{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:LNDB5GBJZ6DEKMVMOO2KRKAOLK","short_pith_number":"pith:LNDB5GBJ","canonical_record":{"source":{"id":"1605.08982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-29T09:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"60192d6bb853134b5bde09a006624000c1b81f054a8b861cc7711712e70ff9b5","abstract_canon_sha256":"a140a6168a66402a9b121c40617fdf416af6456e9b8f451e562f87782118c173"},"schema_version":"1.0"},"canonical_sha256":"5b461e9829cf864532ac73b4a8a80e5a882104abc0f27197dd03b6dae1da07f2","source":{"kind":"arxiv","id":"1605.08982","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08982","created_at":"2026-05-18T01:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08982v1","created_at":"2026-05-18T01:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08982","created_at":"2026-05-18T01:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"LNDB5GBJZ6DE","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LNDB5GBJZ6DEKMVM","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LNDB5GBJ","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:LNDB5GBJZ6DEKMVMOO2KRKAOLK","target":"record","payload":{"canonical_record":{"source":{"id":"1605.08982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-29T09:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"60192d6bb853134b5bde09a006624000c1b81f054a8b861cc7711712e70ff9b5","abstract_canon_sha256":"a140a6168a66402a9b121c40617fdf416af6456e9b8f451e562f87782118c173"},"schema_version":"1.0"},"canonical_sha256":"5b461e9829cf864532ac73b4a8a80e5a882104abc0f27197dd03b6dae1da07f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:22.442839Z","signature_b64":"DlHgncU2H/Z32zGB3bO2N0oz6PwFVvBUAE4fR0eAZMt9sYIN/5LnYfl81NeF1ckgdIV4dm4UQGVx4Q2v2Jw4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b461e9829cf864532ac73b4a8a80e5a882104abc0f27197dd03b6dae1da07f2","last_reissued_at":"2026-05-18T01:13:22.442333Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:22.442333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.08982","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":"2026-05-18T01:13:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9eO2LSvEN22Fq61bFkHIO2fBCHr1alG8bInTC/OLi6MSJKm59w7ovTnfNaWkdXzeytMY4a+n0oWgITnl+w7VAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:49:34.560724Z"},"content_sha256":"bd7bd5fa938d066a10d6098da79139440986b460948fd2fed27c56ef98c32b1f","schema_version":"1.0","event_id":"sha256:bd7bd5fa938d066a10d6098da79139440986b460948fd2fed27c56ef98c32b1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:LNDB5GBJZ6DEKMVMOO2KRKAOLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coordinate Descent Face-Off: Primal or Dual?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dominik Csiba, Peter Richt\\'arik","submitted_at":"2016-05-29T09:32:37Z","abstract_excerpt":"Randomized coordinate descent (RCD) methods are state-of-the-art algorithms for training linear predictors via minimizing regularized empirical risk. When the number of examples ($n$) is much larger than the number of features ($d$), a common strategy is to apply RCD to the dual problem. On the other hand, when the number of features is much larger than the number of examples, it makes sense to apply RCD directly to the primal problem. In this paper we provide the first joint study of these two approaches when applied to L2-regularized ERM. First, we show through a rigorous analysis that for d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08982","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":"2026-05-18T01:13:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ioUVUW8h+sdEnfeG93euBN8vM9KIHAQcNxTZ9CX78oUwX4CUUqIP8IJyTOivx5ey184IVHhiFC2KFopxI8CABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:49:34.561182Z"},"content_sha256":"60877d7891702528ecea1ebb15433d73cc8e358df711e3314a26d9f30e9331d4","schema_version":"1.0","event_id":"sha256:60877d7891702528ecea1ebb15433d73cc8e358df711e3314a26d9f30e9331d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK/bundle.json","state_url":"https://pith.science/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK/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":"2026-05-26T20:49:34Z","links":{"resolver":"https://pith.science/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK","bundle":"https://pith.science/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK/bundle.json","state":"https://pith.science/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LNDB5GBJZ6DEKMVMOO2KRKAOLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:LNDB5GBJZ6DEKMVMOO2KRKAOLK","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":"a140a6168a66402a9b121c40617fdf416af6456e9b8f451e562f87782118c173","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-29T09:32:37Z","title_canon_sha256":"60192d6bb853134b5bde09a006624000c1b81f054a8b861cc7711712e70ff9b5"},"schema_version":"1.0","source":{"id":"1605.08982","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08982","created_at":"2026-05-18T01:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08982v1","created_at":"2026-05-18T01:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08982","created_at":"2026-05-18T01:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"LNDB5GBJZ6DE","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LNDB5GBJZ6DEKMVM","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LNDB5GBJ","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:60877d7891702528ecea1ebb15433d73cc8e358df711e3314a26d9f30e9331d4","target":"graph","created_at":"2026-05-18T01:13:22Z","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":"Randomized coordinate descent (RCD) methods are state-of-the-art algorithms for training linear predictors via minimizing regularized empirical risk. When the number of examples ($n$) is much larger than the number of features ($d$), a common strategy is to apply RCD to the dual problem. On the other hand, when the number of features is much larger than the number of examples, it makes sense to apply RCD directly to the primal problem. In this paper we provide the first joint study of these two approaches when applied to L2-regularized ERM. First, we show through a rigorous analysis that for d","authors_text":"Dominik Csiba, Peter Richt\\'arik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-29T09:32:37Z","title":"Coordinate Descent Face-Off: Primal or Dual?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08982","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:bd7bd5fa938d066a10d6098da79139440986b460948fd2fed27c56ef98c32b1f","target":"record","created_at":"2026-05-18T01:13:22Z","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":"a140a6168a66402a9b121c40617fdf416af6456e9b8f451e562f87782118c173","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-29T09:32:37Z","title_canon_sha256":"60192d6bb853134b5bde09a006624000c1b81f054a8b861cc7711712e70ff9b5"},"schema_version":"1.0","source":{"id":"1605.08982","kind":"arxiv","version":1}},"canonical_sha256":"5b461e9829cf864532ac73b4a8a80e5a882104abc0f27197dd03b6dae1da07f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b461e9829cf864532ac73b4a8a80e5a882104abc0f27197dd03b6dae1da07f2","first_computed_at":"2026-05-18T01:13:22.442333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:22.442333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DlHgncU2H/Z32zGB3bO2N0oz6PwFVvBUAE4fR0eAZMt9sYIN/5LnYfl81NeF1ckgdIV4dm4UQGVx4Q2v2Jw4Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:22.442839Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.08982","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd7bd5fa938d066a10d6098da79139440986b460948fd2fed27c56ef98c32b1f","sha256:60877d7891702528ecea1ebb15433d73cc8e358df711e3314a26d9f30e9331d4"],"state_sha256":"37a493fbce71c0e13efe4c11e6c20b547439d72aa8df08025e67032b68f9c929"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9A1E1Bt1/FCtRwYn95UyiWGXd0d8mkByG/hAAtRfkDh4vMWFG0IAiiYP5NFq7or2fJOo4vUuACoUZkP0G9haAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:49:34.564576Z","bundle_sha256":"ea0c1290551ee330cf1dd61f61ccb64cf8420e54c893eefc9614a6cc847352bb"}}