{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:WYOSX7ZKNFT2MI7WUJ3RQ7WG6E","short_pith_number":"pith:WYOSX7ZK","canonical_record":{"source":{"id":"1412.4182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-12-13T02:32:06Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"5be9e8ab930f77736f1c5e741497a455ce8caa856ff477f022c349f0502ecc61","abstract_canon_sha256":"ad2907b4e6480558ef15b3d612eac727cdfd46678f1dec80466dde1c3d093c5c"},"schema_version":"1.0"},"canonical_sha256":"b61d2bff2a6967a623f6a277187ec6f11ee3468f6f9515996407411fc709a0b2","source":{"kind":"arxiv","id":"1412.4182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4182","created_at":"2026-05-18T02:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4182v1","created_at":"2026-05-18T02:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4182","created_at":"2026-05-18T02:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"WYOSX7ZKNFT2","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WYOSX7ZKNFT2MI7W","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WYOSX7ZK","created_at":"2026-05-18T12:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:WYOSX7ZKNFT2MI7WUJ3RQ7WG6E","target":"record","payload":{"canonical_record":{"source":{"id":"1412.4182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-12-13T02:32:06Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"5be9e8ab930f77736f1c5e741497a455ce8caa856ff477f022c349f0502ecc61","abstract_canon_sha256":"ad2907b4e6480558ef15b3d612eac727cdfd46678f1dec80466dde1c3d093c5c"},"schema_version":"1.0"},"canonical_sha256":"b61d2bff2a6967a623f6a277187ec6f11ee3468f6f9515996407411fc709a0b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:19.993105Z","signature_b64":"HcpAWkoEKxt0MMYkz+PCpsTrGJu71LaNH9mplg7vPoVkwIlnUehXPqc6l1fAR6HIVOPyHa73eWgUnQtKLH3qBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b61d2bff2a6967a623f6a277187ec6f11ee3468f6f9515996407411fc709a0b2","last_reissued_at":"2026-05-18T02:31:19.992493Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:19.992493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.4182","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":"2026-05-18T02:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVuAuDg5vYX2/l57LkAy8nYJquqTUXer1fRjIvXM5GrVTj0nSYoDuo25h9FdyYjJGuAlOc+KuNoW23YbJVx6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:02:45.679527Z"},"content_sha256":"e4b8b7e2f0106e4dfe13d2ddce4fa376b916e4be07a785219b30421563dce2ed","schema_version":"1.0","event_id":"sha256:e4b8b7e2f0106e4dfe13d2ddce4fa376b916e4be07a785219b30421563dce2ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:WYOSX7ZKNFT2MI7WUJ3RQ7WG6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Statistics of Streaming Sparse Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jacob Steinhardt, Percy Liang, Stefan Wager","submitted_at":"2014-12-13T02:32:06Z","abstract_excerpt":"We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresentable noise features, our algorithm recovers the support set of the optimal parameter vector with high probability, and achieves a statistically quasi-optimal rate of convergence of Op(k log(d)/T), where k is the sparsity of the solution, d is the number of features, and T is the number of training examples. Meanwhile, our algorithm does not require any more computational resources than stochastic gradient descent. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4182","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":"2026-05-18T02:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3o89OmhOaLgwGsk5yPodPh7VubfhgZr0PJZei1M+azDjK+7Z7pdyJ3+BUONOJXgzz2O4LS9hHYzh1KQ9C/IuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:02:45.680273Z"},"content_sha256":"cd1829d11e7acd754cd010f1125eb2e6ce2f68b4d37bf8ec941d650fbeb6d2d9","schema_version":"1.0","event_id":"sha256:cd1829d11e7acd754cd010f1125eb2e6ce2f68b4d37bf8ec941d650fbeb6d2d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E/bundle.json","state_url":"https://pith.science/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E/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":"2026-05-30T14:02:45Z","links":{"resolver":"https://pith.science/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E","bundle":"https://pith.science/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E/bundle.json","state":"https://pith.science/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYOSX7ZKNFT2MI7WUJ3RQ7WG6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:WYOSX7ZKNFT2MI7WUJ3RQ7WG6E","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":"ad2907b4e6480558ef15b3d612eac727cdfd46678f1dec80466dde1c3d093c5c","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-12-13T02:32:06Z","title_canon_sha256":"5be9e8ab930f77736f1c5e741497a455ce8caa856ff477f022c349f0502ecc61"},"schema_version":"1.0","source":{"id":"1412.4182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4182","created_at":"2026-05-18T02:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4182v1","created_at":"2026-05-18T02:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4182","created_at":"2026-05-18T02:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"WYOSX7ZKNFT2","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WYOSX7ZKNFT2MI7W","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WYOSX7ZK","created_at":"2026-05-18T12:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:cd1829d11e7acd754cd010f1125eb2e6ce2f68b4d37bf8ec941d650fbeb6d2d9","target":"graph","created_at":"2026-05-18T02:31:19Z","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":"We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresentable noise features, our algorithm recovers the support set of the optimal parameter vector with high probability, and achieves a statistically quasi-optimal rate of convergence of Op(k log(d)/T), where k is the sparsity of the solution, d is the number of features, and T is the number of training examples. Meanwhile, our algorithm does not require any more computational resources than stochastic gradient descent. I","authors_text":"Jacob Steinhardt, Percy Liang, Stefan Wager","cross_cats":["cs.LG","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-12-13T02:32:06Z","title":"The Statistics of Streaming Sparse Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4182","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:e4b8b7e2f0106e4dfe13d2ddce4fa376b916e4be07a785219b30421563dce2ed","target":"record","created_at":"2026-05-18T02:31:19Z","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":"ad2907b4e6480558ef15b3d612eac727cdfd46678f1dec80466dde1c3d093c5c","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-12-13T02:32:06Z","title_canon_sha256":"5be9e8ab930f77736f1c5e741497a455ce8caa856ff477f022c349f0502ecc61"},"schema_version":"1.0","source":{"id":"1412.4182","kind":"arxiv","version":1}},"canonical_sha256":"b61d2bff2a6967a623f6a277187ec6f11ee3468f6f9515996407411fc709a0b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b61d2bff2a6967a623f6a277187ec6f11ee3468f6f9515996407411fc709a0b2","first_computed_at":"2026-05-18T02:31:19.992493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:31:19.992493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HcpAWkoEKxt0MMYkz+PCpsTrGJu71LaNH9mplg7vPoVkwIlnUehXPqc6l1fAR6HIVOPyHa73eWgUnQtKLH3qBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:31:19.993105Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.4182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4b8b7e2f0106e4dfe13d2ddce4fa376b916e4be07a785219b30421563dce2ed","sha256:cd1829d11e7acd754cd010f1125eb2e6ce2f68b4d37bf8ec941d650fbeb6d2d9"],"state_sha256":"b6b12fe2cd4f4ef0db923ec95fe54db8ecdde48d8a4a8160a0e4d640b30d3f53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AdEn5c6fe8Kdh0YI1ixbXTe6GXY/N5Km2H0OFjEdnt0syHDOcyXiANWjrljazx/rg78Hps6UOXFvrjbtQc4bAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:02:45.687154Z","bundle_sha256":"dc34fc117aab69ea6ae6995150827877b1448d0498b50d6fe3949c8606356462"}}