{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F3CU3RYGE3DX3XJS5NT55LUBWD","short_pith_number":"pith:F3CU3RYG","canonical_record":{"source":{"id":"2607.01741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-02T05:54:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3ac74984c37289544e66b1ad626fac3993373ea37363deca183c5fee869d786e","abstract_canon_sha256":"a62d605f9e1020d0b9bd5095ca9a63583466cf05262f4daf6bd2e01262917acb"},"schema_version":"1.0"},"canonical_sha256":"2ec54dc70626c77ddd32eb67deae81b0d8ab958fc0349db475d1178847dfd9d0","source":{"kind":"arxiv","id":"2607.01741","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01741","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01741v1","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01741","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"F3CU3RYGE3DX","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"pith_short_16","alias_value":"F3CU3RYGE3DX3XJS","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"pith_short_8","alias_value":"F3CU3RYG","created_at":"2026-07-03T01:17:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F3CU3RYGE3DX3XJS5NT55LUBWD","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-02T05:54:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3ac74984c37289544e66b1ad626fac3993373ea37363deca183c5fee869d786e","abstract_canon_sha256":"a62d605f9e1020d0b9bd5095ca9a63583466cf05262f4daf6bd2e01262917acb"},"schema_version":"1.0"},"canonical_sha256":"2ec54dc70626c77ddd32eb67deae81b0d8ab958fc0349db475d1178847dfd9d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:28.276064Z","signature_b64":"XVi4gD/0QCErep1kIWsEdyQPHLpDicU8LvkN7Q+fuB3pEygHhrpbj1kjZC2vwJpRsogmPt0E1uaiGg+w/DqNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec54dc70626c77ddd32eb67deae81b0d8ab958fc0349db475d1178847dfd9d0","last_reissued_at":"2026-07-03T01:17:28.275680Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:28.275680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01741","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":"2026-07-03T01:17:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NnYstAuIM7vrdbqf1oWxn6qpsB3w+KUeTjQDjs6tcjQ6CsQQ1gwdnZilgQ/AhozZz3/8g1fftqOz0hY/8tgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:54:20.652771Z"},"content_sha256":"17caa92afc9612861749de2cc48c81d8437744c3d5b487b5e3562a28f747a7d7","schema_version":"1.0","event_id":"sha256:17caa92afc9612861749de2cc48c81d8437744c3d5b487b5e3562a28f747a7d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F3CU3RYGE3DX3XJS5NT55LUBWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Full Bayesian Reinforcement Learning via LF-IBIS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Cecilia Viscardi, Michela Baccini, Stefano Masini","submitted_at":"2026-07-02T05:54:01Z","abstract_excerpt":"Reinforcement Learning (RL) is a sequential decision-making framework in which an agent learns optimal policies through interaction with an environment by maximizing cumulative rewards. Among RL methods, Bayesian Reinforcement Learning (BRL) addresses common practical challenges related to data scarcity by leveraging prior knowledge about the environment and sequential belief updates. However, most BRL approaches require an explicit likelihood function, which is frequently inaccessible or intractable in real-world settings.\n  We propose Likelihood-Free Iterated Batch Importance Sampling (LF-IB"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01741","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/2607.01741/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":"2026-07-03T01:17:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9MM3arPDlgqH3XqlT/UXJflIfzXoRHTHnfZ+smOWEXVsnNNo9Q6h5AFBJ8/CGZ35l4iQGqBvpam1vzgjTrTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:54:20.653147Z"},"content_sha256":"8bc49ae9d66c2b2d149141f0e9a3a23fc0662f58e37388c7b82a7f249c75786b","schema_version":"1.0","event_id":"sha256:8bc49ae9d66c2b2d149141f0e9a3a23fc0662f58e37388c7b82a7f249c75786b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/bundle.json","state_url":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/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":"2026-07-06T20:54:20Z","links":{"resolver":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD","bundle":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/bundle.json","state":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F3CU3RYGE3DX3XJS5NT55LUBWD","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":"a62d605f9e1020d0b9bd5095ca9a63583466cf05262f4daf6bd2e01262917acb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-02T05:54:01Z","title_canon_sha256":"3ac74984c37289544e66b1ad626fac3993373ea37363deca183c5fee869d786e"},"schema_version":"1.0","source":{"id":"2607.01741","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01741","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01741v1","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01741","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"F3CU3RYGE3DX","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"pith_short_16","alias_value":"F3CU3RYGE3DX3XJS","created_at":"2026-07-03T01:17:28Z"},{"alias_kind":"pith_short_8","alias_value":"F3CU3RYG","created_at":"2026-07-03T01:17:28Z"}],"graph_snapshots":[{"event_id":"sha256:8bc49ae9d66c2b2d149141f0e9a3a23fc0662f58e37388c7b82a7f249c75786b","target":"graph","created_at":"2026-07-03T01:17:28Z","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/2607.01741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is a sequential decision-making framework in which an agent learns optimal policies through interaction with an environment by maximizing cumulative rewards. Among RL methods, Bayesian Reinforcement Learning (BRL) addresses common practical challenges related to data scarcity by leveraging prior knowledge about the environment and sequential belief updates. However, most BRL approaches require an explicit likelihood function, which is frequently inaccessible or intractable in real-world settings.\n  We propose Likelihood-Free Iterated Batch Importance Sampling (LF-IB","authors_text":"Cecilia Viscardi, Michela Baccini, Stefano Masini","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-02T05:54:01Z","title":"Full Bayesian Reinforcement Learning via LF-IBIS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01741","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":"sha256:17caa92afc9612861749de2cc48c81d8437744c3d5b487b5e3562a28f747a7d7","target":"record","created_at":"2026-07-03T01:17:28Z","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":"a62d605f9e1020d0b9bd5095ca9a63583466cf05262f4daf6bd2e01262917acb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-02T05:54:01Z","title_canon_sha256":"3ac74984c37289544e66b1ad626fac3993373ea37363deca183c5fee869d786e"},"schema_version":"1.0","source":{"id":"2607.01741","kind":"arxiv","version":1}},"canonical_sha256":"2ec54dc70626c77ddd32eb67deae81b0d8ab958fc0349db475d1178847dfd9d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ec54dc70626c77ddd32eb67deae81b0d8ab958fc0349db475d1178847dfd9d0","first_computed_at":"2026-07-03T01:17:28.275680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:28.275680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XVi4gD/0QCErep1kIWsEdyQPHLpDicU8LvkN7Q+fuB3pEygHhrpbj1kjZC2vwJpRsogmPt0E1uaiGg+w/DqNAA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:28.276064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01741","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17caa92afc9612861749de2cc48c81d8437744c3d5b487b5e3562a28f747a7d7","sha256:8bc49ae9d66c2b2d149141f0e9a3a23fc0662f58e37388c7b82a7f249c75786b"],"state_sha256":"fa3801bed59654a09c142f4bdd757e2c5dece0a08aca7c376000592f60c2f01a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NG5Z+dyy9cHsd6CtrEM8ljU+1z8zeUVzH0wDhY20RRZvfKuRq68mtnZspTRe2nop5oZ5v8h4x55bC+RfVOr8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:54:20.655295Z","bundle_sha256":"1f0384fe196f6ecf7b7e85b9cbb9799d8563373ba63b8558e23e1de1138e12f1"}}