{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XO27GVMYFLI2ZEGDOLPGHOIMBL","short_pith_number":"pith:XO27GVMY","canonical_record":{"source":{"id":"1605.06398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T15:16:29Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5e96b68c0aaabfec7e663f3b29e00a0a245dcce24266fd384c4f984bd864f5fd","abstract_canon_sha256":"6628a7c987e4bf179d888b3a7c18d4984afa815563945c7f296d0974b90e07ee"},"schema_version":"1.0"},"canonical_sha256":"bbb5f355982ad1ac90c372de63b90c0ae1a77721d629703175d6f8f96ceb5fe2","source":{"kind":"arxiv","id":"1605.06398","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06398","created_at":"2026-05-18T01:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06398v2","created_at":"2026-05-18T01:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06398","created_at":"2026-05-18T01:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"XO27GVMYFLI2","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XO27GVMYFLI2ZEGD","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XO27GVMY","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XO27GVMYFLI2ZEGDOLPGHOIMBL","target":"record","payload":{"canonical_record":{"source":{"id":"1605.06398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T15:16:29Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5e96b68c0aaabfec7e663f3b29e00a0a245dcce24266fd384c4f984bd864f5fd","abstract_canon_sha256":"6628a7c987e4bf179d888b3a7c18d4984afa815563945c7f296d0974b90e07ee"},"schema_version":"1.0"},"canonical_sha256":"bbb5f355982ad1ac90c372de63b90c0ae1a77721d629703175d6f8f96ceb5fe2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:19.355901Z","signature_b64":"SS0Q/HHUl7G+IcSCOhW7ov/TUK/VOf3VubqxwdclfmLzvnsSkvQYyiqvExiTl2Ln11iIwNxon2bVERR7B22UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbb5f355982ad1ac90c372de63b90c0ae1a77721d629703175d6f8f96ceb5fe2","last_reissued_at":"2026-05-18T01:00:19.355138Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:19.355138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.06398","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":"2026-05-18T01:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8n9YuUua7vsr02gG5Tp4W+N0FQsNMVzbZmLW3XyR9h539hj5OIE9361OdWKFWXTLtesLX5uQpC6GFcL0YW5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:52:00.841304Z"},"content_sha256":"db508a7bce3ffbf20ff105cd662bf15a1b1ac2c360115738a8a5daa347bccb6a","schema_version":"1.0","event_id":"sha256:db508a7bce3ffbf20ff105cd662bf15a1b1ac2c360115738a8a5daa347bccb6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XO27GVMYFLI2ZEGDOLPGHOIMBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Variance Reduction Methods for Saddle-Point Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Francis Bach (SIERRA, LIENS), P Balamurugan (SIERRA","submitted_at":"2016-05-20T15:16:29Z","abstract_excerpt":"We consider convex-concave saddle-point problems where the objective functions may be split in many components, and extend recent stochastic variance reduction methods (such as SVRG or SAGA) to provide the first large-scale linearly convergent algorithms for this class of problems which is common in machine learning. While the algorithmic extension is straightforward, it comes with challenges and opportunities: (a) the convex minimization analysis does not apply and we use the notion of monotone operators to prove convergence, showing in particular that the same algorithm applies to a larger c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06398","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":"2026-05-18T01:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHuYnRo03mSJRjw5Es5OsH6ipYERLG/Z1lfZBaRRKc7qqOqTu6TlOUkTgqeaiEpbaSI602dJOENcIx0FpqAZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:52:00.841680Z"},"content_sha256":"9e0bc28e6da96283a84ba26c7ebe7526d7572a3f5a0e744e9eb1c27d9b0abeea","schema_version":"1.0","event_id":"sha256:9e0bc28e6da96283a84ba26c7ebe7526d7572a3f5a0e744e9eb1c27d9b0abeea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL/bundle.json","state_url":"https://pith.science/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL/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":"2026-06-05T18:52:00Z","links":{"resolver":"https://pith.science/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL","bundle":"https://pith.science/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL/bundle.json","state":"https://pith.science/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XO27GVMYFLI2ZEGDOLPGHOIMBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XO27GVMYFLI2ZEGDOLPGHOIMBL","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":"6628a7c987e4bf179d888b3a7c18d4984afa815563945c7f296d0974b90e07ee","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T15:16:29Z","title_canon_sha256":"5e96b68c0aaabfec7e663f3b29e00a0a245dcce24266fd384c4f984bd864f5fd"},"schema_version":"1.0","source":{"id":"1605.06398","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06398","created_at":"2026-05-18T01:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06398v2","created_at":"2026-05-18T01:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06398","created_at":"2026-05-18T01:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"XO27GVMYFLI2","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XO27GVMYFLI2ZEGD","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XO27GVMY","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:9e0bc28e6da96283a84ba26c7ebe7526d7572a3f5a0e744e9eb1c27d9b0abeea","target":"graph","created_at":"2026-05-18T01:00:19Z","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":"We consider convex-concave saddle-point problems where the objective functions may be split in many components, and extend recent stochastic variance reduction methods (such as SVRG or SAGA) to provide the first large-scale linearly convergent algorithms for this class of problems which is common in machine learning. While the algorithmic extension is straightforward, it comes with challenges and opportunities: (a) the convex minimization analysis does not apply and we use the notion of monotone operators to prove convergence, showing in particular that the same algorithm applies to a larger c","authors_text":"Francis Bach (SIERRA, LIENS), P Balamurugan (SIERRA","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T15:16:29Z","title":"Stochastic Variance Reduction Methods for Saddle-Point Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06398","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:db508a7bce3ffbf20ff105cd662bf15a1b1ac2c360115738a8a5daa347bccb6a","target":"record","created_at":"2026-05-18T01:00:19Z","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":"6628a7c987e4bf179d888b3a7c18d4984afa815563945c7f296d0974b90e07ee","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T15:16:29Z","title_canon_sha256":"5e96b68c0aaabfec7e663f3b29e00a0a245dcce24266fd384c4f984bd864f5fd"},"schema_version":"1.0","source":{"id":"1605.06398","kind":"arxiv","version":2}},"canonical_sha256":"bbb5f355982ad1ac90c372de63b90c0ae1a77721d629703175d6f8f96ceb5fe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbb5f355982ad1ac90c372de63b90c0ae1a77721d629703175d6f8f96ceb5fe2","first_computed_at":"2026-05-18T01:00:19.355138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:19.355138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SS0Q/HHUl7G+IcSCOhW7ov/TUK/VOf3VubqxwdclfmLzvnsSkvQYyiqvExiTl2Ln11iIwNxon2bVERR7B22UCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:19.355901Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.06398","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db508a7bce3ffbf20ff105cd662bf15a1b1ac2c360115738a8a5daa347bccb6a","sha256:9e0bc28e6da96283a84ba26c7ebe7526d7572a3f5a0e744e9eb1c27d9b0abeea"],"state_sha256":"cee0f9f3ba19cbb859a8842aa9af4de37c4cdee25ac23b812807ee5831ad4263"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2/HzQUdVBQE265cMbw5GCCpoj16RvJHG1843JWMTjFzMOMaued53L3VePLm8+x+wDdN8zB5AZIpbaXPjTAZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T18:52:00.843867Z","bundle_sha256":"a6b4b4355ad63f4292fe3c80a78eedbaa946d377682984afd737e84d403a662f"}}