{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XGIURO52HAOSEVO7ZSRO7AFKVH","short_pith_number":"pith:XGIURO52","canonical_record":{"source":{"id":"2605.13717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:02:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4ce383fb2f50f96a37eaf1a8737831c6b6fdefa78bb96794104ecb1aa8822a16","abstract_canon_sha256":"32f060087b56c361c4c30ebf6b47bce1e30f7242602fc313af11def460648777"},"schema_version":"1.0"},"canonical_sha256":"b99148bbba381d2255dfcca2ef80aaa9dcfff2706ba2e078b19abee30bf1db86","source":{"kind":"arxiv","id":"2605.13717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13717","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13717v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13717","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"XGIURO52HAOS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XGIURO52HAOSEVO7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XGIURO52","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XGIURO52HAOSEVO7ZSRO7AFKVH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:02:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4ce383fb2f50f96a37eaf1a8737831c6b6fdefa78bb96794104ecb1aa8822a16","abstract_canon_sha256":"32f060087b56c361c4c30ebf6b47bce1e30f7242602fc313af11def460648777"},"schema_version":"1.0"},"canonical_sha256":"b99148bbba381d2255dfcca2ef80aaa9dcfff2706ba2e078b19abee30bf1db86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.692442Z","signature_b64":"bU6BRRwRdKDhYyDE0eCpxkLGoOXCxQwJsF3NdInC537v82l9UhNlH+tSx6t26ZJAVXc9iKTs45YqSY7GhdNICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b99148bbba381d2255dfcca2ef80aaa9dcfff2706ba2e078b19abee30bf1db86","last_reissued_at":"2026-05-18T02:44:16.691728Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.691728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13717","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":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OmBMdp0M6uz0xyJf1XToKuqt+Um1K3j7k0eNNY0qIW6kRNPcm5S6tqWLHYXAMnHbupRf5Z+RIkPEclBhdqmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:31:33.602996Z"},"content_sha256":"5b9252e163f2da70358cd1f0f70179831770f781c567a751b661d94b92d65675","schema_version":"1.0","event_id":"sha256:5b9252e163f2da70358cd1f0f70179831770f781c567a751b661d94b92d65675"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XGIURO52HAOSEVO7ZSRO7AFKVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tight Sample Complexity Bounds for Entropic Best Policy Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A new stopping rule closes the exponential gap and matches the lower bound for entropic best-policy identification.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amer Essakine, Claire Vernade","submitted_at":"2026-05-13T16:02:26Z","abstract_excerpt":"We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the number of samples required to identify an approximately optimal policy. Precisely, known lower bounds scale in $\\Omega(e^{|\\beta| H})$ where $H$ is the horizon of the MDP, while the state-of-the-art upper bound achieves at best $O(e^{2|\\beta| H})$ (arXiv:2506.00286v2) using a generative model. We show that this extra exponential factor can be traced to over"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that this extra exponential factor can be traced to overly loose concentration control for exponential utilities. [...] we propose a new stopping rule that exploits further this tightness to obtain a sample complexity that matches the lower bound.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The smoothness properties of the exponential utility suffice to derive sharper concentration bounds that are tight enough for the new stopping rule to match the lower bound.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"New concentration bounds and stopping rule close the exponential gap to match the lower bound for entropic best policy identification.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new stopping rule closes the exponential gap and matches the lower bound for entropic best-policy identification.