{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EFSX3SGU3P6PSTIFHWPDQP3RZ6","short_pith_number":"pith:EFSX3SGU","canonical_record":{"source":{"id":"2411.06739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T06:19:33Z","cross_cats_sorted":[],"title_canon_sha256":"9a547a624f8e77c4ece6abedfa88555a84fff00aa4269685799a56aebcfba47f","abstract_canon_sha256":"bd95e4bb998a2b0dfeaa6d4feb06b9f279a55b058e8f8ca41564d6bd8a04ea58"},"schema_version":"1.0"},"canonical_sha256":"21657dc8d4dbfcf94d053d9e383f71cf8c9c1c6ba048e07e5a3a66d253b813f1","source":{"kind":"arxiv","id":"2411.06739","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06739","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06739v1","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06739","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"EFSX3SGU3P6P","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"EFSX3SGU3P6PSTIF","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"EFSX3SGU","created_at":"2026-07-05T09:33:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EFSX3SGU3P6PSTIFHWPDQP3RZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T06:19:33Z","cross_cats_sorted":[],"title_canon_sha256":"9a547a624f8e77c4ece6abedfa88555a84fff00aa4269685799a56aebcfba47f","abstract_canon_sha256":"bd95e4bb998a2b0dfeaa6d4feb06b9f279a55b058e8f8ca41564d6bd8a04ea58"},"schema_version":"1.0"},"canonical_sha256":"21657dc8d4dbfcf94d053d9e383f71cf8c9c1c6ba048e07e5a3a66d253b813f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:50.752801Z","signature_b64":"ucjuuxkRKrYlF+UokhmAZ2Xw8XQba9Cmgy7paxj/SmmpvNuJlH0Ikk9CFm8Ff2BtVLzETrHTVfIPT7qe+HAOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21657dc8d4dbfcf94d053d9e383f71cf8c9c1c6ba048e07e5a3a66d253b813f1","last_reissued_at":"2026-07-05T09:33:50.752350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:50.752350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06739","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":"2026-07-05T09:33:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FyYM4FpHeHGJZVbj4U+Bc7Qr6v6etnRLgOuSkwijuMYSA8GVI5UaNW20BgebfY86Tr/Xshz1XQa3guUTMoiWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:42:30.470757Z"},"content_sha256":"3f3c823778cbb19a24638592cecc332985923530331906557a017f125ff37b56","schema_version":"1.0","event_id":"sha256:3f3c823778cbb19a24638592cecc332985923530331906557a017f125ff37b56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EFSX3SGU3P6PSTIFHWPDQP3RZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Haolin Liu, Julian Zimmert, Zakaria Mhammedi","submitted_at":"2024-11-11T06:19:33Z","abstract_excerpt":"We consider regret minimization in low-rank MDPs with fixed transition and adversarial losses. Previous work has investigated this problem under either full-information loss feedback with unknown transitions (Zhao et al., 2024), or bandit loss feedback with known transition (Foster et al., 2022). First, we improve the $poly(d, A, H)T^{5/6}$ regret bound of Zhao et al. (2024) to $poly(d, A, H)T^{2/3}$ for the full-information unknown transition setting, where d is the rank of the transitions, A is the number of actions, H is the horizon length, and T is the number of episodes. Next, we initiate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06739","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.06739/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T09:33:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9rpWEzzxNJ1cbDhtjhzOWjkP5dGNFwe9Pkey1F5rehOnr7obQKdtnyAiar/5cqLKXmO2RrCbHgG2Z3kXf+TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:42:30.471129Z"},"content_sha256":"c41429b7e1e3c59027b9f66e922c4f034ae83ac561c273cd9b08ebb05786e165","schema_version":"1.0","event_id":"sha256:c41429b7e1e3c59027b9f66e922c4f034ae83ac561c273cd9b08ebb05786e165"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6/bundle.json","state_url":"https://pith.science/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6/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":"2026-07-05T15:42:30Z","links":{"resolver":"https://pith.science/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6","bundle":"https://pith.science/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6/bundle.json","state":"https://pith.science/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFSX3SGU3P6PSTIFHWPDQP3RZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EFSX3SGU3P6PSTIFHWPDQP3RZ6","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":"bd95e4bb998a2b0dfeaa6d4feb06b9f279a55b058e8f8ca41564d6bd8a04ea58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T06:19:33Z","title_canon_sha256":"9a547a624f8e77c4ece6abedfa88555a84fff00aa4269685799a56aebcfba47f"},"schema_version":"1.0","source":{"id":"2411.06739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06739","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06739v1","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06739","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"EFSX3SGU3P6P","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"EFSX3SGU3P6PSTIF","created_at":"2026-07-05T09:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"EFSX3SGU","created_at":"2026-07-05T09:33:50Z"}],"graph_snapshots":[{"event_id":"sha256:c41429b7e1e3c59027b9f66e922c4f034ae83ac561c273cd9b08ebb05786e165","target":"graph","created_at":"2026-07-05T09:33:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.06739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider regret minimization in low-rank MDPs with fixed transition and adversarial losses. Previous work has investigated this problem under either full-information loss feedback with unknown transitions (Zhao et al., 2024), or bandit loss feedback with known transition (Foster et al., 2022). First, we improve the $poly(d, A, H)T^{5/6}$ regret bound of Zhao et al. (2024) to $poly(d, A, H)T^{2/3}$ for the full-information unknown transition setting, where d is the rank of the transitions, A is the number of actions, H is the horizon length, and T is the number of episodes. Next, we initiate","authors_text":"Chen-Yu Wei, Haolin Liu, Julian Zimmert, Zakaria Mhammedi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T06:19:33Z","title":"Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06739","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":"sha256:3f3c823778cbb19a24638592cecc332985923530331906557a017f125ff37b56","target":"record","created_at":"2026-07-05T09:33:50Z","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":"bd95e4bb998a2b0dfeaa6d4feb06b9f279a55b058e8f8ca41564d6bd8a04ea58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T06:19:33Z","title_canon_sha256":"9a547a624f8e77c4ece6abedfa88555a84fff00aa4269685799a56aebcfba47f"},"schema_version":"1.0","source":{"id":"2411.06739","kind":"arxiv","version":1}},"canonical_sha256":"21657dc8d4dbfcf94d053d9e383f71cf8c9c1c6ba048e07e5a3a66d253b813f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21657dc8d4dbfcf94d053d9e383f71cf8c9c1c6ba048e07e5a3a66d253b813f1","first_computed_at":"2026-07-05T09:33:50.752350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:50.752350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ucjuuxkRKrYlF+UokhmAZ2Xw8XQba9Cmgy7paxj/SmmpvNuJlH0Ikk9CFm8Ff2BtVLzETrHTVfIPT7qe+HAOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:50.752801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f3c823778cbb19a24638592cecc332985923530331906557a017f125ff37b56","sha256:c41429b7e1e3c59027b9f66e922c4f034ae83ac561c273cd9b08ebb05786e165"],"state_sha256":"ae0fc06c3a5e3daeb5ab7e9cb06e2009c073bb5c754ece621206be0de8ae057d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4XgaEiFZHS14IHtAbLRU8I8QVOTPKr0349YL1+tuRb7t4PHzgu+cgNOTuSG1mj27jaUNYD2Fyx4V0PDTBO0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:42:30.473348Z","bundle_sha256":"461eee473692334415ad36247132147fc6ba1784042cd772b3179a12f33af9d0"}}