{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:WSDIUX5UBGEYDIXEAVBSPFELT3","short_pith_number":"pith:WSDIUX5U","canonical_record":{"source":{"id":"1203.3497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-03-15T11:17:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7b12b15de4194f0cdf6ee564a7fe294301dd4d696f9955627ce464f0e3173c97","abstract_canon_sha256":"14b4694f7000240027746af3675581132572f67242f7948db3fe976adb285ce8"},"schema_version":"1.0"},"canonical_sha256":"b4868a5fb4098981a2e4054327948b9efead08921cb721b2f470d929bf340500","source":{"kind":"arxiv","id":"1203.3497","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1203.3497","created_at":"2026-05-18T04:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"1203.3497v1","created_at":"2026-05-18T04:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.3497","created_at":"2026-05-18T04:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"WSDIUX5UBGEY","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WSDIUX5UBGEYDIXE","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WSDIUX5U","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:WSDIUX5UBGEYDIXEAVBSPFELT3","target":"record","payload":{"canonical_record":{"source":{"id":"1203.3497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-03-15T11:17:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7b12b15de4194f0cdf6ee564a7fe294301dd4d696f9955627ce464f0e3173c97","abstract_canon_sha256":"14b4694f7000240027746af3675581132572f67242f7948db3fe976adb285ce8"},"schema_version":"1.0"},"canonical_sha256":"b4868a5fb4098981a2e4054327948b9efead08921cb721b2f470d929bf340500","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:00:00.222938Z","signature_b64":"C+pvZ7fsQfm4oWycvm1cl15N6pBacY4oho8RjQ+lapXcfS8VgyG2t2PDJYgI92/AOT1gHUU/l4qdnjtRxgOPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4868a5fb4098981a2e4054327948b9efead08921cb721b2f470d929bf340500","last_reissued_at":"2026-05-18T04:00:00.222291Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:00:00.222291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1203.3497","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":"2026-05-18T04:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWOSz6EZalON9A9FqQPfubSrzlhjjsAOM17wjKgZX88fARRFdpuE2pePT2hi23worbX6W1iLIegrnEyuNqpfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:10:23.497877Z"},"content_sha256":"32eba4d9e26c475a358ab8bea0259c480c98d7cf61474dac76334079ff7e065a","schema_version":"1.0","event_id":"sha256:32eba4d9e26c475a358ab8bea0259c480c98d7cf61474dac76334079ff7e065a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:WSDIUX5UBGEYDIXEAVBSPFELT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parametric Return Density Estimation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hirotaka Hachiya, Hisashi Kashima, Masashi Sugiyama, Tetsuro Morimura, Toshiyuki Tanaka","submitted_at":"2012-03-15T11:17:56Z","abstract_excerpt":"Most conventional Reinforcement Learning (RL) algorithms aim to optimize decision-making rules in terms of the expected returns. However, especially for risk management purposes, other risk-sensitive criteria such as the value-at-risk or the expected shortfall are sometimes preferred in real applications. Here, we describe a parametric method for estimating density of the returns, which allows us to handle various criteria in a unified manner. We first extend the Bellman equation for the conditional expected return to cover a conditional probability density of the returns. Then we derive an ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.3497","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":""},"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":"2026-05-18T04:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cPUjkzFPtaDC5JCnlYFMNcU3cf+TtVhMlHXlzteSqqpC070kdBEnHOVJua1M6JitPJOYrnNLspi48/AzEsNmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:10:23.498221Z"},"content_sha256":"efe5af6df792a1e43665653b74e220e27555e0f92c428d2cdd8a75ced7b4cea2","schema_version":"1.0","event_id":"sha256:efe5af6df792a1e43665653b74e220e27555e0f92c428d2cdd8a75ced7b4cea2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSDIUX5UBGEYDIXEAVBSPFELT3/bundle.json","state_url