{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NYWS5UNVLVWAKL73CBC2L4DVNK","short_pith_number":"pith:NYWS5UNV","canonical_record":{"source":{"id":"2102.00966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T16:47:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd47c69abcf1c80fafc0bbc2d50fc89e31ee5e5b33231a202607874d596f1779","abstract_canon_sha256":"9e78c6e19b33a89098d1fb58420c138979cac809f1fd23a989e4da3fe954bfb9"},"schema_version":"1.0"},"canonical_sha256":"6e2d2ed1b55d6c052ffb1045a5f0756aacce42913962e6a10af8e15b7c6ff66a","source":{"kind":"arxiv","id":"2102.00966","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.00966","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2102.00966v2","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00966","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"NYWS5UNVLVWA","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"NYWS5UNVLVWAKL73","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"NYWS5UNV","created_at":"2026-07-05T02:11:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NYWS5UNVLVWAKL73CBC2L4DVNK","target":"record","payload":{"canonical_record":{"source":{"id":"2102.00966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T16:47:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd47c69abcf1c80fafc0bbc2d50fc89e31ee5e5b33231a202607874d596f1779","abstract_canon_sha256":"9e78c6e19b33a89098d1fb58420c138979cac809f1fd23a989e4da3fe954bfb9"},"schema_version":"1.0"},"canonical_sha256":"6e2d2ed1b55d6c052ffb1045a5f0756aacce42913962e6a10af8e15b7c6ff66a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:26.693471Z","signature_b64":"Y4XthciczEnNwqaEk0JXr9t5dmHY5S2MMySBL9pN3npjRNMm1mfkR2Co0L4YS2EWSAfCNo0CG+YJTn2K/lRxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e2d2ed1b55d6c052ffb1045a5f0756aacce42913962e6a10af8e15b7c6ff66a","last_reissued_at":"2026-07-05T02:11:26.693072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:26.693072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.00966","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":"2026-07-05T02:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BdN0eK5GnXzgfKN+pu75ubD42DVGK+VuvRCORDfAlKvbBbqRmmJmTxgw0gI1h9z0ELvYPXIUOxCPIF1KxThxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:40:56.522992Z"},"content_sha256":"d347500ecedd05c4ca206700f5897f96286ff62d2f0bc411638fa39e21285c41","schema_version":"1.0","event_id":"sha256:d347500ecedd05c4ca206700f5897f96286ff62d2f0bc411638fa39e21285c41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NYWS5UNVLVWAKL73CBC2L4DVNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Mathieu Reymond, Patrick Mannion","submitted_at":"2021-02-01T16:47:39Z","abstract_excerpt":"In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from the single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. When making a decision, just the expected return -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Our key insight is that we should use the distribution over expected future"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00966","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/2102.00966/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":"2026-07-05T02:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5G99nLANqYYChHhIB0colqrTLuVJ2G3aeVi7krem0PyBxdOcjIxaxWrEaLi+qGmf2I6mlksFmj/4lv5G2QDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:40:56.523381Z"},"content_sha256":"ce4c85342a94ac2d43c45f737a98afb65cc5513627436abf331c09e693213339","schema_version":"1.0","event_id":"sha256:ce4c85342a94ac2d43c45f737a98afb65cc5513627436abf331c09e693213339"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYWS5UNVLVWAKL73CBC2L4DVNK/bundle.json","state_url":"https://pith.science/pith/NYWS5UNVLVWAKL73CBC2L4DVNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYWS5UNVLVWAKL73CBC2L4DVNK/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":"2026-07-07T11:40:56Z","links":{"resolver":"https://pith.science/pith/NYWS5UNVLVWAKL73CBC2L4DVNK","bundle":"https://pith.science/pith/NYWS5UNVLVWAKL73CBC2L4DVNK/bundle.json","state":"https://pith.science/pith/NYWS5UNVLVWAKL73CBC2L4DVNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYWS5UNVLVWAKL73CBC2L4DVNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NYWS5UNVLVWAKL73CBC2L4DVNK","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":"9e78c6e19b33a89098d1fb58420c138979cac809f1fd23a989e4da3fe954bfb9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T16:47:39Z","title_canon_sha256":"bd47c69abcf1c80fafc0bbc2d50fc89e31ee5e5b33231a202607874d596f1779"},"schema_version":"1.0","source":{"id":"2102.00966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.00966","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2102.00966v2","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00966","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"NYWS5UNVLVWA","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"NYWS5UNVLVWAKL73","created_at":"2026-07-05T02:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"NYWS5UNV","created_at":"2026-07-05T02:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:ce4c85342a94ac2d43c45f737a98afb65cc5513627436abf331c09e693213339","target":"graph","created_at":"2026-07-05T02:11:26Z","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/2102.00966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from the single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. When making a decision, just the expected return -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Our key insight is that we should use the distribution over expected future","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Mathieu Reymond, Patrick Mannion","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T16:47:39Z","title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00966","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:d347500ecedd05c4ca206700f5897f96286ff62d2f0bc411638fa39e21285c41","target":"record","created_at":"2026-07-05T02:11:26Z","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":"9e78c6e19b33a89098d1fb58420c138979cac809f1fd23a989e4da3fe954bfb9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-01T16:47:39Z","title_canon_sha256":"bd47c69abcf1c80fafc0bbc2d50fc89e31ee5e5b33231a202607874d596f1779"},"schema_version":"1.0","source":{"id":"2102.00966","kind":"arxiv","version":2}},"canonical_sha256":"6e2d2ed1b55d6c052ffb1045a5f0756aacce42913962e6a10af8e15b7c6ff66a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e2d2ed1b55d6c052ffb1045a5f0756aacce42913962e6a10af8e15b7c6ff66a","first_computed_at":"2026-07-05T02:11:26.693072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:11:26.693072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y4XthciczEnNwqaEk0JXr9t5dmHY5S2MMySBL9pN3npjRNMm1mfkR2Co0L4YS2EWSAfCNo0CG+YJTn2K/lRxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:11:26.693471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.00966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d347500ecedd05c4ca206700f5897f96286ff62d2f0bc411638fa39e21285c41","sha256:ce4c85342a94ac2d43c45f737a98afb65cc5513627436abf331c09e693213339"],"state_sha256":"7ab1f67263512b73886bf2c369c5b32c1a7f0c412fd29e248e87f6ade7c2f2e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UmQ79AVwqZOmxWPULosTwJ9uWMDlKesUXhFZ13FP4at8M39pVpzDiKNv1lPyQgxe7+K5MRs2D7PEYeD7MZMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:40:56.525505Z","bundle_sha256":"00d27a53197c4fead185d13a8381db724791a57e6c7a5b0f01ecdd6edd525c60"}}