{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:XFGYDXLABNPOMCJLDX4E3MCSJL","short_pith_number":"pith:XFGYDXLA","canonical_record":{"source":{"id":"1205.4481","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-21T03:29:17Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"25292a928d169bc48b22372f8a6e54f91d9323bf3966a1e8b97215056b991b34","abstract_canon_sha256":"1fb62920a8b34e9fdcbc16d0b3a4aafc88727b71d16471fd37a3211eced26813"},"schema_version":"1.0"},"canonical_sha256":"b94d81dd600b5ee6092b1df84db0524aed1ccd8eaa6fdaa35ed79ce6dc428ee8","source":{"kind":"arxiv","id":"1205.4481","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.4481","created_at":"2026-05-18T03:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"1205.4481v4","created_at":"2026-05-18T03:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.4481","created_at":"2026-05-18T03:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"XFGYDXLABNPO","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"XFGYDXLABNPOMCJL","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"XFGYDXLA","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:XFGYDXLABNPOMCJLDX4E3MCSJL","target":"record","payload":{"canonical_record":{"source":{"id":"1205.4481","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-21T03:29:17Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"25292a928d169bc48b22372f8a6e54f91d9323bf3966a1e8b97215056b991b34","abstract_canon_sha256":"1fb62920a8b34e9fdcbc16d0b3a4aafc88727b71d16471fd37a3211eced26813"},"schema_version":"1.0"},"canonical_sha256":"b94d81dd600b5ee6092b1df84db0524aed1ccd8eaa6fdaa35ed79ce6dc428ee8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:44:24.039155Z","signature_b64":"D5U0V7jMulPBuKa79Ii66I0LFMtdSbXvvFZWyZjfdzPcjuJLu0hpCrv7CqQN4v6B30Y2voFOpw44V4GUbkyiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b94d81dd600b5ee6092b1df84db0524aed1ccd8eaa6fdaa35ed79ce6dc428ee8","last_reissued_at":"2026-05-18T03:44:24.038509Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:44:24.038509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1205.4481","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3F1s5SyfgA8pzLCGiKgsFw5RRx3+3ALt0c5qnoa/nSxvTsvvXA+uX3u7+D+4mp4Ze0n8ja4jtEyfU/UG4BFfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:11:20.920203Z"},"content_sha256":"c51cad79945c4a65b61d2c59852ed5321c1a730d4ab8cba53662b058a16465c3","schema_version":"1.0","event_id":"sha256:c51cad79945c4a65b61d2c59852ed5321c1a730d4ab8cba53662b058a16465c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:XFGYDXLABNPOMCJLDX4E3MCSJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Smoothing for Nonsmooth Minimizations: Accelerating SGD by Exploiting Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Gray, Hua Ouyang","submitted_at":"2012-05-21T03:29:17Z","abstract_excerpt":"In this work we consider the stochastic minimization of nonsmooth convex loss functions, a central problem in machine learning. We propose a novel algorithm called Accelerated Nonsmooth Stochastic Gradient Descent (ANSGD), which exploits the structure of common nonsmooth loss functions to achieve optimal convergence rates for a class of problems including SVMs. It is the first stochastic algorithm that can achieve the optimal O(1/t) rate for minimizing nonsmooth loss functions (with strong convexity). The fast rates are confirmed by empirical comparisons, in which ANSGD significantly outperfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.4481","kind":"arxiv","version":4},"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":"2026-05-18T03:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U94Eu46qhgmVRq12D79dH1vIkmknXX704KIvfEfYcGhSVkFB/8FAiklKeCaVmepQKORLWH0gF5wma8+plWyVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:11:20.920583Z"},"content_sha256":"9619970ac6a36a89a254cac9b0f361dfbf00f0d92e426bcc2b5007b02e325681","schema_version":"1.0","event_id":"sha256:9619970ac6a36a89a254cac9b0f361dfbf00f0d92e426bcc2b5007b02e325681"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFGYDXLABNPOMCJLDX4E3MCSJL/bundle.json","state_url":"https://pith.science/pith/XFGYDXLABNPOMCJLDX4E3MCSJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFGYDXLABNPOMCJLDX4E3MCSJL/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":"2026-06-25T05:11:20Z","links":{"resolver":"https://pith.science/pith/XFGYDXLABNPOMCJLDX4E3MCSJL","bundle":"https://pith.science/pith/XFGYDXLABNPOMCJLDX4E3MCSJL/bundle.json","state":"https://pith.science/pith/XFGYDXLABNPOMCJLDX4E3MCSJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFGYDXLABNPOMCJLDX4E3MCSJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:XFGYDXLABNPOMCJLDX4E3MCSJL","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":"1fb62920a8b34e9fdcbc16d0b3a4aafc88727b71d16471fd37a3211eced26813","cross_cats_sorted":["stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-21T03:29:17Z","title_canon_sha256":"25292a928d169bc48b22372f8a6e54f91d9323bf3966a1e8b97215056b991b34"},"schema_version":"1.0","source":{"id":"1205.4481","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.4481","created_at":"2026-05-18T03:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"1205.4481v4","created_at":"2026-05-18T03:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.4481","created_at":"2026-05-18T03:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"XFGYDXLABNPO","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"XFGYDXLABNPOMCJL","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"XFGYDXLA","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:9619970ac6a36a89a254cac9b0f361dfbf00f0d92e426bcc2b5007b02e325681","target":"graph","created_at":"2026-05-18T03:44:24Z","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":"In this work we consider the stochastic minimization of nonsmooth convex loss functions, a central problem in machine learning. We propose a novel algorithm called Accelerated Nonsmooth Stochastic Gradient Descent (ANSGD), which exploits the structure of common nonsmooth loss functions to achieve optimal convergence rates for a class of problems including SVMs. It is the first stochastic algorithm that can achieve the optimal O(1/t) rate for minimizing nonsmooth loss functions (with strong convexity). The fast rates are confirmed by empirical comparisons, in which ANSGD significantly outperfor","authors_text":"Alexander Gray, Hua Ouyang","cross_cats":["stat.CO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-21T03:29:17Z","title":"Stochastic Smoothing for Nonsmooth Minimizations: Accelerating SGD by Exploiting Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.4481","kind":"arxiv","version":4},"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:c51cad79945c4a65b61d2c59852ed5321c1a730d4ab8cba53662b058a16465c3","target":"record","created_at":"2026-05-18T03:44:24Z","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":"1fb62920a8b34e9fdcbc16d0b3a4aafc88727b71d16471fd37a3211eced26813","cross_cats_sorted":["stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-21T03:29:17Z","title_canon_sha256":"25292a928d169bc48b22372f8a6e54f91d9323bf3966a1e8b97215056b991b34"},"schema_version":"1.0","source":{"id":"1205.4481","kind":"arxiv","version":4}},"canonical_sha256":"b94d81dd600b5ee6092b1df84db0524aed1ccd8eaa6fdaa35ed79ce6dc428ee8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b94d81dd600b5ee6092b1df84db0524aed1ccd8eaa6fdaa35ed79ce6dc428ee8","first_computed_at":"2026-05-18T03:44:24.038509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:44:24.038509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D5U0V7jMulPBuKa79Ii66I0LFMtdSbXvvFZWyZjfdzPcjuJLu0hpCrv7CqQN4v6B30Y2voFOpw44V4GUbkyiAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:44:24.039155Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.4481","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c51cad79945c4a65b61d2c59852ed5321c1a730d4ab8cba53662b058a16465c3","sha256:9619970ac6a36a89a254cac9b0f361dfbf00f0d92e426bcc2b5007b02e325681"],"state_sha256":"49bb701365430008bf471fa50cc81a655a419f7fd3a59c62fcb931df42696600"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xl9ofVP0RDBTb+3Up2+NC916BZ7pjUTOwZCUR1L340C5qufQRdGI+17arAgv8+nWVSotkfJ9Bz1ENOKEVXntBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T05:11:20.922619Z","bundle_sha256":"e9dcc9047301e1fdbba22ccee7cd33d29ea5ec8035ee88834e0a53d919301d00"}}