{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:36V43DEBH2IEPOSFVNX4NWNZ3M","short_pith_number":"pith:36V43DEB","schema_version":"1.0","canonical_sha256":"dfabcd8c813e9047ba45ab6fc6d9b9db2dd272ea5d60105525e2b767bbd33707","source":{"kind":"arxiv","id":"1909.07843","version":2},"attestation_state":"computed","paper":{"title":"Active Learning for Risk-Sensitive Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Rui Chen, Wenshuo Wang, Zirui Zhao","submitted_at":"2019-09-14T00:57:50Z","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"},"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":"1909.07843","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T00:57:50Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"cf0054087d3452a3ae0bb37fc30c33ab1326c4a5a1f96a6c4323c919af43d3b4","abstract_canon_sha256":"895b1a39bdffa36bb737435d856d77033c6a8301db1083f337d7e5a31931659c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:59.518115Z","signature_b64":"eUQXjcP/xujwDC2TfXJ4i5/Z9nBlncupqL6ZILPGNavXIzvm7/NvLKhzuQLvDl+tvMyyZi6IkWYYBn71pbbwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfabcd8c813e9047ba45ab6fc6d9b9db2dd272ea5d60105525e2b767bbd33707","last_reissued_at":"2026-07-05T00:06:59.517653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:59.517653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Learning for Risk-Sensitive Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Rui Chen, Wenshuo Wang, Zirui Zhao","submitted_at":"2019-09-14T00:57:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07843","kind":"arxiv","version":2},"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/1909.07843/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":"1909.07843","created_at":"2026-07-05T00:06:59.517709+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07843v2","created_at":"2026-07-05T00:06:59.517709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07843","created_at":"2026-07-05T00:06:59.517709+00:00"},{"alias_kind":"pith_short_12","alias_value":"36V43DEBH2IE","created_at":"2026-07-05T00:06:59.517709+00:00"},{"alias_kind":"pith_short_16","alias_value":"36V43DEBH2IEPOSF","created_at":"2026-07-05T00:06:59.517709+00:00"},{"alias_kind":"pith_short_8","alias_value":"36V43DEB","created_at":"2026-07-05T00:06:59.517709+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/36V43DEBH2IEPOSFVNX4NWNZ3M","json":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M.json","graph_json":"https://pith.science/api/pith-number/36V43DEBH2IEPOSFVNX4NWNZ3M/graph.json","events_json":"https://pith.science/api/pith-number/36V43DEBH2IEPOSFVNX4NWNZ3M/events.json","paper":"https://pith.science/paper/36V43DEB"},"agent_actions":{"view_html":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M","download_json":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M.json","view_paper":"https://pith.science/paper/36V43DEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07843&json=true","fetch_graph":"https://pith.science/api/pith-number/36V43DEBH2IEPOSFVNX4NWNZ3M/graph.json","fetch_events":"https://pith.science/api/pith-number/36V43DEBH2IEPOSFVNX4NWNZ3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M/action/storage_attestation","attest_author":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M/action/author_attestation","sign_citation":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M/action/citation_signature","submit_replication":"https://pith.science/pith/36V43DEBH2IEPOSFVNX4NWNZ3M/action/replication_record"}},"created_at":"2026-07-05T00:06:59.517709+00:00","updated_at":"2026-07-05T00:06:59.517709+00:00"}