{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BPUBJKFPEHXNIUUGGEY7NEIOF7","short_pith_number":"pith:BPUBJKFP","canonical_record":{"source":{"id":"1808.04468","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T21:08:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"01abbb3d536acc24d3c47f169bca29d49296a3ece78484d46e2e08e09e5b9504","abstract_canon_sha256":"726a20dd4647f3004179a1ff558470ca6c8195876180b219a88a5748933883be"},"schema_version":"1.0"},"canonical_sha256":"0be814a8af21eed452863131f6910e2fed0f8bd854c2451e7cdfff5f1f6dd438","source":{"kind":"arxiv","id":"1808.04468","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04468","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04468v2","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04468","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"BPUBJKFPEHXN","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BPUBJKFPEHXNIUUG","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BPUBJKFP","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BPUBJKFPEHXNIUUGGEY7NEIOF7","target":"record","payload":{"canonical_record":{"source":{"id":"1808.04468","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T21:08:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"01abbb3d536acc24d3c47f169bca29d49296a3ece78484d46e2e08e09e5b9504","abstract_canon_sha256":"726a20dd4647f3004179a1ff558470ca6c8195876180b219a88a5748933883be"},"schema_version":"1.0"},"canonical_sha256":"0be814a8af21eed452863131f6910e2fed0f8bd854c2451e7cdfff5f1f6dd438","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:31.512938Z","signature_b64":"wSV6/kbo7IHSfl91zS+OHy8GsHj3K/yisYzZ1m+TYMcJdVhUy+1vkonfLN9+e/nzBfETum108w0bw1DtFvgoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0be814a8af21eed452863131f6910e2fed0f8bd854c2451e7cdfff5f1f6dd438","last_reissued_at":"2026-05-17T23:57:31.512342Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:31.512342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.04468","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":"2026-05-17T23:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+WStU0yTGQqI/FTux8RB4Yca6WgIJCfaGc7Jq5yX3hu99cwNflq9fejGCMwMwM9ubnXlC+OkVCmo3fcwi7MvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:07:47.609827Z"},"content_sha256":"3d8ddd30f8ea26daa46763dacd24b197b303b74dce6d571e2832e69eddf76eb1","schema_version":"1.0","event_id":"sha256:3d8ddd30f8ea26daa46763dacd24b197b303b74dce6d571e2832e69eddf76eb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BPUBJKFPEHXNIUUGGEY7NEIOF7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Sensitive Generative Adversarial Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonathan Lacotte, Marco Pavone, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2018-08-13T21:08:46Z","abstract_excerpt":"We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for our formulation, which we call it risk-sensitive GAIL (RS-GAIL). We then derive two different versions of our RS-GAIL optimization problem that aim at matching the risk profiles of the agent and the expert w.r.t. Jensen-Shannon (JS) divergence and Wasserstein distance, and devel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04468","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":"2026-05-17T23:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGP0FEUktUYUoqEf67Cf/raOTPrDk8mxNc9fHVqGyAEOScmUqh2uH2yZILHBqRNHvrCvVkQ67HdHNyqDMRSQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:07:47.610166Z"},"content_sha256":"8c186b7adbc20d08915c78cb342d73f2be50eb8b4677fe79ca5f4663d1b804f6","schema_version":"1.0","event_id":"sha256:8c186b7adbc20d08915c78cb342d73f2be50eb8b4677fe79ca5f4663d1b804f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7/bundle.json","state_url":"https://pith.science/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7/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":"2026-06-03T22:07:47Z","links":{"resolver":"https://pith.science/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7","bundle":"https://pith.science/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7/bundle.json","state":"https://pith.science/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPUBJKFPEHXNIUUGGEY7NEIOF7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BPUBJKFPEHXNIUUGGEY7NEIOF7","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":"726a20dd4647f3004179a1ff558470ca6c8195876180b219a88a5748933883be","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T21:08:46Z","title_canon_sha256":"01abbb3d536acc24d3c47f169bca29d49296a3ece78484d46e2e08e09e5b9504"},"schema_version":"1.0","source":{"id":"1808.04468","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04468","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04468v2","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04468","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"BPUBJKFPEHXN","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BPUBJKFPEHXNIUUG","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BPUBJKFP","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:8c186b7adbc20d08915c78cb342d73f2be50eb8b4677fe79ca5f4663d1b804f6","target":"graph","created_at":"2026-05-17T23:57:31Z","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":"We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for our formulation, which we call it risk-sensitive GAIL (RS-GAIL). We then derive two different versions of our RS-GAIL optimization problem that aim at matching the risk profiles of the agent and the expert w.r.t. Jensen-Shannon (JS) divergence and Wasserstein distance, and devel","authors_text":"Jonathan Lacotte, Marco Pavone, Mohammad Ghavamzadeh, Yinlam Chow","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T21:08:46Z","title":"Risk-Sensitive Generative Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04468","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":"sha256:3d8ddd30f8ea26daa46763dacd24b197b303b74dce6d571e2832e69eddf76eb1","target":"record","created_at":"2026-05-17T23:57:31Z","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":"726a20dd4647f3004179a1ff558470ca6c8195876180b219a88a5748933883be","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T21:08:46Z","title_canon_sha256":"01abbb3d536acc24d3c47f169bca29d49296a3ece78484d46e2e08e09e5b9504"},"schema_version":"1.0","source":{"id":"1808.04468","kind":"arxiv","version":2}},"canonical_sha256":"0be814a8af21eed452863131f6910e2fed0f8bd854c2451e7cdfff5f1f6dd438","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0be814a8af21eed452863131f6910e2fed0f8bd854c2451e7cdfff5f1f6dd438","first_computed_at":"2026-05-17T23:57:31.512342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:31.512342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSV6/kbo7IHSfl91zS+OHy8GsHj3K/yisYzZ1m+TYMcJdVhUy+1vkonfLN9+e/nzBfETum108w0bw1DtFvgoDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:31.512938Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04468","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d8ddd30f8ea26daa46763dacd24b197b303b74dce6d571e2832e69eddf76eb1","sha256:8c186b7adbc20d08915c78cb342d73f2be50eb8b4677fe79ca5f4663d1b804f6"],"state_sha256":"2fa2af5529f33576d335fe64af9fe0e96aa9b81e251e9789229c7d3f335e82bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"58yy9NRIq2a/6ADSUXiOsi5IrCoH6a8uXteupg0GXniRBTLXJYo/zHaD1mroxWOny0SpISc3PZrH9oEarENJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:07:47.612178Z","bundle_sha256":"dececd448efbba0d49d07e2bb8ae80010557d3591204647542e1ef7655de0a46"}}