{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RX2HDA2SREGF2F63AO2SCY3S4M","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":"e7a76dd1ec5ca3417fa8ecfa9d53371d68fa88bda60d728acc8e042a6ec5204b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:26:45Z","title_canon_sha256":"812120b480823a93ff2c8952ab06519ed741f7f8459ff7c51a41e2245c9e13db"},"schema_version":"1.0","source":{"id":"2605.31222","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31222","created_at":"2026-06-01T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31222v1","created_at":"2026-06-01T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31222","created_at":"2026-06-01T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"RX2HDA2SREGF","created_at":"2026-06-01T01:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"RX2HDA2SREGF2F63","created_at":"2026-06-01T01:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"RX2HDA2S","created_at":"2026-06-01T01:04:04Z"}],"graph_snapshots":[{"event_id":"sha256:ee5a4efe043ffa4bfb948bb0a9b308c0865cd0007f4dc495d0f60c150a8f73c9","target":"graph","created_at":"2026-06-01T01:04:04Z","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/2605.31222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional reinforcement learning (DRL) models the full return distribution rather than expectations, but extending it to multivariate settings remains challenging. Many common metrics do not naturally generalize beyond one dimension or lose computational tractability, and the multivariate case introduces additional difficulties such as general matrix discounting, for which no contraction results are available. We introduce Sliced Distributional Reinforcement Learning (SDRL), which lifts tractable one-dimensional divergences to multivariate return distributions via projections. We prove Be","authors_text":"Baptiste Debes, Tinne Tuytelaars","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:26:45Z","title":"Multivariate Distributional Reinforcement Learning Using Sliced Divergences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31222","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":"sha256:65fcc79f2d0e8003d8f0cd066823e99750e1c68f75387fe0aa6d104125dc899c","target":"record","created_at":"2026-06-01T01:04:04Z","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":"e7a76dd1ec5ca3417fa8ecfa9d53371d68fa88bda60d728acc8e042a6ec5204b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:26:45Z","title_canon_sha256":"812120b480823a93ff2c8952ab06519ed741f7f8459ff7c51a41e2245c9e13db"},"schema_version":"1.0","source":{"id":"2605.31222","kind":"arxiv","version":1}},"canonical_sha256":"8df4718352890c5d17db03b5216372e32a1ebf2cce8a072fdd1ac6c8203460eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8df4718352890c5d17db03b5216372e32a1ebf2cce8a072fdd1ac6c8203460eb","first_computed_at":"2026-06-01T01:04:04.685718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:04.685718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1KzO0J0XsbZA16Vm9jg1baR/Z6Ei0on0Wmfdj5fO/mWJrh4XI11M2T+sMk2La4sgRhwn8yHcK79exRAu85RBQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:04.686390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31222","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65fcc79f2d0e8003d8f0cd066823e99750e1c68f75387fe0aa6d104125dc899c","sha256:ee5a4efe043ffa4bfb948bb0a9b308c0865cd0007f4dc495d0f60c150a8f73c9"],"state_sha256":"8e2d3b0b5700e1d95f4f7c38e0ce7363a007213e48ba09537e498ded02967513"}