{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KR7JNAQBMFJ7S7IWRS3AFGVNAW","short_pith_number":"pith:KR7JNAQB","canonical_record":{"source":{"id":"1707.06468","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2017-07-20T12:14:31Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5c24982c1d2ba47ba4373513a24da6d340ac0da63356dcab3fec77990616d85d","abstract_canon_sha256":"efb076f2c7f1e0c14ef824c496c9e7ada8dc7be1b2fbd8dba7450d7609ed0e1b"},"schema_version":"1.0"},"canonical_sha256":"547e9682016153f97d168cb6029aad0589598951ae83e457adc16af1bd2bd135","source":{"kind":"arxiv","id":"1707.06468","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06468","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06468v3","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06468","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"KR7JNAQBMFJ7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KR7JNAQBMFJ7S7IW","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KR7JNAQB","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KR7JNAQBMFJ7S7IWRS3AFGVNAW","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06468","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2017-07-20T12:14:31Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5c24982c1d2ba47ba4373513a24da6d340ac0da63356dcab3fec77990616d85d","abstract_canon_sha256":"efb076f2c7f1e0c14ef824c496c9e7ada8dc7be1b2fbd8dba7450d7609ed0e1b"},"schema_version":"1.0"},"canonical_sha256":"547e9682016153f97d168cb6029aad0589598951ae83e457adc16af1bd2bd135","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:19.107876Z","signature_b64":"QJy6Y9byUeFa06AgkZR9m3AnSb59k4VtHj7wKGIPirApGQBXw41OJlQI9tae44MCYrfmrYNqMGPJ81yt8zXZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"547e9682016153f97d168cb6029aad0589598951ae83e457adc16af1bd2bd135","last_reissued_at":"2026-05-18T00:31:19.107138Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:19.107138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06468","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjxWRSqJ/6JxLecHyPLApp0lzJJP6Jre3icA8LzRAySwpL4dbhghB0fMrYskLT4vg7mhDQ1YL/kTe4285EEwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:08:42.713051Z"},"content_sha256":"7bf0ba791f0d11fb4bebced5efbd30f0b5710792da8de5e3097fcf5e91918fcb","schema_version":"1.0","event_id":"sha256:7bf0ba791f0d11fb4bebced5efbd30f0b5710792da8de5e3097fcf5e91918fcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KR7JNAQBMFJ7S7IWRS3AFGVNAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Fabian Pedregosa, R\\'emi Leblond, Simon Lacoste-Julien","submitted_at":"2017-07-20T12:14:31Z","abstract_excerpt":"Due to their simplicity and excellent performance, parallel asynchronous variants of stochastic gradient descent have become popular methods to solve a wide range of large-scale optimization problems on multi-core architectures. Yet, despite their practical success, support for nonsmooth objectives is still lacking, making them unsuitable for many problems of interest in machine learning, such as the Lasso, group Lasso or empirical risk minimization with convex constraints.\n  In this work, we propose and analyze ProxASAGA, a fully asynchronous sparse method inspired by SAGA, a variance reduced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06468","kind":"arxiv","version":3},"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":"2026-05-18T00:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jsq1h1COmR/tgltXMWS/nffmvSweubTQtuOisr4GsgDpaoZaWQ9rghUCuX8KBNsSjEnU9dPlsWY2TEz3juxZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:08:42.713422Z"},"content_sha256":"8d25008976f28159ea934cc2224341d5063d1ad08391fcc7873947f03a0a7989","schema_version":"1.0","event_id":"sha256:8d25008976f28159ea934cc2224341d5063d1ad08391fcc7873947f03a0a7989"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW/bundle.json","state_url":"https://pith.science/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW/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":"2026-06-04T04:08:42Z","links":{"resolver":"https://pith.science/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW","bundle":"https://pith.science/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW/bundle.json","state":"https://pith.science/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KR7JNAQBMFJ7S7IWRS3AFGVNAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KR7JNAQBMFJ7S7IWRS3AFGVNAW","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":"efb076f2c7f1e0c14ef824c496c9e7ada8dc7be1b2fbd8dba7450d7609ed0e1b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2017-07-20T12:14:31Z","title_canon_sha256":"5c24982c1d2ba47ba4373513a24da6d340ac0da63356dcab3fec77990616d85d"},"schema_version":"1.0","source":{"id":"1707.06468","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06468","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06468v3","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06468","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"KR7JNAQBMFJ7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KR7JNAQBMFJ7S7IW","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KR7JNAQB","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:8d25008976f28159ea934cc2224341d5063d1ad08391fcc7873947f03a0a7989","target":"graph","created_at":"2026-05-18T00:31:19Z","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":"Due to their simplicity and excellent performance, parallel asynchronous variants of stochastic gradient descent have become popular methods to solve a wide range of large-scale optimization problems on multi-core architectures. Yet, despite their practical success, support for nonsmooth objectives is still lacking, making them unsuitable for many problems of interest in machine learning, such as the Lasso, group Lasso or empirical risk minimization with convex constraints.\n  In this work, we propose and analyze ProxASAGA, a fully asynchronous sparse method inspired by SAGA, a variance reduced","authors_text":"Fabian Pedregosa, R\\'emi Leblond, Simon Lacoste-Julien","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2017-07-20T12:14:31Z","title":"Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06468","kind":"arxiv","version":3},"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":"sha256:7bf0ba791f0d11fb4bebced5efbd30f0b5710792da8de5e3097fcf5e91918fcb","target":"record","created_at":"2026-05-18T00:31:19Z","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":"efb076f2c7f1e0c14ef824c496c9e7ada8dc7be1b2fbd8dba7450d7609ed0e1b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2017-07-20T12:14:31Z","title_canon_sha256":"5c24982c1d2ba47ba4373513a24da6d340ac0da63356dcab3fec77990616d85d"},"schema_version":"1.0","source":{"id":"1707.06468","kind":"arxiv","version":3}},"canonical_sha256":"547e9682016153f97d168cb6029aad0589598951ae83e457adc16af1bd2bd135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"547e9682016153f97d168cb6029aad0589598951ae83e457adc16af1bd2bd135","first_computed_at":"2026-05-18T00:31:19.107138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:19.107138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QJy6Y9byUeFa06AgkZR9m3AnSb59k4VtHj7wKGIPirApGQBXw41OJlQI9tae44MCYrfmrYNqMGPJ81yt8zXZCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:19.107876Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06468","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bf0ba791f0d11fb4bebced5efbd30f0b5710792da8de5e3097fcf5e91918fcb","sha256:8d25008976f28159ea934cc2224341d5063d1ad08391fcc7873947f03a0a7989"],"state_sha256":"1a4d21c0640eb9b74da8e67d4932877e0159c0a5d6af38a42a0327d38bef3f53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vUq+3k6+b9cM19cbG9QHApft6tx26DAgtGfn54exsdlrWo9J7oaPYMzvnms6tgjgsIIjM8TUPQh3uSdnSkyOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T04:08:42.715720Z","bundle_sha256":"d71ff52b4b1d725695079405f791341086bdbace33ec70eb7239aad6f227b5a5"}}