{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:55JUSQDWYQ5WWADXXZ3F2UV5KG","short_pith_number":"pith:55JUSQDW","canonical_record":{"source":{"id":"2607.08444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-09T13:06:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d051e237cdfc26b7535b320fa790c87fd6cae777ef9bcf29dab7193a1421cc2a","abstract_canon_sha256":"9602be99b26e3278559f9d142d0e25b957748a0b4134284dd2d551a1c5d3928f"},"schema_version":"1.0"},"canonical_sha256":"ef53494076c43b6b0077be765d52bd519940b7af734d146e9fb286510bc8a5df","source":{"kind":"arxiv","id":"2607.08444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08444","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08444v1","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08444","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"55JUSQDWYQ5W","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"55JUSQDWYQ5WWADX","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"55JUSQDW","created_at":"2026-07-10T01:19:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:55JUSQDWYQ5WWADXXZ3F2UV5KG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-09T13:06:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d051e237cdfc26b7535b320fa790c87fd6cae777ef9bcf29dab7193a1421cc2a","abstract_canon_sha256":"9602be99b26e3278559f9d142d0e25b957748a0b4134284dd2d551a1c5d3928f"},"schema_version":"1.0"},"canonical_sha256":"ef53494076c43b6b0077be765d52bd519940b7af734d146e9fb286510bc8a5df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:50.798029Z","signature_b64":"Aai8qacqMEs5K7zUbih/V/fBXf7neRrV9UBLrAMjRyqzd+KYK4uvOXV70yOMuyXJ0OTr9qD2MaQYVrum+3euCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef53494076c43b6b0077be765d52bd519940b7af734d146e9fb286510bc8a5df","last_reissued_at":"2026-07-10T01:19:50.797566Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:50.797566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08444","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":"2026-07-10T01:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WcK+rSeu8cE0lmJTgOJ56Fj242WyzRAjlU21mii3nu78lhWkfOJ02xeyJSvbTvsGNsvw+qnkFplTA5C423MFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:33:42.509395Z"},"content_sha256":"e2b922f8e54c30e63d5a0c79b04d735ea58c785431f7ab077691f4fa62f8138b","schema_version":"1.0","event_id":"sha256:e2b922f8e54c30e63d5a0c79b04d735ea58c785431f7ab077691f4fa62f8138b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:55JUSQDWYQ5WWADXXZ3F2UV5KG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Yang Peng, Zhihua Zhang, Zijie Cheng","submitted_at":"2026-07-09T13:06:07Z","abstract_excerpt":"In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency. We focus on distributional policy evaluation, whose goal is to characterize the return distribution, namely the distribution of discounted cumulative rewards under a given policy. To obtain a finite-dimensional representation of the return distribution, we consider the quantile fixed point $\\eta_m$ induced by the quantile-projected distributional Bellman equation. Assuming access to a generative model, we construct an estimator $\\eta_m^{(n)}$ based on an empirical Markov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08444","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/2607.08444/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":"2026-07-10T01:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pDjXMNmP6SeXX46JJAxulKWcAk2VbfM9IxLFDidrg6uqiEnmyFDHx62OicZsNGkh+3tc6+GcbCQBcBDBp2FqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:33:42.509902Z"},"content_sha256":"3d371c7d655d3bf1320b9aa1b071c6c79389d0f2cf401e7b80ad1ac6bab06b8b","schema_version":"1.0","event_id":"sha256:3d371c7d655d3bf1320b9aa1b071c6c79389d0f2cf401e7b80ad1ac6bab06b8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG/bundle.json","state_url":"https://pith.science/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG/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":"2026-08-07T00:33:42Z","links":{"resolver":"https://pith.science/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG","bundle":"https://pith.science/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG/bundle.json","state":"https://pith.science/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55JUSQDWYQ5WWADXXZ3F2UV5KG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:55JUSQDWYQ5WWADXXZ3F2UV5KG","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":"9602be99b26e3278559f9d142d0e25b957748a0b4134284dd2d551a1c5d3928f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-09T13:06:07Z","title_canon_sha256":"d051e237cdfc26b7535b320fa790c87fd6cae777ef9bcf29dab7193a1421cc2a"},"schema_version":"1.0","source":{"id":"2607.08444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08444","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08444v1","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08444","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"55JUSQDWYQ5W","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"55JUSQDWYQ5WWADX","created_at":"2026-07-10T01:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"55JUSQDW","created_at":"2026-07-10T01:19:50Z"}],"graph_snapshots":[{"event_id":"sha256:3d371c7d655d3bf1320b9aa1b071c6c79389d0f2cf401e7b80ad1ac6bab06b8b","target":"graph","created_at":"2026-07-10T01:19:50Z","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/2607.08444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency. We focus on distributional policy evaluation, whose goal is to characterize the return distribution, namely the distribution of discounted cumulative rewards under a given policy. To obtain a finite-dimensional representation of the return distribution, we consider the quantile fixed point $\\eta_m$ induced by the quantile-projected distributional Bellman equation. Assuming access to a generative model, we construct an estimator $\\eta_m^{(n)}$ based on an empirical Markov","authors_text":"Yang Peng, Zhihua Zhang, Zijie Cheng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-09T13:06:07Z","title":"Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08444","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:e2b922f8e54c30e63d5a0c79b04d735ea58c785431f7ab077691f4fa62f8138b","target":"record","created_at":"2026-07-10T01:19:50Z","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":"9602be99b26e3278559f9d142d0e25b957748a0b4134284dd2d551a1c5d3928f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-09T13:06:07Z","title_canon_sha256":"d051e237cdfc26b7535b320fa790c87fd6cae777ef9bcf29dab7193a1421cc2a"},"schema_version":"1.0","source":{"id":"2607.08444","kind":"arxiv","version":1}},"canonical_sha256":"ef53494076c43b6b0077be765d52bd519940b7af734d146e9fb286510bc8a5df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef53494076c43b6b0077be765d52bd519940b7af734d146e9fb286510bc8a5df","first_computed_at":"2026-07-10T01:19:50.797566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:50.797566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aai8qacqMEs5K7zUbih/V/fBXf7neRrV9UBLrAMjRyqzd+KYK4uvOXV70yOMuyXJ0OTr9qD2MaQYVrum+3euCg==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:50.798029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2b922f8e54c30e63d5a0c79b04d735ea58c785431f7ab077691f4fa62f8138b","sha256:3d371c7d655d3bf1320b9aa1b071c6c79389d0f2cf401e7b80ad1ac6bab06b8b"],"state_sha256":"08a560c943f9548bb9d8763646acbcede34fd82172eb9f54f102f3e7e08f7020"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHmZvTLSMysdq9kg/quDpDIGpiQNUy5LvqGQjk8HGwW/bCXqyeMWlAtjE3bdukPCs+qkIVumWjnXQqPJLAlmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:33:42.513851Z","bundle_sha256":"e060d423a36f17510caa30b432b69429d813cb0603abf499fea4e826a558a3e5"}}