{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4CTJZSOMKGKBXSHYDUZRWHFDR5","short_pith_number":"pith:4CTJZSOM","schema_version":"1.0","canonical_sha256":"e0a69cc9cc51941bc8f81d331b1ca38f6a7d8933f9ad338b62b7612e65edf78f","source":{"kind":"arxiv","id":"2303.06827","version":4},"attestation_state":"computed","paper":{"title":"Kernel Density Bayesian Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aishwarya Mandyam, Andrew Jones, Barbara E. Engelhardt, Diana Cai, Didong Li, Jiayu Yao","submitted_at":"2023-03-13T03:00:03Z","abstract_excerpt":"Inverse reinforcement learning (IRL) methods infer an agent's reward function using demonstrations of expert behavior. A Bayesian IRL approach models a distribution over candidate reward functions, capturing a degree of uncertainty in the inferred reward function. This is critical in some applications, such as those involving clinical data. Typically, Bayesian IRL algorithms require large demonstration datasets, which may not be available in practice. In this work, we incorporate existing domain-specific data to achieve better posterior concentration rates. We study a common setting in clinica"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.06827","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T03:00:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"829aae2cfeed86875f68a75b47a41160816718270d43faa8a8189f9707e5eb8b","abstract_canon_sha256":"bad8f511d35918da985ae67103ae3740acd6642f2a4d92f33c27eb133a580381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:00.218084Z","signature_b64":"BE8T37O0oTl8XUv9JMESAoWhiURSP2ox9FsCzSBnUnCV/2f6hW5Un7tgbxv45yg/OQfenMieN/3VZwz5Se8tDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a69cc9cc51941bc8f81d331b1ca38f6a7d8933f9ad338b62b7612e65edf78f","last_reissued_at":"2026-07-05T11:31:00.217614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:00.217614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel Density Bayesian Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aishwarya Mandyam, Andrew Jones, Barbara E. Engelhardt, Diana Cai, Didong Li, Jiayu Yao","submitted_at":"2023-03-13T03:00:03Z","abstract_excerpt":"Inverse reinforcement learning (IRL) methods infer an agent's reward function using demonstrations of expert behavior. A Bayesian IRL approach models a distribution over candidate reward functions, capturing a degree of uncertainty in the inferred reward function. This is critical in some applications, such as those involving clinical data. Typically, Bayesian IRL algorithms require large demonstration datasets, which may not be available in practice. In this work, we incorporate existing domain-specific data to achieve better posterior concentration rates. We study a common setting in clinica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06827","kind":"arxiv","version":4},"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/2303.06827/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.06827","created_at":"2026-07-05T11:31:00.217699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06827v4","created_at":"2026-07-05T11:31:00.217699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06827","created_at":"2026-07-05T11:31:00.217699+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CTJZSOMKGKB","created_at":"2026-07-05T11:31:00.217699+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CTJZSOMKGKBXSHY","created_at":"2026-07-05T11:31:00.217699+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CTJZSOM","created_at":"2026-07-05T11:31:00.217699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5","json":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5.json","graph_json":"https://pith.science/api/pith-number/4CTJZSOMKGKBXSHYDUZRWHFDR5/graph.json","events_json":"https://pith.science/api/pith-number/4CTJZSOMKGKBXSHYDUZRWHFDR5/events.json","paper":"https://pith.science/paper/4CTJZSOM"},"agent_actions":{"view_html":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5","download_json":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5.json","view_paper":"https://pith.science/paper/4CTJZSOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06827&json=true","fetch_graph":"https://pith.science/api/pith-number/4CTJZSOMKGKBXSHYDUZRWHFDR5/graph.json","fetch_events":"https://pith.science/api/pith-number/4CTJZSOMKGKBXSHYDUZRWHFDR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5/action/storage_attestation","attest_author":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5/action/author_attestation","sign_citation":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5/action/citation_signature","submit_replication":"https://pith.science/pith/4CTJZSOMKGKBXSHYDUZRWHFDR5/action/replication_record"}},"created_at":"2026-07-05T11:31:00.217699+00:00","updated_at":"2026-07-05T11:31:00.217699+00:00"}