{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:BK3T3QRE2NM4E74ZXOC3H6ABUN","short_pith_number":"pith:BK3T3QRE","canonical_record":{"source":{"id":"1509.04609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-09-15T15:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"28cff32996f20a7c9e89fdd9acdf313277432289b1215670670dabc9d8cd2f02","abstract_canon_sha256":"91b050bf4356c2a369ae56103880634adcb53a1dd2cefcc27a062845891d9d1e"},"schema_version":"1.0"},"canonical_sha256":"0ab73dc224d359c27f99bb85b3f801a3577d5c9c60fced6aa3b769c431bf646d","source":{"kind":"arxiv","id":"1509.04609","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.04609","created_at":"2026-05-18T01:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"1509.04609v1","created_at":"2026-05-18T01:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.04609","created_at":"2026-05-18T01:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"BK3T3QRE2NM4","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BK3T3QRE2NM4E74Z","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BK3T3QRE","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:BK3T3QRE2NM4E74ZXOC3H6ABUN","target":"record","payload":{"canonical_record":{"source":{"id":"1509.04609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-09-15T15:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"28cff32996f20a7c9e89fdd9acdf313277432289b1215670670dabc9d8cd2f02","abstract_canon_sha256":"91b050bf4356c2a369ae56103880634adcb53a1dd2cefcc27a062845891d9d1e"},"schema_version":"1.0"},"canonical_sha256":"0ab73dc224d359c27f99bb85b3f801a3577d5c9c60fced6aa3b769c431bf646d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:58.410133Z","signature_b64":"hYKDHhhWiOc8AG10y4RoJZQ3IQhoyiYiVWh3i1jx3CrzXZVLLjJdc+/Z2ZsocJqNy//VkibDbeoHu+bSqY0pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ab73dc224d359c27f99bb85b3f801a3577d5c9c60fced6aa3b769c431bf646d","last_reissued_at":"2026-05-18T01:32:58.409512Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:58.409512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.04609","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJs6tEJaGfF467Ae0mnSgH510gJeM/xLKUkkdgRMj5gb2/r/vJIH3Esdxl+GadqEuV5wG/96yHx5gvG846+ACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T23:27:44.141080Z"},"content_sha256":"fe800c5fc87e6580b9f489044e64f3832a50bd7343dcbfd1c7a09210bc7b9e95","schema_version":"1.0","event_id":"sha256:fe800c5fc87e6580b9f489044e64f3832a50bd7343dcbfd1c7a09210bc7b9e95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:BK3T3QRE2NM4E74ZXOC3H6ABUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Randomized Block Subgradient Methods for Convex Nonsmooth and Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Anand Rangarajan, Guanghui Lan, Qi Deng","submitted_at":"2015-09-15T15:50:31Z","abstract_excerpt":"Block coordinate descent methods and stochastic subgradient methods have been extensively studied in optimization and machine learning. By combining randomized block sampling with stochastic subgradient methods based on dual averaging, we present stochastic block dual averaging (SBDA)---a novel class of block subgradient methods for convex nonsmooth and stochastic optimization. SBDA requires only a block of subgradients and updates blocks of variables and hence has significantly lower iteration cost than traditional subgradient methods. We show that the SBDA-based methods exhibit the optimal c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.04609","kind":"arxiv","version":1},"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":"2026-05-18T01:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ep0qETHx0UBpLhkgSxrpVoRU/yoqTF1CnfAG5pqgpcCKXitEr8qrWINkhnI3DBNc7s7t2hOSHClksLUyEcAJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T23:27:44.141440Z"},"content_sha256":"fc681f4b7036aab26600a8da3f15c5e3a2fb6eaeffd50030e4dd0bbe5c261f25","schema_version":"1.0","event_id":"sha256:fc681f4b7036aab26600a8da3f15c5e3a2fb6eaeffd50030e4dd0bbe5c261f25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN/bundle.json","state_url":"https://pith.science/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN/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":"2026-07-03T23:27:44Z","links":{"resolver":"https://pith.science/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN","bundle":"https://pith.science/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN/bundle.json","state":"https://pith.science/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BK3T3QRE2NM4E74ZXOC3H6ABUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:BK3T3QRE2NM4E74ZXOC3H6ABUN","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":"91b050bf4356c2a369ae56103880634adcb53a1dd2cefcc27a062845891d9d1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-09-15T15:50:31Z","title_canon_sha256":"28cff32996f20a7c9e89fdd9acdf313277432289b1215670670dabc9d8cd2f02"},"schema_version":"1.0","source":{"id":"1509.04609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.04609","created_at":"2026-05-18T01:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"1509.04609v1","created_at":"2026-05-18T01:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.04609","created_at":"2026-05-18T01:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"BK3T3QRE2NM4","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BK3T3QRE2NM4E74Z","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BK3T3QRE","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:fc681f4b7036aab26600a8da3f15c5e3a2fb6eaeffd50030e4dd0bbe5c261f25","target":"graph","created_at":"2026-05-18T01:32:58Z","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":"Block coordinate descent methods and stochastic subgradient methods have been extensively studied in optimization and machine learning. By combining randomized block sampling with stochastic subgradient methods based on dual averaging, we present stochastic block dual averaging (SBDA)---a novel class of block subgradient methods for convex nonsmooth and stochastic optimization. SBDA requires only a block of subgradients and updates blocks of variables and hence has significantly lower iteration cost than traditional subgradient methods. We show that the SBDA-based methods exhibit the optimal c","authors_text":"Anand Rangarajan, Guanghui Lan, Qi Deng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-09-15T15:50:31Z","title":"Randomized Block Subgradient Methods for Convex Nonsmooth and Stochastic Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.04609","kind":"arxiv","version":1},"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:fe800c5fc87e6580b9f489044e64f3832a50bd7343dcbfd1c7a09210bc7b9e95","target":"record","created_at":"2026-05-18T01:32:58Z","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":"91b050bf4356c2a369ae56103880634adcb53a1dd2cefcc27a062845891d9d1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-09-15T15:50:31Z","title_canon_sha256":"28cff32996f20a7c9e89fdd9acdf313277432289b1215670670dabc9d8cd2f02"},"schema_version":"1.0","source":{"id":"1509.04609","kind":"arxiv","version":1}},"canonical_sha256":"0ab73dc224d359c27f99bb85b3f801a3577d5c9c60fced6aa3b769c431bf646d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ab73dc224d359c27f99bb85b3f801a3577d5c9c60fced6aa3b769c431bf646d","first_computed_at":"2026-05-18T01:32:58.409512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:32:58.409512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hYKDHhhWiOc8AG10y4RoJZQ3IQhoyiYiVWh3i1jx3CrzXZVLLjJdc+/Z2ZsocJqNy//VkibDbeoHu+bSqY0pDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:32:58.410133Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.04609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe800c5fc87e6580b9f489044e64f3832a50bd7343dcbfd1c7a09210bc7b9e95","sha256:fc681f4b7036aab26600a8da3f15c5e3a2fb6eaeffd50030e4dd0bbe5c261f25"],"state_sha256":"77cb2c16adb07ca2376454b8f168dc217f69584d4e2e851ccf6614afa0774be2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKaOk7SGWTKrHD2X62uxjr2Z6bCTO+MPvdJKNU/7NhP9MjyS6cANpZ7iNDiKxJ1+KFlvoAzBsGqYf1HTjhONCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T23:27:44.143479Z","bundle_sha256":"2fec890148399955c671e79f9923520bd51fc443a43501b22a13a2959f509cc4"}}