{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PD4GVCRYZZUOPYWNMVHNVQDBKE","short_pith_number":"pith:PD4GVCRY","canonical_record":{"source":{"id":"2207.05852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T21:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"32c93ad0eb73f7874a267a6fc4383c3a7551f5d2c7392ae472327c241fb5b36a","abstract_canon_sha256":"a6153df1051b7aa04a54b8c8c7ac1004916a082aac33527eef0a4be4bc20bee4"},"schema_version":"1.0"},"canonical_sha256":"78f86a8a38ce68e7e2cd654edac061510dee1de1f3cac30f14a7bf6a914c187a","source":{"kind":"arxiv","id":"2207.05852","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05852","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05852v1","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05852","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"pith_short_12","alias_value":"PD4GVCRYZZUO","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"pith_short_16","alias_value":"PD4GVCRYZZUOPYWN","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"pith_short_8","alias_value":"PD4GVCRY","created_at":"2026-07-05T04:39:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PD4GVCRYZZUOPYWNMVHNVQDBKE","target":"record","payload":{"canonical_record":{"source":{"id":"2207.05852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T21:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"32c93ad0eb73f7874a267a6fc4383c3a7551f5d2c7392ae472327c241fb5b36a","abstract_canon_sha256":"a6153df1051b7aa04a54b8c8c7ac1004916a082aac33527eef0a4be4bc20bee4"},"schema_version":"1.0"},"canonical_sha256":"78f86a8a38ce68e7e2cd654edac061510dee1de1f3cac30f14a7bf6a914c187a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:52.266934Z","signature_b64":"DY1bUFlu/y3bPkr1AzsJGpWD/fFp1APld6vwLifK3ZFbipdZm6R7j/DXXmjmjk5mPWfLjwtuByl1wsyvZBjxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f86a8a38ce68e7e2cd654edac061510dee1de1f3cac30f14a7bf6a914c187a","last_reissued_at":"2026-07-05T04:39:52.266561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:52.266561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.05852","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":"2026-07-05T04:39:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTGoXVypNWCXTtxNK3Xh1KFjlG630ZT+9uw9kayJnS9dt9nB2l+Ww/QwgcNFNbgA1vN4vsD3RUYhTnnL1Fh9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:22:21.691388Z"},"content_sha256":"cc28d834564e13c910ef9bfb372df14737c7fade28c3b81c1a7970e5fa04cdcd","schema_version":"1.0","event_id":"sha256:cc28d834564e13c910ef9bfb372df14737c7fade28c3b81c1a7970e5fa04cdcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PD4GVCRYZZUOPYWNMVHNVQDBKE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Tirinzoni, Aymen Al-Marjani, Emilie Kaufmann","submitted_at":"2022-07-12T21:35:03Z","abstract_excerpt":"Optimistic algorithms have been extensively studied for regret minimization in episodic tabular MDPs, both from a minimax and an instance-dependent view. However, for the PAC RL problem, where the goal is to identify a near-optimal policy with high probability, little is known about their instance-dependent sample complexity. A negative result of Wagenmaker et al. (2021) suggests that optimistic sampling rules cannot be used to attain the (still elusive) optimal instance-dependent sample complexity. On the positive side, we provide the first instance-dependent bound for an optimistic algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05852","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/2207.05852/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":"2026-07-05T04:39:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eibTcKT3aV3tmzlZWFSdT47MZ7J6/93kQPjy2gKAPsKVQ+Sd6dDNnHSPA7rVf+KqgDOyDzBKHKtGW/i6eoOXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:22:21.691887Z"},"content_sha256":"d905702938bb414512890e03ccdd755549f619f7f4d0a4e239ad4ebf6d99ebc4","schema_version":"1.0","event_id":"sha256:d905702938bb414512890e03ccdd755549f619f7f4d0a4e239ad4ebf6d99ebc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE/bundle.json","state_url":"https://pith.science/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE/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":"2026-08-24T04:22:21Z","links":{"resolver":"https://pith.science/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE","bundle":"https://pith.science/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE/bundle.json","state":"https://pith.science/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PD4GVCRYZZUOPYWNMVHNVQDBKE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PD4GVCRYZZUOPYWNMVHNVQDBKE","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":"a6153df1051b7aa04a54b8c8c7ac1004916a082aac33527eef0a4be4bc20bee4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T21:35:03Z","title_canon_sha256":"32c93ad0eb73f7874a267a6fc4383c3a7551f5d2c7392ae472327c241fb5b36a"},"schema_version":"1.0","source":{"id":"2207.05852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05852","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05852v1","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05852","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"pith_short_12","alias_value":"PD4GVCRYZZUO","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"pith_short_16","alias_value":"PD4GVCRYZZUOPYWN","created_at":"2026-07-05T04:39:52Z"},{"alias_kind":"pith_short_8","alias_value":"PD4GVCRY","created_at":"2026-07-05T04:39:52Z"}],"graph_snapshots":[{"event_id":"sha256:d905702938bb414512890e03ccdd755549f619f7f4d0a4e239ad4ebf6d99ebc4","target":"graph","created_at":"2026-07-05T04:39:52Z","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/2207.05852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimistic algorithms have been extensively studied for regret minimization in episodic tabular MDPs, both from a minimax and an instance-dependent view. However, for the PAC RL problem, where the goal is to identify a near-optimal policy with high probability, little is known about their instance-dependent sample complexity. A negative result of Wagenmaker et al. (2021) suggests that optimistic sampling rules cannot be used to attain the (still elusive) optimal instance-dependent sample complexity. On the positive side, we provide the first instance-dependent bound for an optimistic algorithm","authors_text":"Andrea Tirinzoni, Aymen Al-Marjani, Emilie Kaufmann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T21:35:03Z","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05852","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:cc28d834564e13c910ef9bfb372df14737c7fade28c3b81c1a7970e5fa04cdcd","target":"record","created_at":"2026-07-05T04:39:52Z","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":"a6153df1051b7aa04a54b8c8c7ac1004916a082aac33527eef0a4be4bc20bee4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T21:35:03Z","title_canon_sha256":"32c93ad0eb73f7874a267a6fc4383c3a7551f5d2c7392ae472327c241fb5b36a"},"schema_version":"1.0","source":{"id":"2207.05852","kind":"arxiv","version":1}},"canonical_sha256":"78f86a8a38ce68e7e2cd654edac061510dee1de1f3cac30f14a7bf6a914c187a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78f86a8a38ce68e7e2cd654edac061510dee1de1f3cac30f14a7bf6a914c187a","first_computed_at":"2026-07-05T04:39:52.266561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:52.266561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DY1bUFlu/y3bPkr1AzsJGpWD/fFp1APld6vwLifK3ZFbipdZm6R7j/DXXmjmjk5mPWfLjwtuByl1wsyvZBjxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:52.266934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.05852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc28d834564e13c910ef9bfb372df14737c7fade28c3b81c1a7970e5fa04cdcd","sha256:d905702938bb414512890e03ccdd755549f619f7f4d0a4e239ad4ebf6d99ebc4"],"state_sha256":"5c9d02cb1f08f5fed1e2480f058a8236d1060d0c9607da09e5d079d92c92261a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N00y9DlRaoTeR7elewpbAxMZ2zDZwyHkArdDkqOmkSzEkqyMemFeZYfbhuD0nfJ2gw4IWDBZ/2QaaOSf4qYyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T04:22:21.695620Z","bundle_sha256":"7e7a45517f8773dd30d073fd148b759a57fe4e47073f51c21b380ec6a11bb93f"}}