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0bfc4575045b0452dd66ae86453e41ec9d39252ef27d5bfb4ee3cd6de482f088"},"source":{"id":"2605.13717","kind":"arxiv","version":1},"verdict":{"id":"a4de2269-15d5-48aa-8269-9fd9bfbd11c6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:10:14.826127Z","strongest_claim":"We show that this extra exponential factor can be traced to overly loose concentration control for exponential utilities. [...] we propose a new stopping rule that exploits further this tightness to obtain a sample complexity that matches the lower bound.","one_line_summary":"New concentration bounds and stopping rule close the exponential gap to match the lower bound for entropic best policy identification.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The smoothness properties of the exponential utility suffice to derive sharper concentration bounds that are tight enough for the new stopping rule to match the lower bound.","pith_extraction_headline":"A new stopping rule closes the exponential gap and matches the lower bound for entropic best-policy identification."},"references":{"count":29,"sample":[{"doi":"","year":2012,"title":"Proceedings of the 29th International Conference on Machine Learning (ICML-12) , series =","work_id":"ad6ca1b2-68e6-4d58-8124-75e24003aaf4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2506.00286 , year =","work_id":"715e52da-416c-402d-88cb-a7b195df8fb1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Computational Economics , year =","work_id":"17929e36-771c-437e-8198-b02330fa0da0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Journal of Intelligent","work_id":"faabab27-c1a4-4527-8344-6d74ecc10ac6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Beyond Average Return in Markov Decision Processes , url =","work_id":"e397c916-0e06-471f-9cc8-d929de9e5bc8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"4519f968eb6213ab2b774adb2f22f307167ea555ca1ca88b748fdf3773e9c3c5","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":"a4de2269-15d5-48aa-8269-9fd9bfbd11c6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"leeuR5bM0mojYvjHffZdZwFm2xKBaidGAwR4E0pHlwSaw0nfTHFxH8BhIGg+sA4ZnTHCwgxO3weYqwpGg/M/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:31:33.604145Z"},"content_sha256":"6e85bc8c08c982fa0cd921c349a325ddd9fbf1c491819eda23d0350f3e084cbb","schema_version":"1.0","event_id":"sha256:6e85bc8c08c982fa0cd921c349a325ddd9fbf1c491819eda23d0350f3e084cbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGIURO52HAOSEVO7ZSRO7AFKVH/bundle.json","state_url":"https://pith.science/pith/XGIURO52HAOSEVO7ZSRO7AFKVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGIURO52HAOSEVO7ZSRO7AFKVH/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":"2026-05-31T22:31:33Z","links":{"resolver":"https://pith.science/pith/XGIURO52HAOSEVO7ZSRO7AFKVH","bundle":"https://pith.science/pith/XGIURO52HAOSEVO7ZSRO7AFKVH/bundle.json","state":"https://pith.science/pith/XGIURO52HAOSEVO7ZSRO7AFKVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGIURO52HAOSEVO7ZSRO7AFKVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XGIURO52HAOSEVO7ZSRO7AFKVH","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":"32f060087b56c361c4c30ebf6b47bce1e30f7242602fc313af11def460648777","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:02:26Z","title_canon_sha256":"4ce383fb2f50f96a37eaf1a8737831c6b6fdefa78bb96794104ecb1aa8822a16"},"schema_version":"1.0","source":{"id":"2605.13717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13717","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13717v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13717","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"XGIURO52HAOS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XGIURO52HAOSEVO7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XGIURO52","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6e85bc8c08c982fa0cd921c349a325ddd9fbf1c491819eda23d0350f3e084cbb","target":"graph","created_at":"2026-05-18T02:44:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We show that this extra exponential factor can be traced to overly loose concentration control for exponential utilities. [...] we propose a new stopping rule that exploits further this tightness to obtain a sample complexity that matches the lower bound."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The smoothness properties of the exponential utility suffice to derive sharper concentration bounds that are tight enough for the new stopping rule to match the lower bound."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"New concentration bounds and stopping rule close the exponential gap to match the lower bound for entropic best policy identification."