{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BZ7LOJRQJTHC64H3AGHHLI23DV","short_pith_number":"pith:BZ7LOJRQ","canonical_record":{"source":{"id":"1702.01166","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-02-03T21:23:46Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"2146bebce4ceacaf5cffdda4c3d7d52c16a3eebca918230566d1ac62d8207edb","abstract_canon_sha256":"4066621c9ad330705f685b3a2f939151ff6c208ca5d83f4d909d4b0d6bbabfa4"},"schema_version":"1.0"},"canonical_sha256":"0e7eb726304cce2f70fb018e75a35b1d775a74041fe2dd8488bcda11e063fec8","source":{"kind":"arxiv","id":"1702.01166","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.01166","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1702.01166v2","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01166","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"BZ7LOJRQJTHC","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BZ7LOJRQJTHC64H3","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BZ7LOJRQ","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BZ7LOJRQJTHC64H3AGHHLI23DV","target":"record","payload":{"canonical_record":{"source":{"id":"1702.01166","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-02-03T21:23:46Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"2146bebce4ceacaf5cffdda4c3d7d52c16a3eebca918230566d1ac62d8207edb","abstract_canon_sha256":"4066621c9ad330705f685b3a2f939151ff6c208ca5d83f4d909d4b0d6bbabfa4"},"schema_version":"1.0"},"canonical_sha256":"0e7eb726304cce2f70fb018e75a35b1d775a74041fe2dd8488bcda11e063fec8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:14.427945Z","signature_b64":"+b7rybVpcFCH1YlGNcpOuhNSxmQwtcDYAIfN1acCNFrDt5Okg23PwmzEqW8oqXF3LuBdh/crAVP3ooWrAKydDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e7eb726304cce2f70fb018e75a35b1d775a74041fe2dd8488bcda11e063fec8","last_reissued_at":"2026-05-17T23:42:14.427103Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:14.427103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.01166","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKWUuAFadoXh+BTACg8vpLHkYJlySyonjRjP3qEDhMbK1uSFoyRhegrTPwv32Wv28rmUbmSwR+9ITFIOIiE3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:35:37.745922Z"},"content_sha256":"e0c796d6dff149fc7c2c15fabadd7edd871fbe3331b7ad82da2346c1abb9e105","schema_version":"1.0","event_id":"sha256:e0c796d6dff149fc7c2c15fabadd7edd871fbe3331b7ad82da2346c1abb9e105"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BZ7LOJRQJTHC64H3AGHHLI23DV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Subsampling for Large Sample Logistic Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"stat.CO","authors_text":"Haiying Wang, Ping Ma, Rong Zhu","submitted_at":"2017-02-03T21:23:46Z","abstract_excerpt":"For massive data, the family of subsampling algorithms is popular to downsize the data volume and reduce computational burden. Existing studies focus on approximating the ordinary least squares estimate in linear regression, where statistical leverage scores are often used to define subsampling probabilities. In this paper, we propose fast subsampling algorithms to efficiently approximate the maximum likelihood estimate in logistic regression. We first establish consistency and asymptotic normality of the estimator from a general subsampling algorithm, and then derive optimal subsampling proba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01166","kind":"arxiv","version":2},"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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOD5ZW99HX4HregoPtdG5J2F2RcdmtqdKtrxizVWDndHILOxg5v+YzC9XTb73Prkz8ys6Pg1CkX2S93VCOFACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:35:37.746612Z"},"content_sha256":"cde70e1721bce55a16b977379bacc0ab74f3f88014ee5589852540eb1ce675a1","schema_version":"1.0","event_id":"sha256:cde70e1721bce55a16b977379bacc0ab74f3f88014ee5589852540eb1ce675a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZ7LOJRQJTHC64H3AGHHLI23DV/bundle.json","state_url":"https://pith.science/pith/BZ7LOJRQJTHC64H3AGHHLI23DV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZ7LOJRQJTHC64H3AGHHLI23DV/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":"2026-05-28T23:35:37Z","links":{"resolver":"https://pith.science/pith/BZ7LOJRQJTHC64H3AGHHLI23DV","bundle":"https://pith.science/pith/BZ7LOJRQJTHC64H3AGHHLI23DV/bundle.json","state":"https://pith.science/pith/BZ7LOJRQJTHC64H3AGHHLI23DV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZ7LOJRQJTHC64H3AGHHLI23DV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BZ7LOJRQJTHC64H3AGHHLI23DV","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":"4066621c9ad330705f685b3a2f939151ff6c208ca5d83f4d909d4b0d6bbabfa4","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-02-03T21:23:46Z","title_canon_sha256":"2146bebce4ceacaf5cffdda4c3d7d52c16a3eebca918230566d1ac62d8207edb"},"schema_version":"1.0","source":{"id":"1702.01166","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.01166","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1702.01166v2","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01166","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"BZ7LOJRQJTHC","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BZ7LOJRQJTHC64H3","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BZ7LOJRQ","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:cde70e1721bce55a16b977379bacc0ab74f3f88014ee5589852540eb1ce675a1","target":"graph","created_at":"2026-05-17T23:42:14Z","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":"For massive data, the family of subsampling algorithms is popular to downsize the data volume and reduce computational burden. Existing studies focus on approximating the ordinary least squares estimate in linear regression, where statistical leverage scores are often used to define subsampling probabilities. In this paper, we propose fast subsampling algorithms to efficiently approximate the maximum likelihood estimate in logistic regression. We first establish consistency and asymptotic normality of the estimator from a general subsampling algorithm, and then derive optimal subsampling proba","authors_text":"Haiying Wang, Ping Ma, Rong Zhu","cross_cats":["stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-02-03T21:23:46Z","title":"Optimal Subsampling for Large Sample Logistic Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01166","kind":"arxiv","version":2},"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:e0c796d6dff149fc7c2c15fabadd7edd871fbe3331b7ad82da2346c1abb9e105","target":"record","created_at":"2026-05-17T23:42:14Z","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":"4066621c9ad330705f685b3a2f939151ff6c208ca5d83f4d909d4b0d6bbabfa4","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-02-03T21:23:46Z","title_canon_sha256":"2146bebce4ceacaf5cffdda4c3d7d52c16a3eebca918230566d1ac62d8207edb"},"schema_version":"1.0","source":{"id":"1702.01166","kind":"arxiv","version":2}},"canonical_sha256":"0e7eb726304cce2f70fb018e75a35b1d775a74041fe2dd8488bcda11e063fec8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e7eb726304cce2f70fb018e75a35b1d775a74041fe2dd8488bcda11e063fec8","first_computed_at":"2026-05-17T23:42:14.427103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:14.427103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+b7rybVpcFCH1YlGNcpOuhNSxmQwtcDYAIfN1acCNFrDt5Okg23PwmzEqW8oqXF3LuBdh/crAVP3ooWrAKydDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:14.427945Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.01166","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0c796d6dff149fc7c2c15fabadd7edd871fbe3331b7ad82da2346c1abb9e105","sha256:cde70e1721bce55a16b977379bacc0ab74f3f88014ee5589852540eb1ce675a1"],"state_sha256":"97b63b4c4482400c070cb74eb5ed5bc8ca8e1d18a6a3cdff3bcc522449647aa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xHFn3tDqZPutaBfRypf7fn2kgDukKcdPCU9fnKhgipLEY8hGbdaqPVJUZ0/2onxA4Mkaw5EUTAE4qxpLKqjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:35:37.750345Z","bundle_sha256":"f32f601543033a0b428a36ece96031413acc46e6c24c331d2056ae37a0263684"}}