{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L2WVJCMFCQBZIUCHO7CFACFRYO","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":"0318c61880b7c8d5bfb74924c61dd4ff862d3f7eb5260e67ba90fbbb6e90ce78","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T18:41:31Z","title_canon_sha256":"18f9089ea4aaa63b408980e9ee9a2a0c839abf6d5e753cdcde6c435271bd18d0"},"schema_version":"1.0","source":{"id":"1906.09624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09624","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09624v1","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09624","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"L2WVJCMFCQBZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L2WVJCMFCQBZIUCH","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L2WVJCMF","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:68982c9ec5111fc1aff974077df483050aa059c6025a65ca3feea7714445efe6","target":"graph","created_at":"2026-05-17T23:42:37Z","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"},"paper":{"abstract_excerpt":"Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the other hand, often have systematic biases: risk-aversion, myopia, etc. One option is to try to characterize these biases and account for them explicitly during learning. But in the era of deep learning, a natural suggestion researchers make is to avoid mathematical models of human behavior that are fraug","authors_text":"Anca D. Dragan, Noah Gundotra, Pieter Abbeel, Rohin Shah","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T18:41:31Z","title":"On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09624","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":"sha256:3a830e439551598a40ce4c9344505f4aa5ab48584086183977f65213e58d34c2","target":"record","created_at":"2026-05-17T23:42:37Z","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":"0318c61880b7c8d5bfb74924c61dd4ff862d3f7eb5260e67ba90fbbb6e90ce78","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T18:41:31Z","title_canon_sha256":"18f9089ea4aaa63b408980e9ee9a2a0c839abf6d5e753cdcde6c435271bd18d0"},"schema_version":"1.0","source":{"id":"1906.09624","kind":"arxiv","version":1}},"canonical_sha256":"5ead548985140394504777c45008b1c3abaaae984ca4a097df33e74bae5e87ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ead548985140394504777c45008b1c3abaaae984ca4a097df33e74bae5e87ea","first_computed_at":"2026-05-17T23:42:37.300767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:37.300767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u6yI1c8ePnaXZlu/pCEqUP6MD548qNvC/XYokRdB+3NvAjNSnTkE3/lvzcs6KTwJ/RQakwRvfpVFKvz83LfMBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:37.301500Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a830e439551598a40ce4c9344505f4aa5ab48584086183977f65213e58d34c2","sha256:68982c9ec5111fc1aff974077df483050aa059c6025a65ca3feea7714445efe6"],"state_sha256":"53535a4999fe743eb55451d26834dcbf3936950b33570ecb50f65598e492b331"}