{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JSV5FVNR6QVXO46NI5L2CI3HI5","short_pith_number":"pith:JSV5FVNR","canonical_record":{"source":{"id":"2007.04203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T15:44:33Z","cross_cats_sorted":["cs.AI","q-fin.CP","q-fin.PM","stat.ML"],"title_canon_sha256":"9b68cbfbcf067e104c936d4ca86e7244372227f016d204a91900dd65d6c780da","abstract_canon_sha256":"a290a188f5f1fc50b69d900f71a4bea75655e8be1e57fd4dd7ea89b8e7e929d5"},"schema_version":"1.0"},"canonical_sha256":"4cabd2d5b1f42b7773cd4757a1236747487d2db0bb7ade2669fe29895dcdad3b","source":{"kind":"arxiv","id":"2007.04203","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04203","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04203v1","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04203","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"JSV5FVNR6QVX","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"JSV5FVNR6QVXO46N","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"JSV5FVNR","created_at":"2026-07-05T01:17:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JSV5FVNR6QVXO46NI5L2CI3HI5","target":"record","payload":{"canonical_record":{"source":{"id":"2007.04203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T15:44:33Z","cross_cats_sorted":["cs.AI","q-fin.CP","q-fin.PM","stat.ML"],"title_canon_sha256":"9b68cbfbcf067e104c936d4ca86e7244372227f016d204a91900dd65d6c780da","abstract_canon_sha256":"a290a188f5f1fc50b69d900f71a4bea75655e8be1e57fd4dd7ea89b8e7e929d5"},"schema_version":"1.0"},"canonical_sha256":"4cabd2d5b1f42b7773cd4757a1236747487d2db0bb7ade2669fe29895dcdad3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:21.940538Z","signature_b64":"GWtX6oYZ7mKd3Lw81uuJ3U20qc+UnIo4FbAXhIBBwFPB899HuLuBsTajMljwH8piQL4dzDTWFGQwcWKBT+8GDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cabd2d5b1f42b7773cd4757a1236747487d2db0bb7ade2669fe29895dcdad3b","last_reissued_at":"2026-07-05T01:17:21.939993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:21.939993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.04203","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":"2026-07-05T01:17:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0rvHI+kZ2Wc9COUm4ALFPqYKIHF4OJtNtNO5qcwgGxfmyekXBgUD9Gfb3F8TE43vyeGhZLU5BJn/hJenU6sDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:31:12.117270Z"},"content_sha256":"7f3bbf76f81542b0f6aca7069b8b13a1b52b737f415228906dd2e79f71cb9767","schema_version":"1.0","event_id":"sha256:7f3bbf76f81542b0f6aca7069b8b13a1b52b737f415228906dd2e79f71cb9767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JSV5FVNR6QVXO46NI5L2CI3HI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Natural Actor-Critic Algorithm with Downside Risk Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-fin.CP","q-fin.PM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rahul Savani, Thomas Spooner","submitted_at":"2020-07-08T15:44:33Z","abstract_excerpt":"Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also suffers from high variance and decreased sample efficiency compared to temporal-difference methods. In this paper, we study prediction and control with aversion to downside risk which we gauge by the lower partial moment of the return. We introduce a new Bellman equation that upper bounds the lower partial moment, circumventing its non-linearity. We prove tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04203","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/2007.04203/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":"2026-07-05T01:17:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDotbSw1MbogOtyOHgbqHNCICygsKvgpZ6e9agVQsrTT7hxmhvmoO6HikNYTsybul190rELTP7i0m4JSSnQtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:31:12.118002Z"},"content_sha256":"c3dd6def6a5e580dd48ecd72b829872aaeae02098f4f49b8471b2a691b8ab55d","schema_version":"1.0","event_id":"sha256:c3dd6def6a5e580dd48ecd72b829872aaeae02098f4f49b8471b2a691b8ab55d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSV5FVNR6QVXO46NI5L2CI3HI5/bundle.json","state_url":