{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6FDNBFHQQ2B4CC6EJXRVJ37MJP","short_pith_number":"pith:6FDNBFHQ","canonical_record":{"source":{"id":"2305.11300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T20:48:50Z","cross_cats_sorted":[],"title_canon_sha256":"93d40817f7ff564be0cba5801b57816bb019fdfd6ad021f6f67519d5cfc2c889","abstract_canon_sha256":"c400af3b7848d2785d0d1c08b88a525f71b9ecac8a1cde763ea5c7c8d9e63f68"},"schema_version":"1.0"},"canonical_sha256":"f146d094f08683c10bc44de354efec4bc80dc4eeef7c686bfa5c09716b8865a8","source":{"kind":"arxiv","id":"2305.11300","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11300","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11300v1","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11300","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"6FDNBFHQQ2B4","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"6FDNBFHQQ2B4CC6E","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"6FDNBFHQ","created_at":"2026-07-05T06:11:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6FDNBFHQQ2B4CC6EJXRVJ37MJP","target":"record","payload":{"canonical_record":{"source":{"id":"2305.11300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T20:48:50Z","cross_cats_sorted":[],"title_canon_sha256":"93d40817f7ff564be0cba5801b57816bb019fdfd6ad021f6f67519d5cfc2c889","abstract_canon_sha256":"c400af3b7848d2785d0d1c08b88a525f71b9ecac8a1cde763ea5c7c8d9e63f68"},"schema_version":"1.0"},"canonical_sha256":"f146d094f08683c10bc44de354efec4bc80dc4eeef7c686bfa5c09716b8865a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:35.442175Z","signature_b64":"kHqlu/8H16Cerrp0BH1hYBdeTzjMFIwVC0owz1dXOPbT+D1kkBflttefy8Qvkla9LXvtCdNln++wQV+y2F9LDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f146d094f08683c10bc44de354efec4bc80dc4eeef7c686bfa5c09716b8865a8","last_reissued_at":"2026-07-05T06:11:35.441851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:35.441851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.11300","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":"2026-07-05T06:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2mfd+c9GZtEDfu2Ux2DcV12xScqSZFVECNidC2o02dTj/Tyv8F0+DNz9PAVruTNfGM8FuvSleuFO03tlW7tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:50:22.251070Z"},"content_sha256":"7e4f7c94a21c3afa6b63b9a7db75a9dbfe64c0939f984e6025e11a1c347d46bc","schema_version":"1.0","event_id":"sha256:7e4f7c94a21c3afa6b63b9a7db75a9dbfe64c0939f984e6025e11a1c347d46bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6FDNBFHQQ2B4CC6EJXRVJ37MJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Risk-Averse Q-Learning with Streaming Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enlu Zhou, Yuhao Wang","submitted_at":"2023-05-18T20:48:50Z","abstract_excerpt":"We consider a robust reinforcement learning problem, where a learning agent learns from a simulated training environment. To account for the model mis-specification between this training environment and the real environment due to lack of data, we adopt a formulation of Bayesian risk MDP (BRMDP) with infinite horizon, which uses Bayesian posterior to estimate the transition model and impose a risk functional to account for the model uncertainty. Observations from the real environment that is out of the agent's control arrive periodically and are utilized by the agent to update the Bayesian pos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11300","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/2305.11300/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":"2026-07-05T06:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dWCiChNxCsH0yH9aAGbKEHNAtxn6UvyZUhODH8Ghi04Ok279tZD2TAePTsA5jtzFtgQJXQ0oKL/W9VrgGnG3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:50:22.252068Z"},"content_sha256":"e1a20c70734d2440b412eefe2c918397b6daca43602ab764619d8ac93bb47dc6","schema_version":"1.0","event_id":"sha256:e1a20c70734d2440b412eefe2c918397b6daca43602ab764619d8ac93bb47dc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP/bundle.json","state_url":"https://pith.science/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP/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":"2026-08-17T13:50:22Z","links":{"resolver":"https://pith.science/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP","bundle":"https://pith.science/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP/bundle.json","state":"https://pith.science/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FDNBFHQQ2B4CC6EJXRVJ37MJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6FDNBFHQQ2B4CC6EJXRVJ37MJP","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":"c400af3b7848d2785d0d1c08b88a525f71b9ecac8a1cde763ea5c7c8d9e63f68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T20:48:50Z","title_canon_sha256":"93d40817f7ff564be0cba5801b57816bb019fdfd6ad021f6f67519d5cfc2c889"},"schema_version":"1.0","source":{"id":"2305.11300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11300","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11300v1","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11300","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"6FDNBFHQQ2B4","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"6FDNBFHQQ2B4CC6E","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"6FDNBFHQ","created_at":"2026-07-05T06:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:e1a20c70734d2440b412eefe2c918397b6daca43602ab764619d8ac93bb47dc6","target":"graph","created_at":"2026-07-05T06:11:35Z","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/2305.11300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a robust reinforcement learning problem, where a learning agent learns from a simulated training environment. To account for the model mis-specification between this training environment and the real environment due to lack of data, we adopt a formulation of Bayesian risk MDP (BRMDP) with infinite horizon, which uses Bayesian posterior to estimate the transition model and impose a risk functional to account for the model uncertainty. Observations from the real environment that is out of the agent's control arrive periodically and are utilized by the agent to update the Bayesian pos","authors_text":"Enlu Zhou, Yuhao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T20:48:50Z","title":"Bayesian Risk-Averse Q-Learning with Streaming Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11300","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":"sha256:7e4f7c94a21c3afa6b63b9a7db75a9dbfe64c0939f984e6025e11a1c347d46bc","target":"record","created_at":"2026-07-05T06:11:35Z","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":"c400af3b7848d2785d0d1c08b88a525f71b9ecac8a1cde763ea5c7c8d9e63f68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T20:48:50Z","title_canon_sha256":"93d40817f7ff564be0cba5801b57816bb019fdfd6ad021f6f67519d5cfc2c889"},"schema_version":"1.0","source":{"id":"2305.11300","kind":"arxiv","version":1}},"canonical_sha256":"f146d094f08683c10bc44de354efec4bc80dc4eeef7c686bfa5c09716b8865a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f146d094f08683c10bc44de354efec4bc80dc4eeef7c686bfa5c09716b8865a8","first_computed_at":"2026-07-05T06:11:35.441851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:35.441851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kHqlu/8H16Cerrp0BH1hYBdeTzjMFIwVC0owz1dXOPbT+D1kkBflttefy8Qvkla9LXvtCdNln++wQV+y2F9LDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:35.442175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e4f7c94a21c3afa6b63b9a7db75a9dbfe64c0939f984e6025e11a1c347d46bc","sha256:e1a20c70734d2440b412eefe2c918397b6daca43602ab764619d8ac93bb47dc6"],"state_sha256":"0045cdf8b3de519b68aa1346d88a2a80d7a4f9f652166cfecba0cf15b00f2369"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lISIxgd2gG71IKVfcDkkbDj6KZ2K+CnoaGQwn1sxrAqvmTdq6RnrOr0Eu7as9BaaZO17xmzzrAZpL+tRfi8dAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:50:22.260079Z","bundle_sha256":"404972e1378ebb754bbcebfb8a27e2690f96bc19bb34b3d65b1fd3726d832053"}}