{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XHH53RIESDB5JYQUVBQBK6AVBL","short_pith_number":"pith:XHH53RIE","canonical_record":{"source":{"id":"2206.07376","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T08:32:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18d78445c29f0c047c7ea7052ce0aa352c35f75c71327ac25fa6b5cf26aac14c","abstract_canon_sha256":"b99ca9ae776cadb33d97dc5cc5f5ce64c2cba9709a0e0d4b836ba860831fbb8d"},"schema_version":"1.0"},"canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","source":{"kind":"arxiv","id":"2206.07376","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07376","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07376v3","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07376","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"XHH53RIESDB5","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"XHH53RIESDB5JYQU","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"XHH53RIE","created_at":"2026-07-05T05:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XHH53RIESDB5JYQUVBQBK6AVBL","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07376","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T08:32:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18d78445c29f0c047c7ea7052ce0aa352c35f75c71327ac25fa6b5cf26aac14c","abstract_canon_sha256":"b99ca9ae776cadb33d97dc5cc5f5ce64c2cba9709a0e0d4b836ba860831fbb8d"},"schema_version":"1.0"},"canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:13.670820Z","signature_b64":"KfjkX3X/alpP28thJ3bxTKtMt5fkb4g1tUqUMYaNBIeZOj0eIoYKtVHvIHmr8dwslGXreykJB/avTtdQsXGCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","last_reissued_at":"2026-07-05T05:49:13.670372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:13.670372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07376","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q3BENtGCEnoY381Nw3KIMOGKtAvP9vnodb9YWSGnXp4wJTVq5nGAGh2/D2V+KAY2D1HMw9EwGSMFg3GpbJXcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:39:55.669133Z"},"content_sha256":"209580b25dffbbbcb270601030219aa3323c17a3f9d3b7b68a7817463566a8af","schema_version":"1.0","event_id":"sha256:209580b25dffbbbcb270601030219aa3323c17a3f9d3b7b68a7817463566a8af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XHH53RIESDB5JYQUVBQBK6AVBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Li Xia, Qianchuan Zhao, Shuai Ma, Xiaoteng Ma","submitted_at":"2022-06-15T08:32:53Z","abstract_excerpt":"Keeping risk under control is often more crucial than maximizing expected rewards in real-world decision-making situations, such as finance, robotics, autonomous driving, etc. The most natural choice of risk measures is variance, which penalizes the upside volatility as much as the downside part. Instead, the (downside) semivariance, which captures the negative deviation of a random variable under its mean, is more suitable for risk-averse proposes. This paper aims at optimizing the mean-semivariance (MSV) criterion in reinforcement learning w.r.t. steady reward distribution. Since semivarianc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07376","kind":"arxiv","version":3},"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/2206.07376/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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kwrq0FI0rP2KiBGA9XrLErCFbdPtrNO3rDfkF38c/xlW47vkGzv4Q/rzMsc+jfkfctjnNCUWpTJlOndjmZo+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:39:55.669538Z"},"content_sha256":"132c72071e9ef2ce7a4083680b34476f9f0cd9d2aeae9e41558b9532d881889f","schema_version":"1.0","event_id":"sha256:132c72071e9ef2ce7a4083680b34476f9f0cd9d2aeae9e41558b9532d881889f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/bundle.json","state_url":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHH53RIESDB5JYQUVBQBK6AVBL/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":"2026-07-06T17:39:55Z","links":{"resolver":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL","bundle":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/bundle.json","state":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHH53RIESDB5JYQUVBQBK6AVBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XHH53RIESDB5JYQUVBQBK6AVBL","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":"b99ca9ae776cadb33d97dc5cc5f5ce64c2cba9709a0e0d4b836ba860831fbb8d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T08:32:53Z","title_canon_sha256":"18d78445c29f0c047c7ea7052ce0aa352c35f75c71327ac25fa6b5cf26aac14c"},"schema_version":"1.0","source":{"id":"2206.07376","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07376","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07376v3","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07376","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"XHH53RIESDB5","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"XHH53RIESDB5JYQU","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"XHH53RIE","created_at":"2026-07-05T05:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:132c72071e9ef2ce7a4083680b34476f9f0cd9d2aeae9e41558b9532d881889f","target":"graph","created_at":"2026-07-05T05:49:13Z","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/2206.07376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Keeping risk under control is often more crucial than maximizing expected rewards in real-world decision-making situations, such as finance, robotics, autonomous driving, etc. The most natural choice of risk measures is variance, which penalizes the upside volatility as much as the downside part. Instead, the (downside) semivariance, which captures the negative deviation of a random variable under its mean, is more suitable for risk-averse proposes. This paper aims at optimizing the mean-semivariance (MSV) criterion in reinforcement learning w.r.t. steady reward distribution. Since semivarianc","authors_text":"Li Xia, Qianchuan Zhao, Shuai Ma, Xiaoteng Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T08:32:53Z","title":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07376","kind":"arxiv","version":3},"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":"sha256:209580b25dffbbbcb270601030219aa3323c17a3f9d3b7b68a7817463566a8af","target":"record","created_at":"2026-07-05T05:49:13Z","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":"b99ca9ae776cadb33d97dc5cc5f5ce64c2cba9709a0e0d4b836ba860831fbb8d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T08:32:53Z","title_canon_sha256":"18d78445c29f0c047c7ea7052ce0aa352c35f75c71327ac25fa6b5cf26aac14c"},"schema_version":"1.0","source":{"id":"2206.07376","kind":"arxiv","version":3}},"canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","first_computed_at":"2026-07-05T05:49:13.670372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:13.670372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KfjkX3X/alpP28thJ3bxTKtMt5fkb4g1tUqUMYaNBIeZOj0eIoYKtVHvIHmr8dwslGXreykJB/avTtdQsXGCDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:13.670820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07376","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:209580b25dffbbbcb270601030219aa3323c17a3f9d3b7b68a7817463566a8af","sha256:132c72071e9ef2ce7a4083680b34476f9f0cd9d2aeae9e41558b9532d881889f"],"state_sha256":"b14bf984458d9ed192aa84f6e1a05c4c7b0819c37fb7522ec232bd22b9ef73ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Dkp7MPy8LHFM10psHm0Ooz6wEF+apHimgg4p5dlUE2ok6MT5hltQIDuo991pR+MEkWietJyebb41lUldD+VDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:39:55.671509Z","bundle_sha256":"60c10663a7337f7ad4d3c6a2c49722380904db5c5faa96710c1874d37ad9bcb2"}}