{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CI26NMO46IVJMCVQZLII3H7SXU","short_pith_number":"pith:CI26NMO4","canonical_record":{"source":{"id":"2505.16925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"758abde69142bfbce70c36af7d8b14f3cba2de7919af1744d2a8da7c4ef8917e","abstract_canon_sha256":"01fc3c462dacaefef50768a7a2bff90be1632f269ea8466706e8ee12fe09542f"},"schema_version":"1.0"},"canonical_sha256":"1235e6b1dcf22a960ab0cad08d9ff2bd35299d6eab6c0a716c8fef8a5e3afed3","source":{"kind":"arxiv","id":"2505.16925","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16925","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16925v2","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16925","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"CI26NMO46IVJ","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"CI26NMO46IVJMCVQ","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"CI26NMO4","created_at":"2026-07-05T11:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CI26NMO46IVJMCVQZLII3H7SXU","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"758abde69142bfbce70c36af7d8b14f3cba2de7919af1744d2a8da7c4ef8917e","abstract_canon_sha256":"01fc3c462dacaefef50768a7a2bff90be1632f269ea8466706e8ee12fe09542f"},"schema_version":"1.0"},"canonical_sha256":"1235e6b1dcf22a960ab0cad08d9ff2bd35299d6eab6c0a716c8fef8a5e3afed3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:47.709092Z","signature_b64":"1+LjUulcdPH7IEYl8u6SyO1BaOrHEe1/U8GPj7f3wpdqZQeyXicYPKmg8AJLr9RIZp2/LdtBSvQwWKzcpLNGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1235e6b1dcf22a960ab0cad08d9ff2bd35299d6eab6c0a716c8fef8a5e3afed3","last_reissued_at":"2026-07-05T11:09:47.708578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:47.708578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16925","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":"2026-07-05T11:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnJ7KMHfOGFn58YAYwyeJfn1PfAAlWIMKC1whxfBLxpNYH9m+7qNe+keZUSXBzdpJ35Rf+d3VFc1f6fgDmEaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:32:37.832072Z"},"content_sha256":"6d78720b8dcf7419bddc0199a9a6a2154b8994aec63b615ff3632bc9ad421c84","schema_version":"1.0","event_id":"sha256:6d78720b8dcf7419bddc0199a9a6a2154b8994aec63b615ff3632bc9ad421c84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CI26NMO46IVJMCVQZLII3H7SXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Averse Reinforcement Learning with Itakura-Saito Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Anita Toleutaeva, Evgeny Burnaev, Igor Udovichenko, Olivier Croissant","submitted_at":"2025-05-22T17:18:07Z","abstract_excerpt":"Risk-averse reinforcement learning finds application in various high-stakes fields. Unlike classical reinforcement learning, which aims to maximize expected returns, risk-averse agents choose policies that minimize risk, occasionally sacrificing expected value. These preferences can be framed through utility theory. We focus on the specific case of the exponential utility function, where one can derive the Bellman equations and employ various reinforcement learning algorithms with few modifications. To address this, we introduce to the broad machine learning community a numerically stable and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16925","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/2505.16925/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRcHYaV6DZPuULk/QkamJ05v7wk7xaU6GZPqMzTrltlnhgVhNTjAdZpbnP7jxmTJVk9rMSHPAeQoSX+pT182AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:32:37.832460Z"},"content_sha256":"9ade95d303cad43457d9b1fb992c35286e97b590a5794c8a838172d6c68b25ef","schema_version":"1.0","event_id":"sha256:9ade95d303cad43457d9b1fb992c35286e97b590a5794c8a838172d6c68b25ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CI26NMO46IVJMCVQZLII3H7SXU/bundle.json","state_url":"https://pith.science/pith/CI26NMO46IVJMCVQZLII3H7SXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CI26NMO46IVJMCVQZLII3H7SXU/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":"2026-07-07T10:32:37Z","links":{"resolver":"https://pith.science/pith/CI26NMO46IVJMCVQZLII3H7SXU","bundle":"https://pith.science/pith/CI26NMO46IVJMCVQZLII3H7SXU/bundle.json","state":"https://pith.science/pith/CI26NMO46IVJMCVQZLII3H7SXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CI26NMO46IVJMCVQZLII3H7SXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CI26NMO46IVJMCVQZLII3H7SXU","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":"01fc3c462dacaefef50768a7a2bff90be1632f269ea8466706e8ee12fe09542f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:18:07Z","title_canon_sha256":"758abde69142bfbce70c36af7d8b14f3cba2de7919af1744d2a8da7c4ef8917e"},"schema_version":"1.0","source":{"id":"2505.16925","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16925","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16925v2","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16925","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"CI26NMO46IVJ","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"CI26NMO46IVJMCVQ","created_at":"2026-07-05T11:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"CI26NMO4","created_at":"2026-07-05T11:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:9ade95d303cad43457d9b1fb992c35286e97b590a5794c8a838172d6c68b25ef","target":"graph","created_at":"2026-07-05T11:09:47Z","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/2505.16925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Risk-averse reinforcement learning finds application in various high-stakes fields. Unlike classical reinforcement learning, which aims to maximize expected returns, risk-averse agents choose policies that minimize risk, occasionally sacrificing expected value. These preferences can be framed through utility theory. We focus on the specific case of the exponential utility function, where one can derive the Bellman equations and employ various reinforcement learning algorithms with few modifications. To address this, we introduce to the broad machine learning community a numerically stable and ","authors_text":"Alexander Korotin, Anita Toleutaeva, Evgeny Burnaev, Igor Udovichenko, Olivier Croissant","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:18:07Z","title":"Risk-Averse Reinforcement Learning with Itakura-Saito Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16925","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":"sha256:6d78720b8dcf7419bddc0199a9a6a2154b8994aec63b615ff3632bc9ad421c84","target":"record","created_at":"2026-07-05T11:09:47Z","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":"01fc3c462dacaefef50768a7a2bff90be1632f269ea8466706e8ee12fe09542f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:18:07Z","title_canon_sha256":"758abde69142bfbce70c36af7d8b14f3cba2de7919af1744d2a8da7c4ef8917e"},"schema_version":"1.0","source":{"id":"2505.16925","kind":"arxiv","version":2}},"canonical_sha256":"1235e6b1dcf22a960ab0cad08d9ff2bd35299d6eab6c0a716c8fef8a5e3afed3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1235e6b1dcf22a960ab0cad08d9ff2bd35299d6eab6c0a716c8fef8a5e3afed3","first_computed_at":"2026-07-05T11:09:47.708578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:47.708578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1+LjUulcdPH7IEYl8u6SyO1BaOrHEe1/U8GPj7f3wpdqZQeyXicYPKmg8AJLr9RIZp2/LdtBSvQwWKzcpLNGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:47.709092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16925","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d78720b8dcf7419bddc0199a9a6a2154b8994aec63b615ff3632bc9ad421c84","sha256:9ade95d303cad43457d9b1fb992c35286e97b590a5794c8a838172d6c68b25ef"],"state_sha256":"67c0bc6ad665818e0ccef565ee906ce0bd754481e962d3984f1178ae58332599"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3NofkhGbznHr5tCBy2AsqS/10hHqyRTJ+KH5vvJsN8kErU1hTPt86JPymyBK2dhbxIT8tbOsJwMYAAIQSQXLDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:32:37.834267Z","bundle_sha256":"41c266d62d557c80554ba2e0a2e12814ca0159111019242504401d4cc3a50974"}}