{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:LZUURGAXU4XZAA3X4YW3GADU46","short_pith_number":"pith:LZUURGAX","canonical_record":{"source":{"id":"1206.6400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"257e2328337e342240e7f99b9a2958152b0bac0cff7391977b960890c8df9591","abstract_canon_sha256":"c021999155cf5f55d932ad8715e6e48230d0e91561a186dc4913204672041f32"},"schema_version":"1.0"},"canonical_sha256":"5e69489817a72f900377e62db30074e7b8f95b22b10459d0f68c7f5be792c2f1","source":{"kind":"arxiv","id":"1206.6400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6400","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6400v1","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6400","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"LZUURGAXU4XZ","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LZUURGAXU4XZAA3X","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LZUURGAX","created_at":"2026-05-18T12:27:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:LZUURGAXU4XZAA3X4YW3GADU46","target":"record","payload":{"canonical_record":{"source":{"id":"1206.6400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"257e2328337e342240e7f99b9a2958152b0bac0cff7391977b960890c8df9591","abstract_canon_sha256":"c021999155cf5f55d932ad8715e6e48230d0e91561a186dc4913204672041f32"},"schema_version":"1.0"},"canonical_sha256":"5e69489817a72f900377e62db30074e7b8f95b22b10459d0f68c7f5be792c2f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:14.443338Z","signature_b64":"/VBKDAcugXOEQCNebPgF5iV/ylpoqJSGXbeZk6DdHziTX6QFTM5oiBhKQwzQpGQo6uFtuTSbnWeaSk5emZGcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e69489817a72f900377e62db30074e7b8f95b22b10459d0f68c7f5be792c2f1","last_reissued_at":"2026-05-18T03:52:14.442648Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:14.442648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.6400","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":"2026-05-18T03:52:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8xaqGQUBAOX82ucwvxWguDvSEr2fjnwrBjus0dzUtvyGKWhdqolDOTqREbcmC/EolVrRyE7MEIRiNWtYYDWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:26:35.199226Z"},"content_sha256":"54f4e6815862355fb28b3ff4dc7af40b0d4b7c219655ee3f80f6369d46c3954d","schema_version":"1.0","event_id":"sha256:54f4e6815862355fb28b3ff4dc7af40b0d4b7c219655ee3f80f6369d46c3954d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:LZUURGAXU4XZAA3X4YW3GADU46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari (University of Texas), Ofer Dekel (Microsoft Research), Raman Arora (TTIC)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to adapt to the online algorithm's actions. We define the alternative notion of policy regret, which attempts to provide a more meaningful way to measure an online algorithm's performance against adaptive adversaries. Focusing on the online bandit setting, we show that no bandit algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6400","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":"2026-05-18T03:52:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HFitGJjpK+6cyiI2kJNNBrtjdB2qM9QOHzb0cDCXXC8HuuL47lJGTfrMWPAfnc9fe5cSvLO0iKO6mmS2ByHSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:26:35.199794Z"},"content_sha256":"1bb8414891956620aa6ae4cc94cd1b84dbf440a6c78e90d6ffcf5681d907963b","schema_version":"1.0","event_id":"sha256:1bb8414891956620aa6ae4cc94cd1b84dbf440a6c78e90d6ffcf5681d907963b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZUURGAXU4XZAA3X4YW3GADU46/bundle.json","state_url":"https://pith.science/pith/LZUURGAXU4XZAA3X4YW3GADU46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZUURGAXU4XZAA3X4YW3GADU46/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":"2026-06-05T03:26:35Z","links":{"resolver":"https://pith.science/pith/LZUURGAXU4XZAA3X4YW3GADU46","bundle":"https://pith.science/pith/LZUURGAXU4XZAA3X4YW3GADU46/bundle.json","state":"https://pith.science/pith/LZUURGAXU4XZAA3X4YW3GADU46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZUURGAXU4XZAA3X4YW3GADU46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:LZUURGAXU4XZAA3X4YW3GADU46","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":"c021999155cf5f55d932ad8715e6e48230d0e91561a186dc4913204672041f32","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","title_canon_sha256":"257e2328337e342240e7f99b9a2958152b0bac0cff7391977b960890c8df9591"},"schema_version":"1.0","source":{"id":"1206.6400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6400","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6400v1","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6400","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"LZUURGAXU4XZ","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LZUURGAXU4XZAA3X","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LZUURGAX","created_at":"2026-05-18T12:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:1bb8414891956620aa6ae4cc94cd1b84dbf440a6c78e90d6ffcf5681d907963b","target":"graph","created_at":"2026-05-18T03:52:14Z","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":"Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to adapt to the online algorithm's actions. We define the alternative notion of policy regret, which attempts to provide a more meaningful way to measure an online algorithm's performance against adaptive adversaries. Focusing on the online bandit setting, we show that no bandit algo","authors_text":"Ambuj Tewari (University of Texas), Ofer Dekel (Microsoft Research), Raman Arora (TTIC)","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","title":"Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6400","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":"sha256:54f4e6815862355fb28b3ff4dc7af40b0d4b7c219655ee3f80f6369d46c3954d","target":"record","created_at":"2026-05-18T03:52:14Z","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":"c021999155cf5f55d932ad8715e6e48230d0e91561a186dc4913204672041f32","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","title_canon_sha256":"257e2328337e342240e7f99b9a2958152b0bac0cff7391977b960890c8df9591"},"schema_version":"1.0","source":{"id":"1206.6400","kind":"arxiv","version":1}},"canonical_sha256":"5e69489817a72f900377e62db30074e7b8f95b22b10459d0f68c7f5be792c2f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e69489817a72f900377e62db30074e7b8f95b22b10459d0f68c7f5be792c2f1","first_computed_at":"2026-05-18T03:52:14.442648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:14.442648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/VBKDAcugXOEQCNebPgF5iV/ylpoqJSGXbeZk6DdHziTX6QFTM5oiBhKQwzQpGQo6uFtuTSbnWeaSk5emZGcBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:14.443338Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.6400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54f4e6815862355fb28b3ff4dc7af40b0d4b7c219655ee3f80f6369d46c3954d","sha256:1bb8414891956620aa6ae4cc94cd1b84dbf440a6c78e90d6ffcf5681d907963b"],"state_sha256":"78ea5f3a0eca49750199268aff97f4c04163fc63862c72c25b60458e6915d0e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8z0mYfDG7xJodX217Rlwz7nj67Kle1rz98eOj7Z2DDqtOlLvM/Y2Ssbwjtmyggmoz+leHamgVGgC8DbHFpnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T03:26:35.203302Z","bundle_sha256":"8dd440394b6e7de09e87610de923085834c4d19fd67a9948a70a2c4324f9009b"}}