{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S54YIR3E6HZGHCI2CZUOTIOOGL","short_pith_number":"pith:S54YIR3E","canonical_record":{"source":{"id":"2405.00950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T02:20:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8687ca78af2cf9256b9f2bd86932954284d17e684e7fa12a1bb722a714d60374","abstract_canon_sha256":"0ac1b5be7454ec2373530023c92b18c4a03bfaeade6145a75ec75ed4b3de80d3"},"schema_version":"1.0"},"canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","source":{"kind":"arxiv","id":"2405.00950","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00950","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00950v1","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00950","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"S54YIR3E6HZG","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"S54YIR3E6HZGHCI2","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"S54YIR3E","created_at":"2026-07-05T08:14:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S54YIR3E6HZGHCI2CZUOTIOOGL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.00950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T02:20:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8687ca78af2cf9256b9f2bd86932954284d17e684e7fa12a1bb722a714d60374","abstract_canon_sha256":"0ac1b5be7454ec2373530023c92b18c4a03bfaeade6145a75ec75ed4b3de80d3"},"schema_version":"1.0"},"canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:28.407400Z","signature_b64":"rFG/ncPzuFKq6meNOns8UbXKHwUXlZ6BhasklAZb1OcC4n28VH1jioRfd6U5xXrEpoLksNXulWpsCIe/gK+1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","last_reissued_at":"2026-07-05T08:14:28.406912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:28.406912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.00950","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":"2026-07-05T08:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yd1+D3Cpa0Z7JBu6V7QQ2ah8F8vAYZyIQWINxml9Wiz+5UvQ0BRuzLDjQ5IFXpY0RfEHQVLoETsVtPqxb+/sBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:20:01.027290Z"},"content_sha256":"20a709f0a6b3414cc80010cc4110b0358a4b2c111e4f83ab691748bdb5cdfeac","schema_version":"1.0","event_id":"sha256:20a709f0a6b3414cc80010cc4110b0358a4b2c111e4f83ab691748bdb5cdfeac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S54YIR3E6HZGHCI2CZUOTIOOGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Xiong, Jian Li","submitted_at":"2024-05-02T02:20:19Z","abstract_excerpt":"Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed with a state that evolves independently according to a Markov decision process regardless of being activated or not. In this paper, we consider the task of learning in episodic RMAB with unknown transition functions and adversarial rewards, which can change arbitrarily across episodes. Further, we consider a challenging but natural bandit feedback setting that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00950","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/2405.00950/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":"2026-07-05T08:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xqFKroHZ9XrLEj6qYAvjbgcUTcAwOpNDrHq1sP9is2qt7VI/H4LovZiq9m7gHQRjzdsdf6RnuFouoaO7KVUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:20:01.027836Z"},"content_sha256":"78944e54b953dabd8e81feca77d2a39cdc14d6cb6e738af3fa8f30ed2cd42615","schema_version":"1.0","event_id":"sha256:78944e54b953dabd8e81feca77d2a39cdc14d6cb6e738af3fa8f30ed2cd42615"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/bundle.json","state_url":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/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":"2026-08-21T22:20:01Z","links":{"resolver":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL","bundle":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/bundle.json","state":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S54YIR3E6HZGHCI2CZUOTIOOGL","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":"0ac1b5be7454ec2373530023c92b18c4a03bfaeade6145a75ec75ed4b3de80d3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T02:20:19Z","title_canon_sha256":"8687ca78af2cf9256b9f2bd86932954284d17e684e7fa12a1bb722a714d60374"},"schema_version":"1.0","source":{"id":"2405.00950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00950","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00950v1","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00950","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"S54YIR3E6HZG","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"S54YIR3E6HZGHCI2","created_at":"2026-07-05T08:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"S54YIR3E","created_at":"2026-07-05T08:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:78944e54b953dabd8e81feca77d2a39cdc14d6cb6e738af3fa8f30ed2cd42615","target":"graph","created_at":"2026-07-05T08:14:28Z","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/2405.00950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed with a state that evolves independently according to a Markov decision process regardless of being activated or not. In this paper, we consider the task of learning in episodic RMAB with unknown transition functions and adversarial rewards, which can change arbitrarily across episodes. Further, we consider a challenging but natural bandit feedback setting that","authors_text":"Guojun Xiong, Jian Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T02:20:19Z","title":"Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00950","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":"sha256:20a709f0a6b3414cc80010cc4110b0358a4b2c111e4f83ab691748bdb5cdfeac","target":"record","created_at":"2026-07-05T08:14:28Z","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":"0ac1b5be7454ec2373530023c92b18c4a03bfaeade6145a75ec75ed4b3de80d3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T02:20:19Z","title_canon_sha256":"8687ca78af2cf9256b9f2bd86932954284d17e684e7fa12a1bb722a714d60374"},"schema_version":"1.0","source":{"id":"2405.00950","kind":"arxiv","version":1}},"canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","first_computed_at":"2026-07-05T08:14:28.406912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:28.406912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rFG/ncPzuFKq6meNOns8UbXKHwUXlZ6BhasklAZb1OcC4n28VH1jioRfd6U5xXrEpoLksNXulWpsCIe/gK+1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:28.407400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20a709f0a6b3414cc80010cc4110b0358a4b2c111e4f83ab691748bdb5cdfeac","sha256:78944e54b953dabd8e81feca77d2a39cdc14d6cb6e738af3fa8f30ed2cd42615"],"state_sha256":"4ac67ba3bd7f00f6b67feba5421b88bd37adcd7d445a262e7a4e1e6249a0f09a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1ofn5HHqjovB9sPecwU24Ao8evhwc1vWkSWByRs0uXFgCCX2atvCU0BjcmRI/sQBr8IqjCopTBPmOfQD32uCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:20:01.032388Z","bundle_sha256":"1002271eac19282f41e6d50b023b95ca578936a03447c5f0ecaecb5e238ffcbf"}}