{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HWTVUEXSCENSYO4ZGBYLV2I44E","short_pith_number":"pith:HWTVUEXS","canonical_record":{"source":{"id":"2411.03107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T13:55:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"622c75b972a318462bacb77b7e4cc6d9ba953fe2d11730f6be4101f9c800ce27","abstract_canon_sha256":"18097b700a717d064f4012c35de950e992396dbf619c8272d87ba7f800f9f29b"},"schema_version":"1.0"},"canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","source":{"kind":"arxiv","id":"2411.03107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03107","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03107v1","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03107","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"pith_short_12","alias_value":"HWTVUEXSCENS","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"pith_short_16","alias_value":"HWTVUEXSCENSYO4Z","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"pith_short_8","alias_value":"HWTVUEXS","created_at":"2026-07-05T09:31:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HWTVUEXSCENSYO4ZGBYLV2I44E","target":"record","payload":{"canonical_record":{"source":{"id":"2411.03107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T13:55:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"622c75b972a318462bacb77b7e4cc6d9ba953fe2d11730f6be4101f9c800ce27","abstract_canon_sha256":"18097b700a717d064f4012c35de950e992396dbf619c8272d87ba7f800f9f29b"},"schema_version":"1.0"},"canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:25.514938Z","signature_b64":"fn7bH3xu+T/9+HHTJfI9H/5hRKpApOPEFTAboNmRsDohdlA7Pam0y5XqNJxHm/DedorVs4MVC9a3jyj3b6UnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","last_reissued_at":"2026-07-05T09:31:25.514449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:25.514449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.03107","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":"2026-07-05T09:31:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCx0iiKJbiTymrBvQVUL792fkeBRA+aX+quwJcwFFElKkDDGSVX80CK2DQYgxqUO/4CwwmTB4dgKMvCulDU7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T03:54:04.484726Z"},"content_sha256":"27e84eafc871bacff65f70540b45ca4482421c6a04fd9b0254f1146268ee6fc4","schema_version":"1.0","event_id":"sha256:27e84eafc871bacff65f70540b45ca4482421c6a04fd9b0254f1146268ee6fc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HWTVUEXSCENSYO4ZGBYLV2I44E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Long-Fei Li, Peng Zhao, Zhi-Hua Zhou","submitted_at":"2024-11-05T13:55:52Z","abstract_excerpt":"We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations of the two most popular methods: occupancy-measure-based and policy-based methods. We observe that while the occupancy-measure-based method is effective in addressing non-stationary environments, it encounters difficulties with the unknown transition. In contrast, the policy-based method can deal with the unknown transition effectively but faces challenges "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03107","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/2411.03107/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":"2026-07-05T09:31:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EqY3r4at7R+xKdkAaOphQSc3QZsJYRm5Ns5jqLZrd55ZnpxKPx04Vr8gojukkNnEcc/Q8V29nWZ4he0KxMkHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T03:54:04.485103Z"},"content_sha256":"c651e1ff7e3f7af810dce46e3a77070fc7f1ab2793e11bd623d0af790006cbbd","schema_version":"1.0","event_id":"sha256:c651e1ff7e3f7af810dce46e3a77070fc7f1ab2793e11bd623d0af790006cbbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/bundle.json","state_url":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/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":"2026-07-06T03:54:04Z","links":{"resolver":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E","bundle":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/bundle.json","state":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HWTVUEXSCENSYO4ZGBYLV2I44E","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":"18097b700a717d064f4012c35de950e992396dbf619c8272d87ba7f800f9f29b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T13:55:52Z","title_canon_sha256":"622c75b972a318462bacb77b7e4cc6d9ba953fe2d11730f6be4101f9c800ce27"},"schema_version":"1.0","source":{"id":"2411.03107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03107","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03107v1","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03107","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"pith_short_12","alias_value":"HWTVUEXSCENS","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"pith_short_16","alias_value":"HWTVUEXSCENSYO4Z","created_at":"2026-07-05T09:31:25Z"},{"alias_kind":"pith_short_8","alias_value":"HWTVUEXS","created_at":"2026-07-05T09:31:25Z"}],"graph_snapshots":[{"event_id":"sha256:c651e1ff7e3f7af810dce46e3a77070fc7f1ab2793e11bd623d0af790006cbbd","target":"graph","created_at":"2026-07-05T09:31:25Z","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/2411.03107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations of the two most popular methods: occupancy-measure-based and policy-based methods. We observe that while the occupancy-measure-based method is effective in addressing non-stationary environments, it encounters difficulties with the unknown transition. In contrast, the policy-based method can deal with the unknown transition effectively but faces challenges ","authors_text":"Long-Fei Li, Peng Zhao, Zhi-Hua Zhou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T13:55:52Z","title":"Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03107","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":"sha256:27e84eafc871bacff65f70540b45ca4482421c6a04fd9b0254f1146268ee6fc4","target":"record","created_at":"2026-07-05T09:31:25Z","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":"18097b700a717d064f4012c35de950e992396dbf619c8272d87ba7f800f9f29b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T13:55:52Z","title_canon_sha256":"622c75b972a318462bacb77b7e4cc6d9ba953fe2d11730f6be4101f9c800ce27"},"schema_version":"1.0","source":{"id":"2411.03107","kind":"arxiv","version":1}},"canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","first_computed_at":"2026-07-05T09:31:25.514449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:25.514449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fn7bH3xu+T/9+HHTJfI9H/5hRKpApOPEFTAboNmRsDohdlA7Pam0y5XqNJxHm/DedorVs4MVC9a3jyj3b6UnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:25.514938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27e84eafc871bacff65f70540b45ca4482421c6a04fd9b0254f1146268ee6fc4","sha256:c651e1ff7e3f7af810dce46e3a77070fc7f1ab2793e11bd623d0af790006cbbd"],"state_sha256":"05028052f4317e1b07503f8ddab49a7fea7ccec4a5c513d591b408f9ce9f7951"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBpFjcP1n4mfTbd1+a9I1guD6NeVnbEdrxtkpeE8okRCuV5QkPU+G9ksEC7vbJRqjmuCACMyZwNZFrkPXPB6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T03:54:04.487450Z","bundle_sha256":"a31af8871b8d17d2d49b356373bcdef7817ffa907bf21af6f3aab7d212149fd4"}}