{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:36V43DEBH2IEPOSFVNX4NWNZ3M","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":"895b1a39bdffa36bb737435d856d77033c6a8301db1083f337d7e5a31931659c","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T00:57:50Z","title_canon_sha256":"cf0054087d3452a3ae0bb37fc30c33ab1326c4a5a1f96a6c4323c919af43d3b4"},"schema_version":"1.0","source":{"id":"1909.07843","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.07843","created_at":"2026-07-05T00:06:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.07843v2","created_at":"2026-07-05T00:06:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07843","created_at":"2026-07-05T00:06:59Z"},{"alias_kind":"pith_short_12","alias_value":"36V43DEBH2IE","created_at":"2026-07-05T00:06:59Z"},{"alias_kind":"pith_short_16","alias_value":"36V43DEBH2IEPOSF","created_at":"2026-07-05T00:06:59Z"},{"alias_kind":"pith_short_8","alias_value":"36V43DEB","created_at":"2026-07-05T00:06:59Z"}],"graph_snapshots":[{"event_id":"sha256:8f8892d7f99a0aa8af6c0a9d42ad1519173097e21610e9c56c9908597d30c756","target":"graph","created_at":"2026-07-05T00:06:59Z","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/1909.07843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behaviors under ambiguity. Risk-sensitive inverse reinforcement learning (RS-IRL) bridges such gap by assuming that humans act according to a random cost with respect to a set of subjectively distorted distributions instead of a fixed one. Such assumption provides the additional flexibility to model human's risk preferences, represented by a risk envelope, in safe-critical tasks. Howe","authors_text":"Ding Zhao, Rui Chen, Wenshuo Wang, Zirui Zhao","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T00:57:50Z","title":"Active Learning for Risk-Sensitive Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07843","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":"sha256:634bad8c7a8ae24e76633e43bca6256d04d6e053252edfaf1e87c8da5ada3919","target":"record","created_at":"2026-07-05T00:06:59Z","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":"895b1a39bdffa36bb737435d856d77033c6a8301db1083f337d7e5a31931659c","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T00:57:50Z","title_canon_sha256":"cf0054087d3452a3ae0bb37fc30c33ab1326c4a5a1f96a6c4323c919af43d3b4"},"schema_version":"1.0","source":{"id":"1909.07843","kind":"arxiv","version":2}},"canonical_sha256":"dfabcd8c813e9047ba45ab6fc6d9b9db2dd272ea5d60105525e2b767bbd33707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfabcd8c813e9047ba45ab6fc6d9b9db2dd272ea5d60105525e2b767bbd33707","first_computed_at":"2026-07-05T00:06:59.517653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:06:59.517653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eUQXjcP/xujwDC2TfXJ4i5/Z9nBlncupqL6ZILPGNavXIzvm7/NvLKhzuQLvDl+tvMyyZi6IkWYYBn71pbbwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:06:59.518115Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.07843","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:634bad8c7a8ae24e76633e43bca6256d04d6e053252edfaf1e87c8da5ada3919","sha256:8f8892d7f99a0aa8af6c0a9d42ad1519173097e21610e9c56c9908597d30c756"],"state_sha256":"b50d8a1bef0759734b21c8259ec8a8589f232ecf6f00c1a64d12e153a148e144"}