":"https://pith.science/pith/WSDIUX5UBGEYDIXEAVBSPFELT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSDIUX5UBGEYDIXEAVBSPFELT3/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":"2026-06-28T11:10:23Z","links":{"resolver":"https://pith.science/pith/WSDIUX5UBGEYDIXEAVBSPFELT3","bundle":"https://pith.science/pith/WSDIUX5UBGEYDIXEAVBSPFELT3/bundle.json","state":"https://pith.science/pith/WSDIUX5UBGEYDIXEAVBSPFELT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSDIUX5UBGEYDIXEAVBSPFELT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:WSDIUX5UBGEYDIXEAVBSPFELT3","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":"14b4694f7000240027746af3675581132572f67242f7948db3fe976adb285ce8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-03-15T11:17:56Z","title_canon_sha256":"7b12b15de4194f0cdf6ee564a7fe294301dd4d696f9955627ce464f0e3173c97"},"schema_version":"1.0","source":{"id":"1203.3497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1203.3497","created_at":"2026-05-18T04:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"1203.3497v1","created_at":"2026-05-18T04:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.3497","created_at":"2026-05-18T04:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"WSDIUX5UBGEY","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WSDIUX5UBGEYDIXE","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WSDIUX5U","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:efe5af6df792a1e43665653b74e220e27555e0f92c428d2cdd8a75ced7b4cea2","target":"graph","created_at":"2026-05-18T04:00:00Z","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":"Most conventional Reinforcement Learning (RL) algorithms aim to optimize decision-making rules in terms of the expected returns. However, especially for risk management purposes, other risk-sensitive criteria such as the value-at-risk or the expected shortfall are sometimes preferred in real applications. Here, we describe a parametric method for estimating density of the returns, which allows us to handle various criteria in a unified manner. We first extend the Bellman equation for the conditional expected return to cover a conditional probability density of the returns. Then we derive an ex","authors_text":"Hirotaka Hachiya, Hisashi Kashima, Masashi Sugiyama, Tetsuro Morimura, Toshiyuki Tanaka","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-03-15T11:17:56Z","title":"Parametric Return Density Estimation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.3497","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":"sha256:32eba4d9e26c475a358ab8bea0259c480c98d7cf61474dac76334079ff7e065a","target":"record","created_at":"2026-05-18T04:00:00Z","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":"14b4694f7000240027746af3675581132572f67242f7948db3fe976adb285ce8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-03-15T11:17:56Z","title_canon_sha256":"7b12b15de4194f0cdf6ee564a7fe294301dd4d696f9955627ce464f0e3173c97"},"schema_version":"1.0","source":{"id":"1203.3497","kind":"arxiv","version":1}},"canonical_sha256":"b4868a5fb4098981a2e4054327948b9efead08921cb721b2f470d929bf340500","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4868a5fb4098981a2e4054327948b9efead08921cb721b2f470d929bf340500","first_computed_at":"2026-05-18T04:00:00.222291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:00:00.222291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C+pvZ7fsQfm4oWycvm1cl15N6pBacY4oho8RjQ+lapXcfS8VgyG2t2PDJYgI92/AOT1gHUU/l4qdnjtRxgOPDA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:00:00.222938Z","signed_message":"canonical_sha256_bytes"},"source_id":"1203.3497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32eba4d9e26c475a358ab8bea0259c480c98d7cf61474dac76334079ff7e065a","sha256:efe5af6df792a1e43665653b74e220e27555e0f92c428d2cdd8a75ced7b4cea2"],"state_sha256":"1331168484c88748a86dc0621475d077be3ca4f315fba6a202387e965e87c0f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFf/bQjRNRm9U7GuQUre8mKogysnSjNMZz9w72FBNkV9pnor5lgOcl2GP+cKOSIO//BgaG+g5N6fVtGq9D1aAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T11:10:23.500094Z","bundle_sha256":"ed9624c77e46ebdba05bfd90c1eaf6fc8e1716b58df875dd100a54569e58bd44"}}