{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EOSXBVP4CHZSJMSUIRDHY2ATTH","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":"9fbe0d4411f67bec90cccd339e1e9780cbbdc69a908e343a08a48f79d63c3dcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:37:09Z","title_canon_sha256":"1ed0081898b37caaa5eefac6ec40529daa9d8a334b900df79e06da718ce2ad7d"},"schema_version":"1.0","source":{"id":"2309.08571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08571","created_at":"2026-07-05T08:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08571v2","created_at":"2026-07-05T08:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08571","created_at":"2026-07-05T08:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"EOSXBVP4CHZS","created_at":"2026-07-05T08:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"EOSXBVP4CHZSJMSU","created_at":"2026-07-05T08:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"EOSXBVP4","created_at":"2026-07-05T08:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:0e21a386f7fed3531ec7fe60392fe4cdab5ebfe3bc570cbed7e682e60e580257","target":"graph","created_at":"2026-07-05T08:05:02Z","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/2309.08571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a Bayesian approach to offline model-based inverse reinforcement learning (IRL). The proposed framework differs from existing offline model-based IRL approaches by performing simultaneous estimation of the expert's reward function and subjective model of environment dynamics. We make use of a class of prior distributions which parameterizes how accurate the expert's model of the environment is to develop efficient algorithms to estimate the expert's reward and subjective dynamics in high-dimensional settings. Our analysis reveals a novel insight that the estimated policy exhibits r","authors_text":"Alfredo Garcia, Anthony McDonald, Chenliang Li, Mingyi Hong, Ran Wei, Siliang Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:37:09Z","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08571","kind":"arxiv","version":2},"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:db3e9c52766f3ea25e27bf743ec5f9486cb965d3467152ccb4122b4d4fe46b5f","target":"record","created_at":"2026-07-05T08:05:02Z","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":"9fbe0d4411f67bec90cccd339e1e9780cbbdc69a908e343a08a48f79d63c3dcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:37:09Z","title_canon_sha256":"1ed0081898b37caaa5eefac6ec40529daa9d8a334b900df79e06da718ce2ad7d"},"schema_version":"1.0","source":{"id":"2309.08571","kind":"arxiv","version":2}},"canonical_sha256":"23a570d5fc11f324b25444467c681399d1d01b20c32c8ad01c19f84728a37ef6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23a570d5fc11f324b25444467c681399d1d01b20c32c8ad01c19f84728a37ef6","first_computed_at":"2026-07-05T08:05:02.294215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:02.294215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kaFeEBYIpDM2p3GKBBu5zJEpu9KLI/eFpTkUjqTlB4nJTo/NfMDVfiuYqmN2XEKa4n4khcJH0eJ5A3RFMGcRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:02.294800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db3e9c52766f3ea25e27bf743ec5f9486cb965d3467152ccb4122b4d4fe46b5f","sha256:0e21a386f7fed3531ec7fe60392fe4cdab5ebfe3bc570cbed7e682e60e580257"],"state_sha256":"7a7a3d419b51620917758017c59f0d0d4e048ca3895337139040aedb5ec623a7"}