{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RED652WRAXGYQN2NQKUB3C4IEY","short_pith_number":"pith:RED652WR","canonical_record":{"source":{"id":"1805.08920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T01:07:47Z","cross_cats_sorted":["cs.CV","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8efd5488d4be9f58a863543b6b43940c057c400a74254580ad577f5e2d9ecaa4","abstract_canon_sha256":"df09a53237e098f5c513f864ee9cae6110b64a3384d97d61da6058ab8084126c"},"schema_version":"1.0"},"canonical_sha256":"8907eeead105cd88374d82a81d8b88260f7a7cee52ebf283f7874395628bdae2","source":{"kind":"arxiv","id":"1805.08920","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08920","created_at":"2026-05-17T23:54:48Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08920v2","created_at":"2026-05-17T23:54:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08920","created_at":"2026-05-17T23:54:48Z"},{"alias_kind":"pith_short_12","alias_value":"RED652WRAXGY","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RED652WRAXGYQN2N","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RED652WR","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RED652WRAXGYQN2NQKUB3C4IEY","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T01:07:47Z","cross_cats_sorted":["cs.CV","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8efd5488d4be9f58a863543b6b43940c057c400a74254580ad577f5e2d9ecaa4","abstract_canon_sha256":"df09a53237e098f5c513f864ee9cae6110b64a3384d97d61da6058ab8084126c"},"schema_version":"1.0"},"canonical_sha256":"8907eeead105cd88374d82a81d8b88260f7a7cee52ebf283f7874395628bdae2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:48.404113Z","signature_b64":"GzTVHmPMjm+qquQUJ9f6FJSiKZmjsP50BFvGSdMbq3scx+4GqCmNagQHcP7NnDSVTtwduMFj9SKdX79SKN7nDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8907eeead105cd88374d82a81d8b88260f7a7cee52ebf283f7874395628bdae2","last_reissued_at":"2026-05-17T23:54:48.403616Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:48.403616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08920","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":"2026-05-17T23:54:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCBDq6liSxyNyDxhO/mbwRwcb2HnM4DHjfCmbXs0tFY/5hlo/pTFejwbJqh1qvvJ3tOMgvUiAwmLP4+TnZBkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:19:14.239525Z"},"content_sha256":"77c15581a1d73a76872f88bfd4d0ac608656c02bbd8f4ff0f1176c28b8222408","schema_version":"1.0","event_id":"sha256:77c15581a1d73a76872f88bfd4d0ac608656c02bbd8f4ff0f1176c28b8222408"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RED652WRAXGYQN2NQKUB3C4IEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Newton-based statistical inference using only stochastic gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Anastasios Kyrillidis, Constantine Caramanis, Liu Liu, Tianyang Li","submitted_at":"2018-05-23T01:07:47Z","abstract_excerpt":"We present a novel statistical inference framework for convex empirical risk minimization, using approximate stochastic Newton steps. The proposed algorithm is based on the notion of finite differences and allows the approximation of a Hessian-vector product from first-order information. In theory, our method efficiently computes the statistical error covariance in $M$-estimation, both for unregularized convex learning problems and high-dimensional LASSO regression, without using exact second order information, or resampling the entire data set. We also present a stochastic gradient sampling s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08920","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":"2026-05-17T23:54:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQ/VH46GJLcQDSXMtVpmk1gXLeotvFZil4z4XVhxDNznan67QbboU5j51/JE/Z7dR4eJ7Qe/3TkkVuTSCq/kAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:19:14.240199Z"},"content_sha256":"029e5fbb213dfc434fecaa380cd1a4bff3a811409a916a42af6bdd16050bbd71","schema_version":"1.0","event_id":"sha256:029e5fbb213dfc434fecaa380cd1a4bff3a811409a916a42af6bdd16050bbd71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RED652WRAXGYQN2NQKUB3C4IEY/bundle.json","state_url":"https://pith.science/pith/RED652