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new stopping rule closes the exponential gap and matches the lower bound for entropic best-policy identification."}],"snapshot_sha256":"0bfc4575045b0452dd66ae86453e41ec9d39252ef27d5bfb4ee3cd6de482f088"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the number of samples required to identify an approximately optimal policy. Precisely, known lower bounds scale in $\\Omega(e^{|\\beta| H})$ where $H$ is the horizon of the MDP, while the state-of-the-art upper bound achieves at best $O(e^{2|\\beta| H})$ (arXiv:2506.00286v2) using a generative model. We show that this extra exponential factor can be traced to over","authors_text":"Amer Essakine, Claire Vernade","cross_cats":["stat.ML"],"headline":"A new stopping rule closes the exponential gap and matches the lower bound for entropic best-policy identification.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:02:26Z","title":"Tight Sample Complexity Bounds for Entropic Best Policy Identification"},"references":{"count":29,"internal_anchors":0,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Proceedings of the 29th International Conference on Machine Learning (ICML-12) , series =","work_id":"ad6ca1b2-68e6-4d58-8124-75e24003aaf4","year":2012},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2506.00286 , year =","work_id":"715e52da-416c-402d-88cb-a7b195df8fb1","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Computational Economics , year =","work_id":"17929e36-771c-437e-8198-b02330fa0da0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Journal of Intelligent","work_id":"faabab27-c1a4-4527-8344-6d74ecc10ac6","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Beyond Average Return in Markov Decision Processes , url =","work_id":"e397c916-0e06-471f-9cc8-d929de9e5bc8","year":null}],"snapshot_sha256":"4519f968eb6213ab2b774adb2f22f307167ea555ca1ca88b748fdf3773e9c3c5"},"source":{"id":"2605.13717","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:10:14.826127Z","id":"a4de2269-15d5-48aa-8269-9fd9bfbd11c6","model_set":{"reader":"grok-4.3"},"one_line_summary":"New concentration bounds and stopping rule close the exponential gap to match the lower bound for entropic best policy identification.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new stopping rule closes the exponential gap and matches the lower bound for entropic best-policy identification.","strongest_claim":"We show that this extra exponential factor can be traced to overly loose concentration control for exponential utilities. [...] we propose a new stopping rule that exploits further this tightness to obtain a sample complexity that matches the lower bound.","weakest_assumption":"The smoothness properties of the exponential utility suffice to derive sharper concentration bounds that are tight enough for the new stopping rule to match the lower bound."}},"verdict_id":"a4de2269-15d5-48aa-8269-9fd9bfbd11c6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b9252e163f2da70358cd1f0f70179831770f781c567a751b661d94b92d65675","target":"record","created_at":"2026-05-18T02:44:16Z","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":"32f060087b56c361c4c30ebf6b47bce1e30f7242602fc313af11def460648777","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:02:26Z","title_canon_sha256":"4ce383fb2f50f96a37eaf1a8737831c6b6fdefa78bb96794104ecb1aa8822a16"},"schema_version":"1.0","source":{"id":"2605.13717","kind":"arxiv","version":1}},"canonical_sha256":"b99148bbba381d2255dfcca2ef80aaa9dcfff2706ba2e078b19abee30bf1db86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b99148bbba381d2255dfcca2ef80aaa9dcfff2706ba2e078b19abee30bf1db86","first_computed_at":"2026-05-18T02:44:16.691728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.691728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bU6BRRwRdKDhYyDE0eCpxkLGoOXCxQwJsF3NdInC537v82l9UhNlH+tSx6t26ZJAVXc9iKTs45YqSY7GhdNICQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.692442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b9252e163f2da70358cd1f0f70179831770f781c567a751b661d94b92d65675","sha256:6e85bc8c08c982fa0cd921c349a325ddd9fbf1c491819eda23d0350f3e084cbb"],"state_sha256":"d12a3010c846cdc2869c24b0b3e907f64f95ab1890b6454011fcacad81e43383"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mk1Et5Vn1Bfm/IHJ3uBstxvaPDKNOE7dy5mOKHcFgTaB98qXBSLsJ8X5zjwIiIaVh7wHW+s3WpUxBFrQfFyNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:31:33.609406Z","bundle_sha256":"66297f5f10b0aeaeacef9fa948a30b26b645af3b04cec33d7bef4ec88cf3b1ab"}}