{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:23YGPHAVLXJK4EAIRVIAKQ7Y55","short_pith_number":"pith:23YGPHAV","canonical_record":{"source":{"id":"2310.07518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T14:16:04Z","cross_cats_sorted":[],"title_canon_sha256":"ace92ed268b30c88b85343cab6ffbcc2067adbac197675e14c327307f3fe4050","abstract_canon_sha256":"e41cacd6906f4832914a5cd3985d33f4d45e7a8b24e9fef80f4bb3e0f438e64f"},"schema_version":"1.0"},"canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","source":{"kind":"arxiv","id":"2310.07518","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:23YGPHAVLXJK4EAIRVIAKQ7Y55","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T14:16:04Z","cross_cats_sorted":[],"title_canon_sha256":"ace92ed268b30c88b85343cab6ffbcc2067adbac197675e14c327307f3fe4050","abstract_canon_sha256":"e41cacd6906f4832914a5cd3985d33f4d45e7a8b24e9fef80f4bb3e0f438e64f"},"schema_version":"1.0"},"canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:03.706468Z","signature_b64":"8nJeA1MCCg2ZC/zAyyud7fywr3zWrkHNcngFTz9btOX4wH7L2/R6r2MMbjs2d+0rAWyORIDMvNP3t3Ta0YDMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","last_reissued_at":"2026-07-05T08:05:03.705982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:03.705982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07518","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":"2026-07-05T08:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xRw1MCWts9PNVxjW5df59Tvx6URjyRJ5xNR518Dvlh6Yp2rqn4S/za/1YagKfH7TFTw8XmhgV9gZjvogGgcQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:28.717178Z"},"content_sha256":"9ee526b3dbd85308747278e34b53f368e6415be13460964bef47ea3636fd9742","schema_version":"1.0","event_id":"sha256:9ee526b3dbd85308747278e34b53f368e6415be13460964bef47ea3636fd9742"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:23YGPHAVLXJK4EAIRVIAKQ7Y55","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Marx, Giorgia Ramponi, Marcello Restelli, Mirco Mutti, Riccardo De Santi","submitted_at":"2023-10-11T14:16:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07518","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/2310.07518/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":"2026-07-05T08:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVdhC47kPc8JE1x/unzMlF7eDmnKrLcO/ryjocHGwb5+ZX6juMocPBtAeZ+OyIqm1uRaRV2w++cA26buTza2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:28.717693Z"},"content_sha256":"df273b59c2f05f10d110830d5eb289da324d10710d2146a58dccc53eb041541a","schema_version":"1.0","event_id":"sha256:df273b59c2f05f10d110830d5eb289da324d10710d2146a58dccc53eb041541a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/bundle.json","state_url":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/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":"2026-08-08T12:59:28Z","links":{"resolver":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55","bundle":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/bundle.json","state":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCQ4eYg5oSxJa/lRQ/0KfhEPM26JvIx0/mvIwjaK6dW/1khZYPPopx8C7qyPgWzg5gnsWUtgzeY51RocbvErBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:59:28.722529Z","bundle_sha256":"a484a6fdd4ec4778e1a064b8206a5ff890067ade4262d04e9ff2a3bbc96a4e20"}}