{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GYUTXJCWLIGYPQFRSX5F3EL5W6","short_pith_number":"pith:GYUTXJCW","canonical_record":{"source":{"id":"1711.10055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-28T00:07:10Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"e2b27f6ff101399e4485dfce902a53f54793f67060fadfaacd2e3ce7ed98fa1a","abstract_canon_sha256":"f8a6f87ee9a779dce008fe5be089df98d5e054a48248ffc562b97d406548c3e1"},"schema_version":"1.0"},"canonical_sha256":"36293ba4565a0d87c0b195fa5d917db7b138c084a35aedbf311732dcfaf332ff","source":{"kind":"arxiv","id":"1711.10055","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.10055","created_at":"2026-05-18T00:20:24Z"},{"alias_kind":"arxiv_version","alias_value":"1711.10055v2","created_at":"2026-05-18T00:20:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10055","created_at":"2026-05-18T00:20:24Z"},{"alias_kind":"pith_short_12","alias_value":"GYUTXJCWLIGY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GYUTXJCWLIGYPQFR","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GYUTXJCW","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GYUTXJCWLIGYPQFRSX5F3EL5W6","target":"record","payload":{"canonical_record":{"source":{"id":"1711.10055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-28T00:07:10Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"e2b27f6ff101399e4485dfce902a53f54793f67060fadfaacd2e3ce7ed98fa1a","abstract_canon_sha256":"f8a6f87ee9a779dce008fe5be089df98d5e054a48248ffc562b97d406548c3e1"},"schema_version":"1.0"},"canonical_sha256":"36293ba4565a0d87c0b195fa5d917db7b138c084a35aedbf311732dcfaf332ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:24.061897Z","signature_b64":"rrufBtTE8JlNEHYc/UygJpFR3oXP2LwzXQvHuogpaGxVwXi2jOBOzq5oK4c6lDZ9F2zqCVZX6AgLg+HAH9T2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36293ba4565a0d87c0b195fa5d917db7b138c084a35aedbf311732dcfaf332ff","last_reissued_at":"2026-05-18T00:20:24.061438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:24.061438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.10055","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AtOGA/RKLKgmxoG9SnJ1s+PXSqb/0rvC55lxGebj4RrPLzwZXe7E8+lmTTpoaRIpLrYbOcl69YpoHnZO8WbOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:50:44.906217Z"},"content_sha256":"6a8e0c4dabd9b0f6371cc082c991c70350b62b29871c773ecb9bab62a6604d3e","schema_version":"1.0","event_id":"sha256:6a8e0c4dabd9b0f6371cc082c991c70350b62b29871c773ecb9bab62a6604d3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GYUTXJCWLIGYPQFRSX5F3EL5W6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Anirudha Majumdar, Jonathan Lacotte, Marco Pavone, Sumeet Singh","submitted_at":"2017-11-28T00:07:10Z","abstract_excerpt":"The literature on Inverse Reinforcement Learning (IRL) typically assumes that humans take actions in order to minimize the expected value of a cost function, i.e., that humans are risk neutral. Yet, in practice, humans are often far from being risk neutral. To fill this gap, the objective of this paper is to devise a framework for risk-sensitive IRL in order to explicitly account for a human's risk sensitivity. To this end, we propose a flexible class of models based on coherent risk measures, which allow us to capture an entire spectrum of risk preferences from risk-neutral to worst-case. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10055","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+smQKXpxOUXi2CbJGIGvJ2NKbqhodW8NCd+l6NGUm9efTvMMhQ1kLyzK+Mo8SRJI80FOn3JfiII+W9AYV8mBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:50:44.906919Z"},"content_sha256":"7970d8f698cc5a24c8195a123f3d6b1d518ed3870b8b2aaec039942c6756711f","schema_version":"1.0","event_id":"sha256:7970d8f698cc5a24c8195a123f3d6b1d518ed3870b8b2aaec039942c6756711f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6/bundle.json","state_url":"https://pith.science/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T04:50:44Z","links":{"resolver":"https://pith.science/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6","bundle":"https://pith.science/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6/bundle.json","state":"https://pith.science/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYUTXJCWLIGYPQFRSX5F3EL5W6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GYUTXJCWLIGYPQFRSX5F3EL5W6","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":"f8a6f87ee9a779dce008fe5be089df98d5e054a48248ffc562b97d406548c3e1","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-28T00:07:10Z","title_canon_sha256":"e2b27f6ff101399e4485dfce902a53f54793f67060fadfaacd2e3ce7ed98fa1a"},"schema_version":"1.0","source":{"id":"1711.10055","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.10055","created_at":"2026-05-18T00:20:24Z"},{"alias_kind":"arxiv_version","alias_value":"1711.10055v2","created_at":"2026-05-18T00:20:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10055","created_at":"2026-05-18T00:20:24Z"},{"alias_kind":"pith_short_12","alias_value":"GYUTXJCWLIGY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GYUTXJCWLIGYPQFR","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GYUTXJCW","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:7970d8f698cc5a24c8195a123f3d6b1d518ed3870b8b2aaec039942c6756711f","target":"graph","created_at":"2026-05-18T00:20:24Z","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":"The literature on Inverse Reinforcement Learning (IRL) typically assumes that humans take actions in order to minimize the expected value of a cost function, i.e., that humans are risk neutral. Yet, in practice, humans are often far from being risk neutral. To fill this gap, the objective of this paper is to devise a framework for risk-sensitive IRL in order to explicitly account for a human's risk sensitivity. To this end, we propose a flexible class of models based on coherent risk measures, which allow us to capture an entire spectrum of risk preferences from risk-neutral to worst-case. We ","authors_text":"Anirudha Majumdar, Jonathan Lacotte, Marco Pavone, Sumeet Singh","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-28T00:07:10Z","title":"Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10055","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":"sha256:6a8e0c4dabd9b0f6371cc082c991c70350b62b29871c773ecb9bab62a6604d3e","target":"record","created_at":"2026-05-18T00:20:24Z","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":"f8a6f87ee9a779dce008fe5be089df98d5e054a48248ffc562b97d406548c3e1","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-28T00:07:10Z","title_canon_sha256":"e2b27f6ff101399e4485dfce902a53f54793f67060fadfaacd2e3ce7ed98fa1a"},"schema_version":"1.0","source":{"id":"1711.10055","kind":"arxiv","version":2}},"canonical_sha256":"36293ba4565a0d87c0b195fa5d917db7b138c084a35aedbf311732dcfaf332ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36293ba4565a0d87c0b195fa5d917db7b138c084a35aedbf311732dcfaf332ff","first_computed_at":"2026-05-18T00:20:24.061438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:24.061438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rrufBtTE8JlNEHYc/UygJpFR3oXP2LwzXQvHuogpaGxVwXi2jOBOzq5oK4c6lDZ9F2zqCVZX6AgLg+HAH9T2CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:24.061897Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.10055","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a8e0c4dabd9b0f6371cc082c991c70350b62b29871c773ecb9bab62a6604d3e","sha256:7970d8f698cc5a24c8195a123f3d6b1d518ed3870b8b2aaec039942c6756711f"],"state_sha256":"e69c2c31152c9493ea2b4162cd09f766519141d3be397c9b427d3a69559e13d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qRe5b5O8g6Zw6bOadWRoCt0+CSOWT+jcXgatSFb5Fbs7nTv3toEFaCgESr2QqNLRuWH5IzOSEzC1GnWowueAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T04:50:44.910760Z","bundle_sha256":"2577d70c70334302370c14b8edf7f7914d554790fc0142f6b54c66a2e6520fc7"}}