{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HISG3A6EOSB4T65B35GTFLCFON","short_pith_number":"pith:HISG3A6E","canonical_record":{"source":{"id":"2608.12973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-08-13T08:53:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e01c57154818441630fcd182f54033c8b82306d6ada69a5b93fa06cbc92e5d49","abstract_canon_sha256":"7dd021a17ffaab1f542afef9cc874f52c10ae5be728645a612a81ed3168f7952"},"schema_version":"1.0"},"canonical_sha256":"3a246d83c47483c9fba1df4d32ac457362aa5efa4f9085ef6f158cd9df21f147","source":{"kind":"arxiv","id":"2608.12973","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12973","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12973v1","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12973","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"HISG3A6EOSB4","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"HISG3A6EOSB4T65B","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"HISG3A6E","created_at":"2026-08-14T01:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HISG3A6EOSB4T65B35GTFLCFON","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-08-13T08:53:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e01c57154818441630fcd182f54033c8b82306d6ada69a5b93fa06cbc92e5d49","abstract_canon_sha256":"7dd021a17ffaab1f542afef9cc874f52c10ae5be728645a612a81ed3168f7952"},"schema_version":"1.0"},"canonical_sha256":"3a246d83c47483c9fba1df4d32ac457362aa5efa4f9085ef6f158cd9df21f147","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:01.797684Z","signature_b64":"WX4JYs09gyFvZvjHukun9DeD8Vgmsvt/iQRbF22BWNXaaOMwCx2/jhsPL+zz1xuP166SCofJdx+P6fSxFjRUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a246d83c47483c9fba1df4d32ac457362aa5efa4f9085ef6f158cd9df21f147","last_reissued_at":"2026-08-14T01:00:01.795263Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:01.795263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12973","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":"2026-08-14T01:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/40IUAkWdjzZmihPHlsWhhp5iqALTluYlO+p3oWGCOn2dXnMR2kzHXMi7ju0ZacxwaLZIMoo9R9idC7K3f3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:16:12.779729Z"},"content_sha256":"86a8cabddfb2871910c7864e0d54807411e2771cb50e210f0a6f5af19a679312","schema_version":"1.0","event_id":"sha256:86a8cabddfb2871910c7864e0d54807411e2771cb50e210f0a6f5af19a679312"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HISG3A6EOSB4T65B35GTFLCFON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Inference for Quantile Temporal Difference Learning in 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":"2026-08-13T08:53:02Z","abstract_excerpt":"In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning. Assuming access to a generative model, we first establish functional central limit theorems for both synchronous and asynchronous QTD, which show that the averaged iterates of QTD converge weakly to a rescaled Brownian motion. We next provide online inference methods. Based on random scaling, the inference procedure constructs an asymptotically pivotal statistic for inference by using the information along the whole QTD path. Meanwhile, the prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12973","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/2608.12973/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":"2026-08-14T01:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AS/gvSg9GiWxTeX4L/CbRpP6FoOw3X8HeAgjpi45q22BRXES/il97ClyD66vEPcWErmYcAQwYEyKjIKms3hFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:16:12.780253Z"},"content_sha256":"4b7b88702278227523a1871c31e8c7ec0197c3a3b5b750aac8d064daa8a951c3","schema_version":"1.0","event_id":"sha256:4b7b88702278227523a1871c31e8c7ec0197c3a3b5b750aac8d064daa8a951c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HISG3A6EOSB4T65B35GTFLCFON/bundle.json","state_url":"https://pith.science/pith/HISG3A6EOSB4T65B35GTFLCFON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HISG3A6EOSB4T65B35GTFLCFON/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":"2026-08-17T20:16:12Z","links":{"resolver":"https://pith.science/pith/HISG3A6EOSB4T65B35GTFLCFON","bundle":"https://pith.science/pith/HISG3A6EOSB4T65B35GTFLCFON/bundle.json","state":"https://pith.science/pith/HISG3A6EOSB4T65B35GTFLCFON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HISG3A6EOSB4T65B35GTFLCFON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HISG3A6EOSB4T65B35GTFLCFON","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":"7dd021a17ffaab1f542afef9cc874f52c10ae5be728645a612a81ed3168f7952","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-08-13T08:53:02Z","title_canon_sha256":"e01c57154818441630fcd182f54033c8b82306d6ada69a5b93fa06cbc92e5d49"},"schema_version":"1.0","source":{"id":"2608.12973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12973","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12973v1","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12973","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"HISG3A6EOSB4","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"HISG3A6EOSB4T65B","created_at":"2026-08-14T01:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"HISG3A6E","created_at":"2026-08-14T01:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:4b7b88702278227523a1871c31e8c7ec0197c3a3b5b750aac8d064daa8a951c3","target":"graph","created_at":"2026-08-14T01:00:01Z","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/2608.12973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning. Assuming access to a generative model, we first establish functional central limit theorems for both synchronous and asynchronous QTD, which show that the averaged iterates of QTD converge weakly to a rescaled Brownian motion. We next provide online inference methods. Based on random scaling, the inference procedure constructs an asymptotically pivotal statistic for inference by using the information along the whole QTD path. Meanwhile, the prop","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":"2026-08-13T08:53:02Z","title":"Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12973","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":"sha256:86a8cabddfb2871910c7864e0d54807411e2771cb50e210f0a6f5af19a679312","target":"record","created_at":"2026-08-14T01:00:01Z","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":"7dd021a17ffaab1f542afef9cc874f52c10ae5be728645a612a81ed3168f7952","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-08-13T08:53:02Z","title_canon_sha256":"e01c57154818441630fcd182f54033c8b82306d6ada69a5b93fa06cbc92e5d49"},"schema_version":"1.0","source":{"id":"2608.12973","kind":"arxiv","version":1}},"canonical_sha256":"3a246d83c47483c9fba1df4d32ac457362aa5efa4f9085ef6f158cd9df21f147","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a246d83c47483c9fba1df4d32ac457362aa5efa4f9085ef6f158cd9df21f147","first_computed_at":"2026-08-14T01:00:01.795263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:01.795263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WX4JYs09gyFvZvjHukun9DeD8Vgmsvt/iQRbF22BWNXaaOMwCx2/jhsPL+zz1xuP166SCofJdx+P6fSxFjRUDA==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:01.797684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86a8cabddfb2871910c7864e0d54807411e2771cb50e210f0a6f5af19a679312","sha256:4b7b88702278227523a1871c31e8c7ec0197c3a3b5b750aac8d064daa8a951c3"],"state_sha256":"6911d277222d9b2243f92acf9dce77eebc0e7e9546685a51303ce9cbba84ddc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCKseqJI1vUCYbM8+ze10m8cTFz3Y1Yp/rSanjuOnWAjAVVRp7S7nZhs86m7kc9+JMf2IklgFDbsNKprZOebDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:16:12.789773Z","bundle_sha256":"36ba4e4298cc2e062326913dac05e84469a072aac267255ce12e4d1067c5a793"}}