{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:23YGPHAVLXJK4EAIRVIAKQ7Y55","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":"e41cacd6906f4832914a5cd3985d33f4d45e7a8b24e9fef80f4bb3e0f438e64f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T14:16:04Z","title_canon_sha256":"ace92ed268b30c88b85343cab6ffbcc2067adbac197675e14c327307f3fe4050"},"schema_version":"1.0","source":{"id":"2310.07518","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07518","created_at":"2026-07-05T08:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07518v2","created_at":"2026-07-05T08:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07518","created_at":"2026-07-05T08:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"23YGPHAVLXJK","created_at":"2026-07-05T08:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"23YGPHAVLXJK4EAI","created_at":"2026-07-05T08:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"23YGPHAV","created_at":"2026-07-05T08:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:df273b59c2f05f10d110830d5eb289da324d10710d2146a58dccc53eb041541a","target":"graph","created_at":"2026-07-05T08:05:03Z","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/2310.07518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Posterior sampling allows exploitation of prior knowledge on the environment's transition dynamics to improve the sample efficiency of reinforcement learning. The prior is typically specified as a class of parametric distributions, the design of which can be cumbersome in practice, often resulting in the choice of uninformative priors. In this work, we propose a novel posterior sampling approach in which the prior is given as a (partial) causal graph over the environment's variables. The latter is often more natural to design, such as listing known causal dependencies between biometric feature","authors_text":"Alexander Marx, Giorgia Ramponi, Marcello Restelli, Mirco Mutti, Riccardo De Santi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T14:16:04Z","title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07518","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":"sha256:9ee526b3dbd85308747278e34b53f368e6415be13460964bef47ea3636fd9742","target":"record","created_at":"2026-07-05T08:05:03Z","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":"e41cacd6906f4832914a5cd3985d33f4d45e7a8b24e9fef80f4bb3e0f438e64f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T14:16:04Z","title_canon_sha256":"ace92ed268b30c88b85343cab6ffbcc2067adbac197675e14c327307f3fe4050"},"schema_version":"1.0","source":{"id":"2310.07518","kind":"arxiv","version":2}},"canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","first_computed_at":"2026-07-05T08:05:03.705982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:03.705982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nJeA1MCCg2ZC/zAyyud7fywr3zWrkHNcngFTz9btOX4wH7L2/R6r2MMbjs2d+0rAWyORIDMvNP3t3Ta0YDMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:03.706468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07518","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ee526b3dbd85308747278e34b53f368e6415be13460964bef47ea3636fd9742","sha256:df273b59c2f05f10d110830d5eb289da324d10710d2146a58dccc53eb041541a"],"state_sha256":"19a15a87cc6e10bb821bcae227ffd8ec5a02d0f0d6cba7ece2dec00d45526566"}