UbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:55:31.618552Z"},"content_sha256":"d81f61d2014267a9426baf612784f9736084d4615d38737bdc46c426570bc152","schema_version":"1.0","event_id":"sha256:d81f61d2014267a9426baf612784f9736084d4615d38737bdc46c426570bc152"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5I6KUZULWVVHARJXWNF5KWYP3/bundle.json","state_url":"https://pith.science/pith/A5I6KUZULWVVHARJXWNF5KWYP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5I6KUZULWVVHARJXWNF5KWYP3/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":"2026-06-09T12:55:31Z","links":{"resolver":"https://pith.science/pith/A5I6KUZULWVVHARJXWNF5KWYP3","bundle":"https://pith.science/pith/A5I6KUZULWVVHARJXWNF5KWYP3/bundle.json","state":"https://pith.science/pith/A5I6KUZULWVVHARJXWNF5KWYP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5I6KUZULWVVHARJXWNF5KWYP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A5I6KUZULWVVHARJXWNF5KWYP3","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":"1acd5f7119aa306694d746993b892797f6ac047cecf2cf5ad9997d7d2d810900","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-10T09:24:06Z","title_canon_sha256":"c2f5c68caafe94173a4c0e07feb4d5afce041feaddb13665c7f3737ae6ad7384"},"schema_version":"1.0","source":{"id":"1807.03545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03545","created_at":"2026-05-17T23:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03545v2","created_at":"2026-05-17T23:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03545","created_at":"2026-05-17T23:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"A5I6KUZULWVV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A5I6KUZULWVVHARJ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A5I6KUZU","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:d81f61d2014267a9426baf612784f9736084d4615d38737bdc46c426570bc152","target":"graph","created_at":"2026-05-17T23:58:14Z","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":"The minimization of convex objectives coming from linear supervised learning problems, such as penalized generalized linear models, can be formulated as finite sums of convex functions. For such problems, a large set of stochastic first-order solvers based on the idea of variance reduction are available and combine both computational efficiency and sound theoretical guarantees (linear convergence rates). Such rates are obtained under both gradient-Lipschitz and strong convexity assumptions. Motivated by learning problems that do not meet the gradient-Lipschitz assumption, such as linear Poisso","authors_text":"Emmanuel Bacry, Martin Bompaire, St\\'ephane Ga\\\"iffas","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-10T09:24:06Z","title":"Dual optimization for convex constrained objectives without the gradient-Lipschitz assumption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03545","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":"sha256:32ed722a685ef3f49a77d619ab75ea3d244c97fc47b28b8bae63b7cb3b903ac9","target":"record","created_at":"2026-05-17T23:58:14Z","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":"1acd5f7119aa306694d746993b892797f6ac047cecf2cf5ad9997d7d2d810900","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-10T09:24:06Z","title_canon_sha256":"c2f5c68caafe94173a4c0e07feb4d5afce041feaddb13665c7f3737ae6ad7384"},"schema_version":"1.0","source":{"id":"1807.03545","kind":"arxiv","version":2}},"canonical_sha256":"0751e553345dab538229bd9a5eaad87ed69c0361b8ec124c0bf50281a68a6435","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0751e553345dab538229bd9a5eaad87ed69c0361b8ec124c0bf50281a68a6435","first_computed_at":"2026-05-17T23:58:14.088260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:14.088260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MQ4hlgoC35UkZO8pYgbXcj8RMuYrUr/LuInTHlaDuCBkkP/TL3Q8+K5Znz1tW+jTGhkV0QWHbDhJZJWOtAbtCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:14.088828Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32ed722a685ef3f49a77d619ab75ea3d244c97fc47b28b8bae63b7cb3b903ac9","sha256:d81f61d2014267a9426baf612784f9736084d4615d38737bdc46c426570bc152"],"state_sha256":"cb7053df5325515d5302dc56922bd518adbab139a426cb2d849e4f3f1cb9ebca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUQgAVzyoL/uL7uIgrmxr19fm4AhcmQ0MY/SBMxvMSPX64W0oJXwXjhKguQCa9uv0GG6xHw4wCzh7mTgD0fEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:55:31.620463Z","bundle_sha256":"93f47204bfa2aae0d57429f4eeb9e431db47cbe425f0cd4d4b655de6b7b34fee"}}