{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:K6RTRA3657W4MH4S2BJXTM2LJJ","short_pith_number":"pith:K6RTRA36","canonical_record":{"source":{"id":"1210.4843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2012-10-16T17:34:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"858e55c9a385e0f768533414fa3dbc40f8dbfd593992e2e4d14e2fc9baf65b01","abstract_canon_sha256":"72477f3e6b46e84fdbcafd75daada69795ebb89415428eed0266f16e66c20ce9"},"schema_version":"1.0"},"canonical_sha256":"57a338837eefedc61f92d05379b34b4a68000a640df3e1a9178d189e4119d43d","source":{"kind":"arxiv","id":"1210.4843","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1210.4843","created_at":"2026-05-18T03:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"1210.4843v1","created_at":"2026-05-18T03:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.4843","created_at":"2026-05-18T03:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"K6RTRA3657W4","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"K6RTRA3657W4MH4S","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"K6RTRA36","created_at":"2026-05-18T12:27:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:K6RTRA3657W4MH4S2BJXTM2LJJ","target":"record","payload":{"canonical_record":{"source":{"id":"1210.4843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2012-10-16T17:34:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"858e55c9a385e0f768533414fa3dbc40f8dbfd593992e2e4d14e2fc9baf65b01","abstract_canon_sha256":"72477f3e6b46e84fdbcafd75daada69795ebb89415428eed0266f16e66c20ce9"},"schema_version":"1.0"},"canonical_sha256":"57a338837eefedc61f92d05379b34b4a68000a640df3e1a9178d189e4119d43d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:42:55.551854Z","signature_b64":"SCtTy7WVRWtpAB8B0XsmUv2+y7zZYnz/BgsPcTsd0Ps7acchoucsdJw9JvCku31QNv9V1R5FYsKKSQgF1Y2lAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57a338837eefedc61f92d05379b34b4a68000a640df3e1a9178d189e4119d43d","last_reissued_at":"2026-05-18T03:42:55.551299Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:42:55.551299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1210.4843","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":"2026-05-18T03:42:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWYy+SnciEhXw/41dsm64+YqnTOMQz6867yh1PQnXOvAbj+lmFDoZMfrMYTY4cosZbSwO6jebDlfHJa6EuszDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:23:04.711560Z"},"content_sha256":"5ba72b7f78fc2fa82f68895555587553a1cd0bd64a64f55df2aef0bb7a55c2d2","schema_version":"1.0","event_id":"sha256:5ba72b7f78fc2fa82f68895555587553a1cd0bd64a64f55df2aef0bb7a55c2d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:K6RTRA3657W4MH4S2BJXTM2LJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic MDPs with Adversarial Rewards and Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GT","authors_text":"Ambuj Tewari, Ofer Dekel, Raman Arora","submitted_at":"2012-10-16T17:34:04Z","abstract_excerpt":"We consider a Markov decision process with deterministic state transition dynamics, adversarially generated rewards that change arbitrarily from round to round, and a bandit feedback model in which the decision maker only observes the rewards it receives. In this setting, we present a novel and efficient online decision making algorithm named MarcoPolo. Under mild assumptions on the structure of the transition dynamics, we prove that MarcoPolo enjoys a regret of O(T^(3/4)sqrt(log(T))) against the best deterministic policy in hindsight. Specifically, our analysis does not rely on the stringent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.4843","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":"2026-05-18T03:42:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"luXOPvKFCAro7jEFKHj1OTRJAPSA6qJqbF/InaMDs+HXbBC+ntg5Fi79O/WvyrAzBJpwK4M+TU/FUJd26+1eDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:23:04.711935Z"},"content_sha256":"00f94a01f19bd5dfa81186c4558bee094d2304c8d2dc85f52a721afcc87c3a79","schema_version":"1.0","event_id":"sha256:00f94a01f19bd5dfa81186c4558bee094d2304c8d2dc85f52a721afcc87c3a79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6RTRA3657W4MH4S2BJXTM2LJJ/bundle.json","state_url":"https://pith.science