{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OHPTB4PVD4HJF24LNJX73G6EOP","short_pith_number":"pith:OHPTB4PV","canonical_record":{"source":{"id":"1804.07837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T21:46:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"26fc9772cfd94bad386482ec1281df2efc0d6fb991dc99e5daec32f1c4fcd263","abstract_canon_sha256":"b861ae098ad59507bec0147c8d04f95d37823dffa881dfd2ae5838173a1cc5de"},"schema_version":"1.0"},"canonical_sha256":"71df30f1f51f0e92eb8b6a6ffd9bc473e0f54e86dc504e2bab2f1ec2d882bebc","source":{"kind":"arxiv","id":"1804.07837","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07837","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07837v1","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07837","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"OHPTB4PVD4HJ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OHPTB4PVD4HJF24L","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OHPTB4PV","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OHPTB4PVD4HJF24LNJX73G6EOP","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T21:46:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"26fc9772cfd94bad386482ec1281df2efc0d6fb991dc99e5daec32f1c4fcd263","abstract_canon_sha256":"b861ae098ad59507bec0147c8d04f95d37823dffa881dfd2ae5838173a1cc5de"},"schema_version":"1.0"},"canonical_sha256":"71df30f1f51f0e92eb8b6a6ffd9bc473e0f54e86dc504e2bab2f1ec2d882bebc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:52.631460Z","signature_b64":"cKsxuiBKpsYDRQm1Dh883e2ps3W8/aa9hFd+0MbWDvcKts2ZtEymKnk0ehJvni+fKKW6QD9l/k+1m/5nclzWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71df30f1f51f0e92eb8b6a6ffd9bc473e0f54e86dc504e2bab2f1ec2d882bebc","last_reissued_at":"2026-05-18T00:17:52.630818Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:52.630818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07837","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":"2026-05-18T00:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9GAPsHu/Cj0N5iXR/eQvscTgu/uHN3vyg0uyxTqO26ConRKVEILBU7nfxoM89PT4Xah44HJOi59c1rwR0fPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:17:13.557919Z"},"content_sha256":"f3862408d7453cf2a4ac23b19921ce462840c7ca8082e51cdc451a56e86c9101","schema_version":"1.0","event_id":"sha256:f3862408d7453cf2a4ac23b19921ce462840c7ca8082e51cdc451a56e86c9101"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OHPTB4PVD4HJF24LNJX73G6EOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Improper Learning with an Approximation Oracle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li","submitted_at":"2018-04-20T21:46:06Z","abstract_excerpt":"We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per iteration. Furthermore, these algorithms apply to the more general improper learning problems. In the bandit setting, our algorithm also significantly improves the best previously known oracle complexity while maintaining the same regret."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07837","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":"2026-05-18T00:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5rRCHWgmfdv+AlUZ7OZ48LZJDnxDh4fBxkrFSp/8QyevjWakb5GB1HBmvWqcvwHntV8mbM1O7/KR0ddUNOTaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:17:13.558267Z"},"content_sha256":"f430495d80e44e9ad7e62527fc112bca319e25610a786624bbd4fdc6afb5f5f9","schema_version":"1.0","event_id":"sha256:f430495d80e44e9ad7e62527fc112bca319e25610a786624bbd4fdc6afb5f5f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHPTB4PVD4HJF24LNJX73G6EOP/bundle.json","state_url":"https://pith.science/pith/OHPTB4PVD4HJF24LNJX73G6EOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHPTB4PVD4HJF24LNJX73G6EOP/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":"2026-05-31T20:17:13Z","links":{"resolver":"https://pith.science/pith/OHPTB4PVD4HJF24LNJX73G6EOP","bundle":"https://pith.science/pith/OHPTB4PVD4HJF24LNJX73G6EOP/bundle.json","state":"https://pith.science/pith/OHPTB4PVD4HJF24LNJX73G6EOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHPTB4PVD4HJF24LNJX73G6EOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OHPTB4PVD4HJF24LNJX73G6EOP","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":"b861ae098ad59507bec0147c8d04f95d37823dffa881dfd2ae5838173a1cc5de","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T21:46:06Z","title_canon_sha256":"26fc9772cfd94bad386482ec1281df2efc0d6fb991dc99e5daec32f1c4fcd263"},"schema_version":"1.0","source":{"id":"1804.07837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07837","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07837v1","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07837","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"OHPTB4PVD4HJ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OHPTB4PVD4HJF24L","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OHPTB4PV","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:f430495d80e44e9ad7e62527fc112bca319e25610a786624bbd4fdc6afb5f5f9","target":"graph","created_at":"2026-05-18T00:17:52Z","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"},"paper":{"abstract_excerpt":"We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per iteration. Furthermore, these algorithms apply to the more general improper learning problems. In the bandit setting, our algorithm also significantly improves the best previously known oracle complexity while maintaining the same regret.","authors_text":"Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T21:46:06Z","title":"Online Improper Learning with an Approximation Oracle"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07837","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:f3862408d7453cf2a4ac23b19921ce462840c7ca8082e51cdc451a56e86c9101","target":"record","created_at":"2026-05-18T00:17:52Z","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":"b861ae098ad59507bec0147c8d04f95d37823dffa881dfd2ae5838173a1cc5de","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T21:46:06Z","title_canon_sha256":"26fc9772cfd94bad386482ec1281df2efc0d6fb991dc99e5daec32f1c4fcd263"},"schema_version":"1.0","source":{"id":"1804.07837","kind":"arxiv","version":1}},"canonical_sha256":"71df30f1f51f0e92eb8b6a6ffd9bc473e0f54e86dc504e2bab2f1ec2d882bebc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71df30f1f51f0e92eb8b6a6ffd9bc473e0f54e86dc504e2bab2f1ec2d882bebc","first_computed_at":"2026-05-18T00:17:52.630818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:52.630818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cKsxuiBKpsYDRQm1Dh883e2ps3W8/aa9hFd+0MbWDvcKts2ZtEymKnk0ehJvni+fKKW6QD9l/k+1m/5nclzWBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:52.631460Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3862408d7453cf2a4ac23b19921ce462840c7ca8082e51cdc451a56e86c9101","sha256:f430495d80e44e9ad7e62527fc112bca319e25610a786624bbd4fdc6afb5f5f9"],"state_sha256":"f5d29eed8019587ee3e3e6ee0f39ae1e841789a27006928d9fdd8ec498fcd0f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yaCwR7UEvE7e2yW1LGUalFndVK/ru8QAwSsz8q8Ne3sRFMkzZek4w/pZO4wW1FZohU0IyHgq/vgBuqv36MHBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:17:13.560421Z","bundle_sha256":"579f8f52c66daa164d7d88182c6dcefff93301ec7a02a13686a6138568422ad9"}}