{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VYNVNGKJA6NICG6NTSFRH5SSRY","short_pith_number":"pith:VYNVNGKJ","canonical_record":{"source":{"id":"2401.10240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-11-28T17:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"de089ebba6b5f38f18a5b3daa49193e676a1ccf3affafe5fdbfa6b41017d1d81","abstract_canon_sha256":"e4086b58c27fd561a4c179e26b2c28bd71fb5e28105531c43f5d76f2f59866fa"},"schema_version":"1.0"},"canonical_sha256":"ae1b569949079a811bcd9c8b13f6528e286a089ba33cf178bc8f55572501d08a","source":{"kind":"arxiv","id":"2401.10240","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10240","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10240v2","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10240","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"VYNVNGKJA6NI","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"VYNVNGKJA6NICG6N","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"VYNVNGKJ","created_at":"2026-07-05T08:00:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VYNVNGKJA6NICG6NTSFRH5SSRY","target":"record","payload":{"canonical_record":{"source":{"id":"2401.10240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-11-28T17:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"de089ebba6b5f38f18a5b3daa49193e676a1ccf3affafe5fdbfa6b41017d1d81","abstract_canon_sha256":"e4086b58c27fd561a4c179e26b2c28bd71fb5e28105531c43f5d76f2f59866fa"},"schema_version":"1.0"},"canonical_sha256":"ae1b569949079a811bcd9c8b13f6528e286a089ba33cf178bc8f55572501d08a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:00.327593Z","signature_b64":"hEoVTPFQfPu/roJeDi2rZ2WVYTWUbmA6VRhk96ZE0I42mBpGqJ0DsGjZ7441Mot1Nnk6mjLjdu5W6sD5glbnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae1b569949079a811bcd9c8b13f6528e286a089ba33cf178bc8f55572501d08a","last_reissued_at":"2026-07-05T08:00:00.327074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:00.327074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.10240","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":"2026-07-05T08:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6W/cI8Uunpvn8uHIp++lUie1oU9KPAiSgbht5XqSFxaj6fUtE5CO/WY9hq47v2YCcg7b3QGrrxQqSc/HdeAYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:45:29.072995Z"},"content_sha256":"2f2215bcf25e4c74bb317ed365162c3c6d97ba1e1a3497108b34ec4a69f84fd8","schema_version":"1.0","event_id":"sha256:2f2215bcf25e4c74bb317ed365162c3c6d97ba1e1a3497108b34ec4a69f84fd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VYNVNGKJA6NICG6NTSFRH5SSRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Evaluation in Distributional LQR (Extended Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Alessandro Abate, Karl H. Johansson, Michael M. Zavlanos, Siyi Wang, Yulong Gao, Zifan Wang","submitted_at":"2023-11-28T17:15:07Z","abstract_excerpt":"Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard reinforcement learning. Meanwhile, a challenge in DRL is that the policy evaluation typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for the special class of DRL problems that rely on a discounted linear quadratic regulator (LQR), which we call \\emph{distributional LQR}. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10240","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/2401.10240/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":"2026-07-05T08:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zx5/Nz/RmemZbfA6f5nrDaNAy72ddtokldmvARlubNYNqF1q1TXkVbXf5ar0gk6yJvR3mfhNroyrNnXiBxpUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:45:29.073491Z"},"content_sha256":"8c9c74b2ce6e5c37d4b1d6392cb56433176bc1507463c5605c9b0d30ac730685","schema_version":"1.0","event_id":"sha256:8c9c74b2ce6e5c37d4b1d6392cb56433176bc1507463c5605c9b0d30ac730685"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYNVNGKJA6NICG6NTSFRH5SSRY/bundle.json","state_url":"https://pith.science/pith/VYNVNGKJA6NICG6NTSFRH5SSRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYNVNGKJA6NICG6NTSFRH5SSRY/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":"2026-08-07T03:45:29Z","links":{"resolver":"https://pith.science/pith/VYNVNGKJA6NICG6NTSFRH5SSRY","bundle":"https://pith.science/pith/VYNVNGKJA6NICG6NTSFRH5SSRY/bundle.json","state":"https://pith.science/pith/VYNVNGKJA6NICG6NTSFRH5SSRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYNVNGKJA6NICG6NTSFRH5SSRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VYNVNGKJA6NICG6NTSFRH5SSRY","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":"e4086b58c27fd561a4c179e26b2c28bd71fb5e28105531c43f5d76f2f59866fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-11-28T17:15:07Z","title_canon_sha256":"de089ebba6b5f38f18a5b3daa49193e676a1ccf3affafe5fdbfa6b41017d1d81"},"schema_version":"1.0","source":{"id":"2401.10240","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10240","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10240v2","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10240","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"VYNVNGKJA6NI","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"VYNVNGKJA6NICG6N","created_at":"2026-07-05T08:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"VYNVNGKJ","created_at":"2026-07-05T08:00:00Z"}],"graph_snapshots":[{"event_id":"sha256:8c9c74b2ce6e5c37d4b1d6392cb56433176bc1507463c5605c9b0d30ac730685","target":"graph","created_at":"2026-07-05T08:00:00Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.10240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard reinforcement learning. Meanwhile, a challenge in DRL is that the policy evaluation typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for the special class of DRL problems that rely on a discounted linear quadratic regulator (LQR), which we call \\emph{distributional LQR}. S","authors_text":"Alessandro Abate, Karl H. Johansson, Michael M. Zavlanos, Siyi Wang, Yulong Gao, Zifan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-11-28T17:15:07Z","title":"Policy Evaluation in Distributional LQR (Extended Version)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10240","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":"sha256:2f2215bcf25e4c74bb317ed365162c3c6d97ba1e1a3497108b34ec4a69f84fd8","target":"record","created_at":"2026-07-05T08:00:00Z","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":"e4086b58c27fd561a4c179e26b2c28bd71fb5e28105531c43f5d76f2f59866fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-11-28T17:15:07Z","title_canon_sha256":"de089ebba6b5f38f18a5b3daa49193e676a1ccf3affafe5fdbfa6b41017d1d81"},"schema_version":"1.0","source":{"id":"2401.10240","kind":"arxiv","version":2}},"canonical_sha256":"ae1b569949079a811bcd9c8b13f6528e286a089ba33cf178bc8f55572501d08a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae1b569949079a811bcd9c8b13f6528e286a089ba33cf178bc8f55572501d08a","first_computed_at":"2026-07-05T08:00:00.327074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:00.327074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hEoVTPFQfPu/roJeDi2rZ2WVYTWUbmA6VRhk96ZE0I42mBpGqJ0DsGjZ7441Mot1Nnk6mjLjdu5W6sD5glbnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:00.327593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10240","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f2215bcf25e4c74bb317ed365162c3c6d97ba1e1a3497108b34ec4a69f84fd8","sha256:8c9c74b2ce6e5c37d4b1d6392cb56433176bc1507463c5605c9b0d30ac730685"],"state_sha256":"0fd8162319d8910f820ea113ea9fc69ffbd186fc73106791080432819faca489"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"04tVWFubI2otQLI/HCdrpz9JFIOsayva64ioFjMSZTpZXZZk5UFXBCegaypTbFajZ8WuccJXuedBDwR/kvjvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:45:29.077602Z","bundle_sha256":"faf34b0d525717e33f648b1ad2b030fdddebe5b8fa1194b4e4586915481796c4"}}