{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LXHGWZODQPQ7PX3YW3TLQZHLL6","short_pith_number":"pith:LXHGWZOD","canonical_record":{"source":{"id":"2408.07660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T16:44:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb938693d0a3d6bdd51ee8631dd52c46b6456f4039bed55fee35099b788a8316","abstract_canon_sha256":"59cacb94ea61f1a8de43ffcabbd99490e585e98260e3481fce43060089c2385d"},"schema_version":"1.0"},"canonical_sha256":"5dce6b65c383e1f7df78b6e6b864eb5fb07c323a07fa7e6962746d05c8460f09","source":{"kind":"arxiv","id":"2408.07660","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07660","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07660v1","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07660","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"LXHGWZODQPQ7","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"LXHGWZODQPQ7PX3Y","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"LXHGWZOD","created_at":"2026-07-05T08:55:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LXHGWZODQPQ7PX3YW3TLQZHLL6","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T16:44:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb938693d0a3d6bdd51ee8631dd52c46b6456f4039bed55fee35099b788a8316","abstract_canon_sha256":"59cacb94ea61f1a8de43ffcabbd99490e585e98260e3481fce43060089c2385d"},"schema_version":"1.0"},"canonical_sha256":"5dce6b65c383e1f7df78b6e6b864eb5fb07c323a07fa7e6962746d05c8460f09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:28.451235Z","signature_b64":"jsGLFEXNA+cNBTpq+/yDFdMqOxd154t6pwZYWF9arraBoyqni8lzKase79W36S9vP4kSiiOz0wlImkj9AqkYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dce6b65c383e1f7df78b6e6b864eb5fb07c323a07fa7e6962746d05c8460f09","last_reissued_at":"2026-07-05T08:55:28.450826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:28.450826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07660","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":"2026-07-05T08:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zjcfHq2WapAmfnS2+izF9hjmaLHz/hAnZm0kgU19UpOYoO0XYSq9KsFqxhiVZcRCkw/gKeh0PRQmImqGv3jqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:36:25.833684Z"},"content_sha256":"7a283b7e086a17a7f7344d8504018f1eec51ecc44ab653def3b892535c4830b1","schema_version":"1.0","event_id":"sha256:7a283b7e086a17a7f7344d8504018f1eec51ecc44ab653def3b892535c4830b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LXHGWZODQPQ7PX3YW3TLQZHLL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Reinforcement Learning with High Dimensional Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dong Neuck Lee, Michael R. Kosorok","submitted_at":"2024-08-14T16:44:56Z","abstract_excerpt":"Conventional off-policy reinforcement learning (RL) focuses on maximizing the expected return of scalar rewards. Distributional RL (DRL), in contrast, studies the distribution of returns with the distributional Bellman operator in a Euclidean space, leading to highly flexible choices for utility. This paper establishes robust theoretical foundations for DRL. We prove the contraction property of the Bellman operator even when the reward space is an infinite-dimensional separable Banach space. Furthermore, we demonstrate that the behavior of high- or infinite-dimensional returns can be effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07660","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/2408.07660/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":"2026-07-05T08:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OULoo3Jd5WtStn6Gccr0eL/W1pOcJN/utLk3z9OMk86pJ4Zakyd2aogJbSImR/XFd5AgOcw2cs9bSLUJezN2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:36:25.834695Z"},"content_sha256":"cec8f47b5d6082b31de661c3da1fa3332486b89703ef960551f8929761cb4dfd","schema_version":"1.0","event_id":"sha256:cec8f47b5d6082b31de661c3da1fa3332486b89703ef960551f8929761cb4dfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6/bundle.json","state_url":"https://pith.science/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6/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":"2026-08-10T07:36:25Z","links":{"resolver":"https://pith.science/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6","bundle":"https://pith.science/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6/bundle.json","state":"https://pith.science/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LXHGWZODQPQ7PX3YW3TLQZHLL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXHGWZODQPQ7PX3YW3TLQZHLL6","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":"59cacb94ea61f1a8de43ffcabbd99490e585e98260e3481fce43060089c2385d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T16:44:56Z","title_canon_sha256":"bb938693d0a3d6bdd51ee8631dd52c46b6456f4039bed55fee35099b788a8316"},"schema_version":"1.0","source":{"id":"2408.07660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07660","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07660v1","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07660","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"LXHGWZODQPQ7","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"LXHGWZODQPQ7PX3Y","created_at":"2026-07-05T08:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"LXHGWZOD","created_at":"2026-07-05T08:55:28Z"}],"graph_snapshots":[{"event_id":"sha256:cec8f47b5d6082b31de661c3da1fa3332486b89703ef960551f8929761cb4dfd","target":"graph","created_at":"2026-07-05T08:55:28Z","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/2408.07660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional off-policy reinforcement learning (RL) focuses on maximizing the expected return of scalar rewards. Distributional RL (DRL), in contrast, studies the distribution of returns with the distributional Bellman operator in a Euclidean space, leading to highly flexible choices for utility. This paper establishes robust theoretical foundations for DRL. We prove the contraction property of the Bellman operator even when the reward space is an infinite-dimensional separable Banach space. Furthermore, we demonstrate that the behavior of high- or infinite-dimensional returns can be effective","authors_text":"Dong Neuck Lee, Michael R. Kosorok","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T16:44:56Z","title":"Off-Policy Reinforcement Learning with High Dimensional Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07660","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":"sha256:7a283b7e086a17a7f7344d8504018f1eec51ecc44ab653def3b892535c4830b1","target":"record","created_at":"2026-07-05T08:55:28Z","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":"59cacb94ea61f1a8de43ffcabbd99490e585e98260e3481fce43060089c2385d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T16:44:56Z","title_canon_sha256":"bb938693d0a3d6bdd51ee8631dd52c46b6456f4039bed55fee35099b788a8316"},"schema_version":"1.0","source":{"id":"2408.07660","kind":"arxiv","version":1}},"canonical_sha256":"5dce6b65c383e1f7df78b6e6b864eb5fb07c323a07fa7e6962746d05c8460f09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dce6b65c383e1f7df78b6e6b864eb5fb07c323a07fa7e6962746d05c8460f09","first_computed_at":"2026-07-05T08:55:28.450826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:28.450826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jsGLFEXNA+cNBTpq+/yDFdMqOxd154t6pwZYWF9arraBoyqni8lzKase79W36S9vP4kSiiOz0wlImkj9AqkYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:28.451235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a283b7e086a17a7f7344d8504018f1eec51ecc44ab653def3b892535c4830b1","sha256:cec8f47b5d6082b31de661c3da1fa3332486b89703ef960551f8929761cb4dfd"],"state_sha256":"2fbe2c61c89c7cb06900eb3c91be887c5649d57def308dc57029ef26e387e6dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r7kSNoj5dbuqWz3QEfXsAHNfgOImmQhNI2Z63J7uJQWj55pxXBN2d+UmxyxASSSMt1g6gIPhVl0srqRqe1rdCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:36:25.840269Z","bundle_sha256":"b382b732c0b30a16d1d51eea6cf4e6891bf8486ec36b08cb492261411028777f"}}