{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KJ5YCU4M3LLJT476ANXEYXBWRK","short_pith_number":"pith:KJ5YCU4M","canonical_record":{"source":{"id":"1803.09349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T21:37:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae3557aaa990690fb40352b9603db75c508f23a50f2edc9c0a33528ae0a3c84e","abstract_canon_sha256":"af6ed2edc1c71422c0b19b6f44a30939c2ec9b66731375cbdb2c3800945cfa3f"},"schema_version":"1.0"},"canonical_sha256":"527b81538cdad699f3fe036e4c5c368aa15421d18f8ed7eaf1f993ce32eaf6bd","source":{"kind":"arxiv","id":"1803.09349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09349","created_at":"2026-05-17T23:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09349v2","created_at":"2026-05-17T23:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09349","created_at":"2026-05-17T23:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"KJ5YCU4M3LLJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KJ5YCU4M3LLJT476","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KJ5YCU4M","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KJ5YCU4M3LLJT476ANXEYXBWRK","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T21:37:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae3557aaa990690fb40352b9603db75c508f23a50f2edc9c0a33528ae0a3c84e","abstract_canon_sha256":"af6ed2edc1c71422c0b19b6f44a30939c2ec9b66731375cbdb2c3800945cfa3f"},"schema_version":"1.0"},"canonical_sha256":"527b81538cdad699f3fe036e4c5c368aa15421d18f8ed7eaf1f993ce32eaf6bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:19.381049Z","signature_b64":"HHELQppqHSjm7YyJzxeF5NQTTw4qfG+J+exRkykaeig324d0a/iMJUM7TR50nLK7hXzG6z8pjzqTGSEOXWysBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527b81538cdad699f3fe036e4c5c368aa15421d18f8ed7eaf1f993ce32eaf6bd","last_reissued_at":"2026-05-17T23:58:19.380595Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:19.380595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09349","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":"2026-05-17T23:58:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HW7AcWrAAECauKoIADyyZTXf6Gvq9ueV2x5iCfo/HMFKdZr5UNormaU0uxMXYlIwHB5BeWqHGL24DOq4wwA5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:56:35.322346Z"},"content_sha256":"47be454e50649e3920853dd1ceddb28565dfee836d6e4bf3b3301b4d469ea5c9","schema_version":"1.0","event_id":"sha256:47be454e50649e3920853dd1ceddb28565dfee836d6e4bf3b3301b4d469ea5c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KJ5YCU4M3LLJT476ANXEYXBWRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Logistic Regression: The Importance of Being Improper","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dylan J. Foster, Haipeng Luo, Karthik Sridharan, Mehryar Mohri, Satyen Kale","submitted_at":"2018-03-25T21:37:08Z","abstract_excerpt":"Learning linear predictors with the logistic loss---both in stochastic and online settings---is a fundamental task in machine learning and statistics, with direct connections to classification and boosting. Existing \"fast rates\" for this setting exhibit exponential dependence on the predictor norm, and Hazan et al. (2014) showed that this is unfortunately unimprovable. Starting with the simple observation that the logistic loss is $1$-mixable, we design a new efficient improper learning algorithm for online logistic regression that circumvents the aforementioned lower bound with a regret bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09349","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":"2026-05-17T23:58:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T092NVCQ80EIfWPyiv6TJrzpwKLaK3LXtVur3FN2sGiJk6Ct5TH+us5zzIa3kFj5oRi5vcoR64tep11EgMxPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:56:35.322706Z"},"content_sha256":"423a53be3904c0b041004ece682afbf86b96813f81ffb3b6dd31d7669ee45169","schema_version":"1.0","event_id":"sha256:423a53be3904c0b041004ece682afbf86b96813f81ffb3b6dd31d7669ee45169"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJ5YCU4M3LLJT476ANXEYXBWRK/bundle.json","state_url":"https://pith.science/pith