{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J5K4MKQK4R5HI57X2FP54BM5SN","short_pith_number":"pith:J5K4MKQK","canonical_record":{"source":{"id":"2507.03900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T04:41:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dc27f9d64a2685289792565bd2a2e629902302de1381b92205257af1a87b8d19","abstract_canon_sha256":"eb7df3868720a0842ba57450debadec402d54f0696b13b128a1568be70e9bec8"},"schema_version":"1.0"},"canonical_sha256":"4f55c62a0ae47a7477f7d15fde059d9356944e94d65cf784de45b3890ff21f8a","source":{"kind":"arxiv","id":"2507.03900","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03900","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03900v1","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03900","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"J5K4MKQK4R5H","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"J5K4MKQK4R5HI57X","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"J5K4MKQK","created_at":"2026-07-05T11:32:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J5K4MKQK4R5HI57X2FP54BM5SN","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T04:41:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dc27f9d64a2685289792565bd2a2e629902302de1381b92205257af1a87b8d19","abstract_canon_sha256":"eb7df3868720a0842ba57450debadec402d54f0696b13b128a1568be70e9bec8"},"schema_version":"1.0"},"canonical_sha256":"4f55c62a0ae47a7477f7d15fde059d9356944e94d65cf784de45b3890ff21f8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:36.956163Z","signature_b64":"iCBRhTrzb/QuG/W8x7bm+tX19B0ADAuTKOHiFDwO7DoRPbfc+qiDJFDFOW8ueYLlsdBGfZEtK7AFt6SAhutcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f55c62a0ae47a7477f7d15fde059d9356944e94d65cf784de45b3890ff21f8a","last_reissued_at":"2026-07-05T11:32:36.955673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:36.955673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03900","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKy3ENrnUY2vC4TKqdBM/eaSD1LrmYdPINDzBeQFHVhFtLJipe5NJJMQ0Mt5tuC+NPPxLCgLV2myW0CQGvoVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:05:27.118651Z"},"content_sha256":"4b7685457608bd5c207a9ea75a3ae127e037d1b48e43cbe9ced08029339df16f","schema_version":"1.0","event_id":"sha256:4b7685457608bd5c207a9ea75a3ae127e037d1b48e43cbe9ced08029339df16f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J5K4MKQK4R5HI57X2FP54BM5SN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyejin Ku, Mehrdad Moghimi","submitted_at":"2025-07-05T04:41:54Z","abstract_excerpt":"The development of Distributional Reinforcement Learning (DRL) has introduced a natural way to incorporate risk sensitivity into value-based and actor-critic methods by employing risk measures other than expectation in the value function. While this approach is widely adopted in many online and offline RL algorithms due to its simplicity, the naive integration of risk measures often results in suboptimal policies. This limitation can be particularly harmful in scenarios where the need for effective risk-sensitive policies is critical and worst-case outcomes carry severe consequences. To addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03900","kind":"arxiv","version":1},"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/2507.03900/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":"2026-07-05T11:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3ATGNuYky3tB+qLgfkUgh0mdlGP2Optz2sPP1OxXwbIswspnZZ6S7TGnOmjznWJB2QZbLwxEfFnqBAViB/DBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:05:27.119258Z"},"content_sha256":"233a2845ca56486dea0ed2bd1d75c7af827c031ffcb6f765e3f84e7d1b320e38","schema_version":"1.0","event_id":"sha256:233a2845ca56486dea0ed2bd1d75c7af827c031ffcb6f765e3f84e7d1b320e38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5K4MKQK4R5HI57X2FP54BM5SN/bundle.json","state_url":"https://pith.science/pith/J5K4MKQK4R5HI57X2FP54BM5SN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5K4MKQK4R5HI57X2FP54BM5SN/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":"2026-08-11T15:05:27Z","links":{"resolver":"https://pith.science/pith/J5K4MKQK4R5HI57X2FP54BM5SN","bundle":"https://pith.science/pith/J5K4MKQK4R5HI57X2FP54BM5SN/bundle.json","state":"https://pith.science/pith/J5K4MKQK4R5HI57X2FP54BM5SN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5K4MKQK4R5HI57X2FP54BM5SN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J5K4MKQK4R5HI57X2FP54BM5SN","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":"eb7df3868720a0842ba57450debadec402d54f0696b13b128a1568be70e9bec8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T04:41:54Z","title_canon_sha256":"dc27f9d64a2685289792565bd2a2e629902302de1381b92205257af1a87b8d19"},"schema_version":"1.0","source":{"id":"2507.03900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03900","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03900v1","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03900","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"J5K4MKQK4R5H","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"J5K4MKQK4R5HI57X","created_at":"2026-07-05T11:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"J5K4MKQK","created_at":"2026-07-05T11:32:36Z"}],"graph_snapshots":[{"event_id":"sha256:233a2845ca56486dea0ed2bd1d75c7af827c031ffcb6f765e3f84e7d1b320e38","target":"graph","created_at":"2026-07-05T11:32:36Z","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/2507.03900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of Distributional Reinforcement Learning (DRL) has introduced a natural way to incorporate risk sensitivity into value-based and actor-critic methods by employing risk measures other than expectation in the value function. While this approach is widely adopted in many online and offline RL algorithms due to its simplicity, the naive integration of risk measures often results in suboptimal policies. This limitation can be particularly harmful in scenarios where the need for effective risk-sensitive policies is critical and worst-case outcomes carry severe consequences. To addres","authors_text":"Hyejin Ku, Mehrdad Moghimi","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T04:41:54Z","title":"Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03900","kind":"arxiv","version":1},"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":"sha256:4b7685457608bd5c207a9ea75a3ae127e037d1b48e43cbe9ced08029339df16f","target":"record","created_at":"2026-07-05T11:32:36Z","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":"eb7df3868720a0842ba57450debadec402d54f0696b13b128a1568be70e9bec8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T04:41:54Z","title_canon_sha256":"dc27f9d64a2685289792565bd2a2e629902302de1381b92205257af1a87b8d19"},"schema_version":"1.0","source":{"id":"2507.03900","kind":"arxiv","version":1}},"canonical_sha256":"4f55c62a0ae47a7477f7d15fde059d9356944e94d65cf784de45b3890ff21f8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f55c62a0ae47a7477f7d15fde059d9356944e94d65cf784de45b3890ff21f8a","first_computed_at":"2026-07-05T11:32:36.955673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:36.955673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iCBRhTrzb/QuG/W8x7bm+tX19B0ADAuTKOHiFDwO7DoRPbfc+qiDJFDFOW8ueYLlsdBGfZEtK7AFt6SAhutcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:36.956163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b7685457608bd5c207a9ea75a3ae127e037d1b48e43cbe9ced08029339df16f","sha256:233a2845ca56486dea0ed2bd1d75c7af827c031ffcb6f765e3f84e7d1b320e38"],"state_sha256":"5664e2bc21412631345354842ab22d6408d2228592a553ddf8582b20cbb562de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aM4XFMaS5GJXTH22uHju3qlHfQA+bJMzBFH3TIrY9aC2lMykhxg0NMuhlYQM1gV0rl1H0B6B6qpw68PEx2jzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:05:27.130427Z","bundle_sha256":"afd2b6043712353f8927d635f056657f66260e48d8754fa83770bbae637735e4"}}