{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F3CU3RYGE3DX3XJS5NT55LUBWD","short_pith_number":"pith:F3CU3RYG","schema_version":"1.0","canonical_sha256":"2ec54dc70626c77ddd32eb67deae81b0d8ab958fc0349db475d1178847dfd9d0","source":{"kind":"arxiv","id":"2607.01741","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.01741","created_at":"2026-07-03T01:17:28.275732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01741v1","created_at":"2026-07-03T01:17:28.275732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01741","created_at":"2026-07-03T01:17:28.275732+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3CU3RYGE3DX","created_at":"2026-07-03T01:17:28.275732+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3CU3RYGE3DX3XJS","created_at":"2026-07-03T01:17:28.275732+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3CU3RYG","created_at":"2026-07-03T01:17:28.275732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD","json":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD.json","graph_json":"https://pith.science/api/pith-number/F3CU3RYGE3DX3XJS5NT55LUBWD/graph.json","events_json":"https://pith.science/api/pith-number/F3CU3RYGE3DX3XJS5NT55LUBWD/events.json","paper":"https://pith.science/paper/F3CU3RYG"},"agent_actions":{"view_html":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD","download_json":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD.json","view_paper":"https://pith.science/paper/F3CU3RYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01741&json=true","fetch_graph":"https://pith.science/api/pith-number/F3CU3RYGE3DX3XJS5NT55LUBWD/graph.json","fetch_events":"https://pith.science/api/pith-number/F3CU3RYGE3DX3XJS5NT55LUBWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/action/storage_attestation","attest_author":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/action/author_attestation","sign_citation":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/action/citation_signature","submit_replication":"https://pith.science/pith/F3CU3RYGE3DX3XJS5NT55LUBWD/action/replication_record"}},"created_at":"2026-07-03T01:17:28.275732+00:00","updated_at":"2026-07-03T01:17:28.275732+00:00"}