WRAXGYQN2NQKUB3C4IEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RED652WRAXGYQN2NQKUB3C4IEY/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":"2026-05-25T17:19:14Z","links":{"resolver":"https://pith.science/pith/RED652WRAXGYQN2NQKUB3C4IEY","bundle":"https://pith.science/pith/RED652WRAXGYQN2NQKUB3C4IEY/bundle.json","state":"https://pith.science/pith/RED652WRAXGYQN2NQKUB3C4IEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RED652WRAXGYQN2NQKUB3C4IEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RED652WRAXGYQN2NQKUB3C4IEY","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":"df09a53237e098f5c513f864ee9cae6110b64a3384d97d61da6058ab8084126c","cross_cats_sorted":["cs.CV","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T01:07:47Z","title_canon_sha256":"8efd5488d4be9f58a863543b6b43940c057c400a74254580ad577f5e2d9ecaa4"},"schema_version":"1.0","source":{"id":"1805.08920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08920","created_at":"2026-05-17T23:54:48Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08920v2","created_at":"2026-05-17T23:54:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08920","created_at":"2026-05-17T23:54:48Z"},{"alias_kind":"pith_short_12","alias_value":"RED652WRAXGY","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RED652WRAXGYQN2N","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RED652WR","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:029e5fbb213dfc434fecaa380cd1a4bff3a811409a916a42af6bdd16050bbd71","target":"graph","created_at":"2026-05-17T23:54:48Z","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 novel statistical inference framework for convex empirical risk minimization, using approximate stochastic Newton steps. The proposed algorithm is based on the notion of finite differences and allows the approximation of a Hessian-vector product from first-order information. In theory, our method efficiently computes the statistical error covariance in $M$-estimation, both for unregularized convex learning problems and high-dimensional LASSO regression, without using exact second order information, or resampling the entire data set. We also present a stochastic gradient sampling s","authors_text":"Anastasios Kyrillidis, Constantine Caramanis, Liu Liu, Tianyang Li","cross_cats":["cs.CV","math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T01:07:47Z","title":"Approximate Newton-based statistical inference using only stochastic gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08920","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":"sha256:77c15581a1d73a76872f88bfd4d0ac608656c02bbd8f4ff0f1176c28b8222408","target":"record","created_at":"2026-05-17T23:54:48Z","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":"df09a53237e098f5c513f864ee9cae6110b64a3384d97d61da6058ab8084126c","cross_cats_sorted":["cs.CV","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T01:07:47Z","title_canon_sha256":"8efd5488d4be9f58a863543b6b43940c057c400a74254580ad577f5e2d9ecaa4"},"schema_version":"1.0","source":{"id":"1805.08920","kind":"arxiv","version":2}},"canonical_sha256":"8907eeead105cd88374d82a81d8b88260f7a7cee52ebf283f7874395628bdae2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8907eeead105cd88374d82a81d8b88260f7a7cee52ebf283f7874395628bdae2","first_computed_at":"2026-05-17T23:54:48.403616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:48.403616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzTVHmPMjm+qquQUJ9f6FJSiKZmjsP50BFvGSdMbq3scx+4GqCmNagQHcP7NnDSVTtwduMFj9SKdX79SKN7nDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:48.404113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77c15581a1d73a76872f88bfd4d0ac608656c02bbd8f4ff0f1176c28b8222408","sha256:029e5fbb213dfc434fecaa380cd1a4bff3a811409a916a42af6bdd16050bbd71"],"state_sha256":"0b27649882f2f7469ae151a85ffebaaf1cb77696ad07d91cb21742de723bf6fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lO/Xod5zu6vsO0zFBVzirA+iODEiJzQBx/8P+lXYxCditw9+fr67HjKWBDXueche9j5fWdA9LNHCfW2EjovDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:19:14.244106Z","bundle_sha256":"10e89d8bb23e08ee0b4ca4d91da7293d32ad099ccadeefebb6a054225df17545"}}