/pith/K6RTRA3657W4MH4S2BJXTM2LJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6RTRA3657W4MH4S2BJXTM2LJJ/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":"2026-05-31T11:23:04Z","links":{"resolver":"https://pith.science/pith/K6RTRA3657W4MH4S2BJXTM2LJJ","bundle":"https://pith.science/pith/K6RTRA3657W4MH4S2BJXTM2LJJ/bundle.json","state":"https://pith.science/pith/K6RTRA3657W4MH4S2BJXTM2LJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6RTRA3657W4MH4S2BJXTM2LJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:K6RTRA3657W4MH4S2BJXTM2LJJ","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":"72477f3e6b46e84fdbcafd75daada69795ebb89415428eed0266f16e66c20ce9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2012-10-16T17:34:04Z","title_canon_sha256":"858e55c9a385e0f768533414fa3dbc40f8dbfd593992e2e4d14e2fc9baf65b01"},"schema_version":"1.0","source":{"id":"1210.4843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1210.4843","created_at":"2026-05-18T03:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"1210.4843v1","created_at":"2026-05-18T03:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.4843","created_at":"2026-05-18T03:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"K6RTRA3657W4","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"K6RTRA3657W4MH4S","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"K6RTRA36","created_at":"2026-05-18T12:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:00f94a01f19bd5dfa81186c4558bee094d2304c8d2dc85f52a721afcc87c3a79","target":"graph","created_at":"2026-05-18T03:42:55Z","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 consider a Markov decision process with deterministic state transition dynamics, adversarially generated rewards that change arbitrarily from round to round, and a bandit feedback model in which the decision maker only observes the rewards it receives. In this setting, we present a novel and efficient online decision making algorithm named MarcoPolo. Under mild assumptions on the structure of the transition dynamics, we prove that MarcoPolo enjoys a regret of O(T^(3/4)sqrt(log(T))) against the best deterministic policy in hindsight. Specifically, our analysis does not rely on the stringent ","authors_text":"Ambuj Tewari, Ofer Dekel, Raman Arora","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2012-10-16T17:34:04Z","title":"Deterministic MDPs with Adversarial Rewards and Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.4843","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":"sha256:5ba72b7f78fc2fa82f68895555587553a1cd0bd64a64f55df2aef0bb7a55c2d2","target":"record","created_at":"2026-05-18T03:42:55Z","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":"72477f3e6b46e84fdbcafd75daada69795ebb89415428eed0266f16e66c20ce9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2012-10-16T17:34:04Z","title_canon_sha256":"858e55c9a385e0f768533414fa3dbc40f8dbfd593992e2e4d14e2fc9baf65b01"},"schema_version":"1.0","source":{"id":"1210.4843","kind":"arxiv","version":1}},"canonical_sha256":"57a338837eefedc61f92d05379b34b4a68000a640df3e1a9178d189e4119d43d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57a338837eefedc61f92d05379b34b4a68000a640df3e1a9178d189e4119d43d","first_computed_at":"2026-05-18T03:42:55.551299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:42:55.551299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SCtTy7WVRWtpAB8B0XsmUv2+y7zZYnz/BgsPcTsd0Ps7acchoucsdJw9JvCku31QNv9V1R5FYsKKSQgF1Y2lAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:42:55.551854Z","signed_message":"canonical_sha256_bytes"},"source_id":"1210.4843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ba72b7f78fc2fa82f68895555587553a1cd0bd64a64f55df2aef0bb7a55c2d2","sha256:00f94a01f19bd5dfa81186c4558bee094d2304c8d2dc85f52a721afcc87c3a79"],"state_sha256":"ce9f447633040c70fa94b12b879a6fbca65a56bb60f01280fcbbd3cfdd399a62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIRx1CJoJblsQ5aScRGFk7wsEFwC5idVtKy4Gaf/CLt5CIq6I6hzPa18SV2l/yVqyLv7bGVLnO8GX6TbdkHpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T11:23:04.714047Z","bundle_sha256":"93d765a87d214d9fb3dd17d518747819329a8fe186e4ac32ce4553c51cba8713"}}