/KJ5YCU4M3LLJT476ANXEYXBWRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJ5YCU4M3LLJT476ANXEYXBWRK/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":"2026-05-28T13:56:35Z","links":{"resolver":"https://pith.science/pith/KJ5YCU4M3LLJT476ANXEYXBWRK","bundle":"https://pith.science/pith/KJ5YCU4M3LLJT476ANXEYXBWRK/bundle.json","state":"https://pith.science/pith/KJ5YCU4M3LLJT476ANXEYXBWRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJ5YCU4M3LLJT476ANXEYXBWRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KJ5YCU4M3LLJT476ANXEYXBWRK","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":"af6ed2edc1c71422c0b19b6f44a30939c2ec9b66731375cbdb2c3800945cfa3f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T21:37:08Z","title_canon_sha256":"ae3557aaa990690fb40352b9603db75c508f23a50f2edc9c0a33528ae0a3c84e"},"schema_version":"1.0","source":{"id":"1803.09349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09349","created_at":"2026-05-17T23:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09349v2","created_at":"2026-05-17T23:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09349","created_at":"2026-05-17T23:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"KJ5YCU4M3LLJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KJ5YCU4M3LLJT476","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KJ5YCU4M","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:423a53be3904c0b041004ece682afbf86b96813f81ffb3b6dd31d7669ee45169","target":"graph","created_at":"2026-05-17T23:58:19Z","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":"Learning linear predictors with the logistic loss---both in stochastic and online settings---is a fundamental task in machine learning and statistics, with direct connections to classification and boosting. Existing \"fast rates\" for this setting exhibit exponential dependence on the predictor norm, and Hazan et al. (2014) showed that this is unfortunately unimprovable. Starting with the simple observation that the logistic loss is $1$-mixable, we design a new efficient improper learning algorithm for online logistic regression that circumvents the aforementioned lower bound with a regret bound","authors_text":"Dylan J. Foster, Haipeng Luo, Karthik Sridharan, Mehryar Mohri, Satyen Kale","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T21:37:08Z","title":"Logistic Regression: The Importance of Being Improper"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09349","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":"sha256:47be454e50649e3920853dd1ceddb28565dfee836d6e4bf3b3301b4d469ea5c9","target":"record","created_at":"2026-05-17T23:58:19Z","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":"af6ed2edc1c71422c0b19b6f44a30939c2ec9b66731375cbdb2c3800945cfa3f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T21:37:08Z","title_canon_sha256":"ae3557aaa990690fb40352b9603db75c508f23a50f2edc9c0a33528ae0a3c84e"},"schema_version":"1.0","source":{"id":"1803.09349","kind":"arxiv","version":2}},"canonical_sha256":"527b81538cdad699f3fe036e4c5c368aa15421d18f8ed7eaf1f993ce32eaf6bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527b81538cdad699f3fe036e4c5c368aa15421d18f8ed7eaf1f993ce32eaf6bd","first_computed_at":"2026-05-17T23:58:19.380595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:19.380595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHELQppqHSjm7YyJzxeF5NQTTw4qfG+J+exRkykaeig324d0a/iMJUM7TR50nLK7hXzG6z8pjzqTGSEOXWysBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:19.381049Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47be454e50649e3920853dd1ceddb28565dfee836d6e4bf3b3301b4d469ea5c9","sha256:423a53be3904c0b041004ece682afbf86b96813f81ffb3b6dd31d7669ee45169"],"state_sha256":"13b087f0aa952416495d783843272af3dbe97e8663660ecdfea98fcade1f8ff2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4lgufm/MZHtbDSrrToj/g2uxAcGRTAGRIq2luLye4I3KeCBIj2yuj92neBed9I1yT9IBTRsXdwzApnasSm4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:56:35.324792Z","bundle_sha256":"3d62b9209cfe15eb23b3a47b765885956ee8eb478cb32ecae98a13d6af5d71ad"}}