{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ORCWDXY2Q2WHEO7PXEPSUPMDTN","short_pith_number":"pith:ORCWDXY2","canonical_record":{"source":{"id":"2501.15941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-27T10:36:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c223a4a06d6ba7454126777cf1fd464f476adaa935540cd94808f432b2f0b710","abstract_canon_sha256":"fe38875f115055723b4c53b86e6fe56daefe22f35f9e3adc0e199f476f1193b5"},"schema_version":"1.0"},"canonical_sha256":"744561df1a86ac723befb91f2a3d839b5ee14991ceb92669ba536940b19340ab","source":{"kind":"arxiv","id":"2501.15941","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15941","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15941v1","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15941","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"ORCWDXY2Q2WH","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"ORCWDXY2Q2WHEO7P","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"ORCWDXY2","created_at":"2026-07-05T10:05:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ORCWDXY2Q2WHEO7PXEPSUPMDTN","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-27T10:36:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c223a4a06d6ba7454126777cf1fd464f476adaa935540cd94808f432b2f0b710","abstract_canon_sha256":"fe38875f115055723b4c53b86e6fe56daefe22f35f9e3adc0e199f476f1193b5"},"schema_version":"1.0"},"canonical_sha256":"744561df1a86ac723befb91f2a3d839b5ee14991ceb92669ba536940b19340ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:52.453271Z","signature_b64":"Nam4ceOJDFaiwRXfpzQuTp6Z2cYsPceU7kSSlOK/OWrfC9t50Bl0eLI0W5lr5YwuH2msskRbTLLuQoYDB2YFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"744561df1a86ac723befb91f2a3d839b5ee14991ceb92669ba536940b19340ab","last_reissued_at":"2026-07-05T10:05:52.452770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:52.452770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15941","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":"2026-07-05T10:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pORter8o1nX7hNX5z7YMS1XmKFlzBCNjacuktYzUmGWCFefQ8Ozign2gDeDhbBCuCGHRb+cDCVXTBeRC4oceBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:01:59.742988Z"},"content_sha256":"2ec40f75ead805d3fb1b83ec7a12902f8a7ea93e09375817293e93e11683ee2c","schema_version":"1.0","event_id":"sha256:2ec40f75ead805d3fb1b83ec7a12902f8a7ea93e09375817293e93e11683ee2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ORCWDXY2Q2WHEO7PXEPSUPMDTN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jingruo Sun, Madeleine Udell, Zachary Frangella","submitted_at":"2025-01-27T10:36:45Z","abstract_excerpt":"Regularized empirical risk minimization (rERM) has become important in data-intensive fields such as genomics and advertising, with stochastic gradient methods typically used to solve the largest problems. However, ill-conditioned objectives and non-smooth regularizers undermine the performance of traditional stochastic gradient methods, leading to slow convergence and significant computational costs. To address these challenges, we propose the $\\texttt{SAPPHIRE}$ ($\\textbf{S}$ketching-based $\\textbf{A}$pproximations for $\\textbf{P}$roximal $\\textbf{P}$reconditioning and $\\textbf{H}$essian $\\t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15941","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.15941/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T10:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fi99Y8QpZ42N/b//GIreNVbfmox95FD4BmsI5gXY7zbJRK+954W+If6djLF35xMY7bXPWmKTUJo1kCfDkrisDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:01:59.743941Z"},"content_sha256":"ea2ad242cf5d3997caaaf6ae7a45190aa501fb7e6af7cb005ddd101dfcc2f71f","schema_version":"1.0","event_id":"sha256:ea2ad242cf5d3997caaaf6ae7a45190aa501fb7e6af7cb005ddd101dfcc2f71f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN/bundle.json","state_url":"https://pith.science/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN/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":"2026-08-14T09:01:59Z","links":{"resolver":"https://pith.science/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN","bundle":"https://pith.science/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN/bundle.json","state":"https://pith.science/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORCWDXY2Q2WHEO7PXEPSUPMDTN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ORCWDXY2Q2WHEO7PXEPSUPMDTN","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":"fe38875f115055723b4c53b86e6fe56daefe22f35f9e3adc0e199f476f1193b5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-27T10:36:45Z","title_canon_sha256":"c223a4a06d6ba7454126777cf1fd464f476adaa935540cd94808f432b2f0b710"},"schema_version":"1.0","source":{"id":"2501.15941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15941","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15941v1","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15941","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"ORCWDXY2Q2WH","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"ORCWDXY2Q2WHEO7P","created_at":"2026-07-05T10:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"ORCWDXY2","created_at":"2026-07-05T10:05:52Z"}],"graph_snapshots":[{"event_id":"sha256:ea2ad242cf5d3997caaaf6ae7a45190aa501fb7e6af7cb005ddd101dfcc2f71f","target":"graph","created_at":"2026-07-05T10:05:52Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.15941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Regularized empirical risk minimization (rERM) has become important in data-intensive fields such as genomics and advertising, with stochastic gradient methods typically used to solve the largest problems. However, ill-conditioned objectives and non-smooth regularizers undermine the performance of traditional stochastic gradient methods, leading to slow convergence and significant computational costs. To address these challenges, we propose the $\\texttt{SAPPHIRE}$ ($\\textbf{S}$ketching-based $\\textbf{A}$pproximations for $\\textbf{P}$roximal $\\textbf{P}$reconditioning and $\\textbf{H}$essian $\\t","authors_text":"Jingruo Sun, Madeleine Udell, Zachary Frangella","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-27T10:36:45Z","title":"SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15941","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":"sha256:2ec40f75ead805d3fb1b83ec7a12902f8a7ea93e09375817293e93e11683ee2c","target":"record","created_at":"2026-07-05T10:05:52Z","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":"fe38875f115055723b4c53b86e6fe56daefe22f35f9e3adc0e199f476f1193b5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-27T10:36:45Z","title_canon_sha256":"c223a4a06d6ba7454126777cf1fd464f476adaa935540cd94808f432b2f0b710"},"schema_version":"1.0","source":{"id":"2501.15941","kind":"arxiv","version":1}},"canonical_sha256":"744561df1a86ac723befb91f2a3d839b5ee14991ceb92669ba536940b19340ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"744561df1a86ac723befb91f2a3d839b5ee14991ceb92669ba536940b19340ab","first_computed_at":"2026-07-05T10:05:52.452770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:52.452770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nam4ceOJDFaiwRXfpzQuTp6Z2cYsPceU7kSSlOK/OWrfC9t50Bl0eLI0W5lr5YwuH2msskRbTLLuQoYDB2YFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:52.453271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ec40f75ead805d3fb1b83ec7a12902f8a7ea93e09375817293e93e11683ee2c","sha256:ea2ad242cf5d3997caaaf6ae7a45190aa501fb7e6af7cb005ddd101dfcc2f71f"],"state_sha256":"3fe1fd1904cba3d11e20b672a24df1e88aebb7b6bc0ebf035ade2c71487797d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LFHRpGEfMqXDNWufIi/KHEQQco5DIMAa+7Hw+CxZmjBjlT8YinzhYag6DEodWq78eJvyqmQ5igFHWju4zDHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:01:59.750952Z","bundle_sha256":"3a2d7862a0f1e39fb3f9eb13199d0ab4ced7437fbdf79516ffc42b6b8015e48e"}}