"https://pith.science/pith/JSV5FVNR6QVXO46NI5L2CI3HI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSV5FVNR6QVXO46NI5L2CI3HI5/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":"2026-08-04T18:31:12Z","links":{"resolver":"https://pith.science/pith/JSV5FVNR6QVXO46NI5L2CI3HI5","bundle":"https://pith.science/pith/JSV5FVNR6QVXO46NI5L2CI3HI5/bundle.json","state":"https://pith.science/pith/JSV5FVNR6QVXO46NI5L2CI3HI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSV5FVNR6QVXO46NI5L2CI3HI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JSV5FVNR6QVXO46NI5L2CI3HI5","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":"a290a188f5f1fc50b69d900f71a4bea75655e8be1e57fd4dd7ea89b8e7e929d5","cross_cats_sorted":["cs.AI","q-fin.CP","q-fin.PM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T15:44:33Z","title_canon_sha256":"9b68cbfbcf067e104c936d4ca86e7244372227f016d204a91900dd65d6c780da"},"schema_version":"1.0","source":{"id":"2007.04203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04203","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04203v1","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04203","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"JSV5FVNR6QVX","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"JSV5FVNR6QVXO46N","created_at":"2026-07-05T01:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"JSV5FVNR","created_at":"2026-07-05T01:17:21Z"}],"graph_snapshots":[{"event_id":"sha256:c3dd6def6a5e580dd48ecd72b829872aaeae02098f4f49b8471b2a691b8ab55d","target":"graph","created_at":"2026-07-05T01:17:21Z","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/2007.04203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also suffers from high variance and decreased sample efficiency compared to temporal-difference methods. In this paper, we study prediction and control with aversion to downside risk which we gauge by the lower partial moment of the return. We introduce a new Bellman equation that upper bounds the lower partial moment, circumventing its non-linearity. We prove tha","authors_text":"Rahul Savani, Thomas Spooner","cross_cats":["cs.AI","q-fin.CP","q-fin.PM","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T15:44:33Z","title":"A Natural Actor-Critic Algorithm with Downside Risk Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04203","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":"sha256:7f3bbf76f81542b0f6aca7069b8b13a1b52b737f415228906dd2e79f71cb9767","target":"record","created_at":"2026-07-05T01:17:21Z","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":"a290a188f5f1fc50b69d900f71a4bea75655e8be1e57fd4dd7ea89b8e7e929d5","cross_cats_sorted":["cs.AI","q-fin.CP","q-fin.PM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T15:44:33Z","title_canon_sha256":"9b68cbfbcf067e104c936d4ca86e7244372227f016d204a91900dd65d6c780da"},"schema_version":"1.0","source":{"id":"2007.04203","kind":"arxiv","version":1}},"canonical_sha256":"4cabd2d5b1f42b7773cd4757a1236747487d2db0bb7ade2669fe29895dcdad3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cabd2d5b1f42b7773cd4757a1236747487d2db0bb7ade2669fe29895dcdad3b","first_computed_at":"2026-07-05T01:17:21.939993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:21.939993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GWtX6oYZ7mKd3Lw81uuJ3U20qc+UnIo4FbAXhIBBwFPB899HuLuBsTajMljwH8piQL4dzDTWFGQwcWKBT+8GDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:21.940538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.04203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f3bbf76f81542b0f6aca7069b8b13a1b52b737f415228906dd2e79f71cb9767","sha256:c3dd6def6a5e580dd48ecd72b829872aaeae02098f4f49b8471b2a691b8ab55d"],"state_sha256":"df9254685787991b8741af600dad2b9f246199ad741d3258dced57a0f413ff1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0L1WwcIRjJPgW3g9vZhwDxjw1+e3R3K1yADHcE53gu0qzfze5U5t+LRoDq/uxmlRz9DiWCz2jDT8PM/X7mxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:31:12.124981Z","bundle_sha256":"4c1089eba80a27bfbafb0a78c33b2f3d82d46137200da1b9a02e8ee7d8e57668"}}