{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MPVYBK2OO7DDDCPFU3IWNZX7HO","short_pith_number":"pith:MPVYBK2O","schema_version":"1.0","canonical_sha256":"63eb80ab4e77c63189e5a6d166e6ff3b9e8cd55394f1613d7601faff9dc2c7a7","source":{"kind":"arxiv","id":"2510.11711","version":2},"attestation_state":"computed","paper":{"title":"Reinforced sequential Monte Carlo for amortised sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Esmeralda S. Whitammer, Jinkyoo Park, Sanghyeok Choi, Sarthak Mittal, V\\'ictor Elvira","submitted_at":"2025-10-13T17:59:11Z","abstract_excerpt":"This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state a connection between sequential Monte Carlo (SMC) and neural sequential samplers trained by maximum-entropy reinforcement learning (MaxEnt RL), wherein learnt sampling policies and value functions define proposal kernels and twist functions. Exploiting this connection, we introduce an off-policy RL training procedure for the sampler that uses samples from SMC -- using the learnt sampler as a proposal -- as a behaviour policy that better explo"},"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":"2510.11711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:59:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d6908e1d79dd938115ab57da3aec456b93435861af65b40b2e51e735986e6dc3","abstract_canon_sha256":"f087f02fae41fcfefa410aa6f7860cb2ecbe3056d736dc7f07c3ce82c95382cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:28.307081Z","signature_b64":"1bqz1Il5wggsHhNAlCP6Qkv4n6zKoIst3f/nDDEKf3aWxoCV9LKc5AVGD/e7hj6+VC/IBy1PxJv9nWaowlorAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63eb80ab4e77c63189e5a6d166e6ff3b9e8cd55394f1613d7601faff9dc2c7a7","last_reissued_at":"2026-06-01T02:03:28.306213Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:28.306213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced sequential Monte Carlo for amortised sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Esmeralda S. Whitammer, Jinkyoo Park, Sanghyeok Choi, Sarthak Mittal, V\\'ictor Elvira","submitted_at":"2025-10-13T17:59:11Z","abstract_excerpt":"This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state a connection between sequential Monte Carlo (SMC) and neural sequential samplers trained by maximum-entropy reinforcement learning (MaxEnt RL), wherein learnt sampling policies and value functions define proposal kernels and twist functions. Exploiting this connection, we introduce an off-policy RL training procedure for the sampler that uses samples from SMC -- using the learnt sampler as a proposal -- as a behaviour policy that better explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11711","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/2510.11711/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":"2510.11711","created_at":"2026-06-01T02:03:28.306352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.11711v2","created_at":"2026-06-01T02:03:28.306352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11711","created_at":"2026-06-01T02:03:28.306352+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPVYBK2OO7DD","created_at":"2026-06-01T02:03:28.306352+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPVYBK2OO7DDDCPF","created_at":"2026-06-01T02:03:28.306352+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPVYBK2O","created_at":"2026-06-01T02:03:28.306352+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/MPVYBK2OO7DDDCPFU3IWNZX7HO","json":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO.json","graph_json":"https://pith.science/api/pith-number/MPVYBK2OO7DDDCPFU3IWNZX7HO/graph.json","events_json":"https://pith.science/api/pith-number/MPVYBK2OO7DDDCPFU3IWNZX7HO/events.json","paper":"https://pith.science/paper/MPVYBK2O"},"agent_actions":{"view_html":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO","download_json":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO.json","view_paper":"https://pith.science/paper/MPVYBK2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.11711&json=true","fetch_graph":"https://pith.science/api/pith-number/MPVYBK2OO7DDDCPFU3IWNZX7HO/graph.json","fetch_events":"https://pith.science/api/pith-number/MPVYBK2OO7DDDCPFU3IWNZX7HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/action/storage_attestation","attest_author":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/action/author_attestation","sign_citation":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/action/citation_signature","submit_replication":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/action/replication_record"}},"created_at":"2026-06-01T02:03:28.306352+00:00","updated_at":"2026-06-01T02:03:28.306352+00:00"}