{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PXZLOZVSQGZM4KHM3XWPXRTG5R","short_pith_number":"pith:PXZLOZVS","canonical_record":{"source":{"id":"2605.23182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:04:45Z","cross_cats_sorted":[],"title_canon_sha256":"a99c58a260be4eb1db5dea25919aff6df1450cbcc3cec227a770e2a0a75eb774","abstract_canon_sha256":"c6dd7b419aef3573e6d690aefb2525df063a9dfd311ade1813b62fbdf6d40545"},"schema_version":"1.0"},"canonical_sha256":"7df2b766b281b2ce28ecddecfbc666ec54dafaa6575c6184539788c1fa5840f0","source":{"kind":"arxiv","id":"2605.23182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23182","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23182v1","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23182","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_12","alias_value":"PXZLOZVSQGZM","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_16","alias_value":"PXZLOZVSQGZM4KHM","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_8","alias_value":"PXZLOZVS","created_at":"2026-05-25T02:01:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PXZLOZVSQGZM4KHM3XWPXRTG5R","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:04:45Z","cross_cats_sorted":[],"title_canon_sha256":"a99c58a260be4eb1db5dea25919aff6df1450cbcc3cec227a770e2a0a75eb774","abstract_canon_sha256":"c6dd7b419aef3573e6d690aefb2525df063a9dfd311ade1813b62fbdf6d40545"},"schema_version":"1.0"},"canonical_sha256":"7df2b766b281b2ce28ecddecfbc666ec54dafaa6575c6184539788c1fa5840f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:41.969859Z","signature_b64":"DyZgilll+9hOJOTTzNbT9YGNYdKJxPH2GyLfY1ADsKkRzripLhZ1nqe1qSFSRbcuZkBIOPapjh7dHL0I1J4GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7df2b766b281b2ce28ecddecfbc666ec54dafaa6575c6184539788c1fa5840f0","last_reissued_at":"2026-05-25T02:01:41.969262Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:41.969262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23182","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":"2026-05-25T02:01:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFfzh3o2dF6pJzsG7l7yXwOadohCXcPGQTOtlXGKw1TKvtJU2KlBzF3vEvi0u+b/s673L59arEEpVucR4VzJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:05:30.549498Z"},"content_sha256":"31829c8dcc5221b3f34b68ec56e3b9d333acd0f0aca8f265b72270737a864000","schema_version":"1.0","event_id":"sha256:31829c8dcc5221b3f34b68ec56e3b9d333acd0f0aca8f265b72270737a864000"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PXZLOZVSQGZM4KHM3XWPXRTG5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wang Chi Cheung, Zitian Li","submitted_at":"2026-05-22T03:04:45Z","abstract_excerpt":"Pure exploration in episodic Reinforcement Learning has primarily focused on Best Policy Identification (BPI), which seeks to identify a (near)-optimal policy with high confidence. Motivated by practical settings where a ``good enough'' policy suffices, we study an alternate objective of Good Policy Identification (GPI). For a given reward threshold $\\mu_0$, GPI only requires identifying a policy with expected reward in an episode at least $\\mu_0$ if such a policy exists (positive instance), or declaring None if no such policy exists (negative instance). We formalize GPI under the fixed-confid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23182","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/2605.23182/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":"2026-05-25T02:01:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tbgE0exzPnq98iiNhAc557nq4vvblD5daJriyo9wF25IMoxAl2DTQzalR9pR9pZIY6lDQyX6DQ1Ok3BANbgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:05:30.549873Z"},"content_sha256":"e75c682f5127dc7ce6766999741f5da58f56b784d7f16275dcfe6818f6672ae9","schema_version":"1.0","event_id":"sha256:e75c682f5127dc7ce6766999741f5da58f56b784d7f16275dcfe6818f6672ae9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R/bundle.json","state_url":"https://pith.science/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R/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":"2026-05-28T04:05:30Z","links":{"resolver":"https://pith.science/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R","bundle":"https://pith.science/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R/bundle.json","state":"https://pith.science/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXZLOZVSQGZM4KHM3XWPXRTG5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PXZLOZVSQGZM4KHM3XWPXRTG5R","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":"c6dd7b419aef3573e6d690aefb2525df063a9dfd311ade1813b62fbdf6d40545","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:04:45Z","title_canon_sha256":"a99c58a260be4eb1db5dea25919aff6df1450cbcc3cec227a770e2a0a75eb774"},"schema_version":"1.0","source":{"id":"2605.23182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23182","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23182v1","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23182","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_12","alias_value":"PXZLOZVSQGZM","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_16","alias_value":"PXZLOZVSQGZM4KHM","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_8","alias_value":"PXZLOZVS","created_at":"2026-05-25T02:01:41Z"}],"graph_snapshots":[{"event_id":"sha256:e75c682f5127dc7ce6766999741f5da58f56b784d7f16275dcfe6818f6672ae9","target":"graph","created_at":"2026-05-25T02:01:41Z","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/2605.23182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pure exploration in episodic Reinforcement Learning has primarily focused on Best Policy Identification (BPI), which seeks to identify a (near)-optimal policy with high confidence. Motivated by practical settings where a ``good enough'' policy suffices, we study an alternate objective of Good Policy Identification (GPI). For a given reward threshold $\\mu_0$, GPI only requires identifying a policy with expected reward in an episode at least $\\mu_0$ if such a policy exists (positive instance), or declaring None if no such policy exists (negative instance). We formalize GPI under the fixed-confid","authors_text":"Wang Chi Cheung, Zitian Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:04:45Z","title":"Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23182","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":"sha256:31829c8dcc5221b3f34b68ec56e3b9d333acd0f0aca8f265b72270737a864000","target":"record","created_at":"2026-05-25T02:01:41Z","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":"c6dd7b419aef3573e6d690aefb2525df063a9dfd311ade1813b62fbdf6d40545","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:04:45Z","title_canon_sha256":"a99c58a260be4eb1db5dea25919aff6df1450cbcc3cec227a770e2a0a75eb774"},"schema_version":"1.0","source":{"id":"2605.23182","kind":"arxiv","version":1}},"canonical_sha256":"7df2b766b281b2ce28ecddecfbc666ec54dafaa6575c6184539788c1fa5840f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7df2b766b281b2ce28ecddecfbc666ec54dafaa6575c6184539788c1fa5840f0","first_computed_at":"2026-05-25T02:01:41.969262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:41.969262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DyZgilll+9hOJOTTzNbT9YGNYdKJxPH2GyLfY1ADsKkRzripLhZ1nqe1qSFSRbcuZkBIOPapjh7dHL0I1J4GCg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:41.969859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31829c8dcc5221b3f34b68ec56e3b9d333acd0f0aca8f265b72270737a864000","sha256:e75c682f5127dc7ce6766999741f5da58f56b784d7f16275dcfe6818f6672ae9"],"state_sha256":"e4b5cab8e607f5d79f37a8337ac4f7c130250dbb45b1d19919c634b35ff59fd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HvIeSbgYdTMpJFsZNMJmT9iu0GkgUxG2gbHuTaZO0IlOUNinVRUKpwAp+zQfvSzngJw0F2BnabF5EmlPw2lECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:05:30.552049Z","bundle_sha256":"7b36282f1e79cae252a4e399c3895231f5e41ef6044e25ea8b0768a2419173f1"}}