{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MPVYBK2OO7DDDCPFU3IWNZX7HO","short_pith_number":"pith:MPVYBK2O","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"},"canonical_sha256":"63eb80ab4e77c63189e5a6d166e6ff3b9e8cd55394f1613d7601faff9dc2c7a7","source":{"kind":"arxiv","id":"2510.11711","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.11711","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2510.11711v2","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11711","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"MPVYBK2OO7DD","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"MPVYBK2OO7DDDCPF","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"MPVYBK2O","created_at":"2026-06-01T02:03:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MPVYBK2OO7DDDCPFU3IWNZX7HO","target":"record","payload":{"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"},"canonical_sha256":"63eb80ab4e77c63189e5a6d166e6ff3b9e8cd55394f1613d7601faff9dc2c7a7","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"},"source_kind":"arxiv","source_id":"2510.11711","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":"2026-06-01T02:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EDZubV67HuZOGsFNqsMf0Jr2L3fzLzjp35tRHyakdHFgjPzs1SUmZ6WPoQPTC04AUqkjIPUn9ldFhLVxIBboDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T07:25:39.399097Z"},"content_sha256":"39e802fe4df85f73ab0ae18948ffe9dbdceee2eebf9b03f0277dbe9ff5ca4235","schema_version":"1.0","event_id":"sha256:39e802fe4df85f73ab0ae18948ffe9dbdceee2eebf9b03f0277dbe9ff5ca4235"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MPVYBK2OO7DDDCPFU3IWNZX7HO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T02:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGSvZV5hwLFq0WCyfvZxg4/omMdSw2JJHCYszDpq5bmfqJx9AWCOkY/zXJaKp9/EJxqiChuwU22iUmhelpmZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T07:25:39.399700Z"},"content_sha256":"c42af1bef50416531a97348cccedc91509264d4ee12be4770bbcf6952a4e9e07","schema_version":"1.0","event_id":"sha256:c42af1bef50416531a97348cccedc91509264d4ee12be4770bbcf6952a4e9e07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/bundle.json","state_url":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/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":"2026-06-05T07:25:39Z","links":{"resolver":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO","bundle":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/bundle.json","state":"https://pith.science/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPVYBK2OO7DDDCPFU3IWNZX7HO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MPVYBK2OO7DDDCPFU3IWNZX7HO","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":"f087f02fae41fcfefa410aa6f7860cb2ecbe3056d736dc7f07c3ce82c95382cd","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:59:11Z","title_canon_sha256":"d6908e1d79dd938115ab57da3aec456b93435861af65b40b2e51e735986e6dc3"},"schema_version":"1.0","source":{"id":"2510.11711","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.11711","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2510.11711v2","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11711","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"MPVYBK2OO7DD","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"MPVYBK2OO7DDDCPF","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"MPVYBK2O","created_at":"2026-06-01T02:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:c42af1bef50416531a97348cccedc91509264d4ee12be4770bbcf6952a4e9e07","target":"graph","created_at":"2026-06-01T02:03:28Z","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/2510.11711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Esmeralda S. Whitammer, Jinkyoo Park, Sanghyeok Choi, Sarthak Mittal, V\\'ictor Elvira","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11711","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":"sha256:39e802fe4df85f73ab0ae18948ffe9dbdceee2eebf9b03f0277dbe9ff5ca4235","target":"record","created_at":"2026-06-01T02:03:28Z","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":"f087f02fae41fcfefa410aa6f7860cb2ecbe3056d736dc7f07c3ce82c95382cd","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:59:11Z","title_canon_sha256":"d6908e1d79dd938115ab57da3aec456b93435861af65b40b2e51e735986e6dc3"},"schema_version":"1.0","source":{"id":"2510.11711","kind":"arxiv","version":2}},"canonical_sha256":"63eb80ab4e77c63189e5a6d166e6ff3b9e8cd55394f1613d7601faff9dc2c7a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63eb80ab4e77c63189e5a6d166e6ff3b9e8cd55394f1613d7601faff9dc2c7a7","first_computed_at":"2026-06-01T02:03:28.306213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:03:28.306213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1bqz1Il5wggsHhNAlCP6Qkv4n6zKoIst3f/nDDEKf3aWxoCV9LKc5AVGD/e7hj6+VC/IBy1PxJv9nWaowlorAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T02:03:28.307081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.11711","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39e802fe4df85f73ab0ae18948ffe9dbdceee2eebf9b03f0277dbe9ff5ca4235","sha256:c42af1bef50416531a97348cccedc91509264d4ee12be4770bbcf6952a4e9e07"],"state_sha256":"c8ab75d0765452a197f1c3460171b49bf7ee36b8c6befc42021c6322f6896f2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9EnMzJv+w5DMQXpuWvYxe7T3Ub9LLWDtkbqesgaTGU6J7z47/Db4vGiPYzALWEk+6ZaSRK5sOoCJRUdT/MESDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T07:25:39.402542Z","bundle_sha256":"09d2f61ffba5871e0cc8621f2d639f2c212b4e1c77bae12f40c121aa3b3a45c8"}}