{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KURCTIWYFB57EI4N3ECCGI26EF","short_pith_number":"pith:KURCTIWY","schema_version":"1.0","canonical_sha256":"552229a2d8287bf2238dd90423235e2140f6ad0a6c85426aa68c2970d466e5f0","source":{"kind":"arxiv","id":"2511.14220","version":3},"attestation_state":"computed","paper":{"title":"Twice Sequential Monte Carlo for Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joery A. de Vries, Matthijs T. J. Spaan, Pascal R. van der Vaart, Wendelin B\\\"ohmer, Yaniv Oren","submitted_at":"2025-11-18T07:54:29Z","abstract_excerpt":"Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize and more suitable to GPU acceleration. However, it also suffers from large variance and path degeneracy which prevent it from scaling well with increased search depth, i.e., increased sequential compute. To address these problems, we introduce Twice Sequential Monte Carlo Tree Search (TSMCTS). Across"},"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":"2511.14220","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-18T07:54:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a022f017bd8f61592edd22aaa32691dbd4074b09947d7722b8f9e5752a630367","abstract_canon_sha256":"33ccd4f8e91b74a06a6f2d53e1bb66166de5ea48e46c110b21bdb1fffe623d7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:50.643804Z","signature_b64":"vYScBqGlUa+4RZcs6hAO7rGg4nesBQe4yRZiyo4CpvqejEqYy0YRXXKH1OujcQrYRES+HrZqZnNskvHlsPKtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552229a2d8287bf2238dd90423235e2140f6ad0a6c85426aa68c2970d466e5f0","last_reissued_at":"2026-05-22T01:03:50.643081Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:50.643081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Twice Sequential Monte Carlo for Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joery A. de Vries, Matthijs T. J. Spaan, Pascal R. van der Vaart, Wendelin B\\\"ohmer, Yaniv Oren","submitted_at":"2025-11-18T07:54:29Z","abstract_excerpt":"Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize and more suitable to GPU acceleration. However, it also suffers from large variance and path degeneracy which prevent it from scaling well with increased search depth, i.e., increased sequential compute. To address these problems, we introduce Twice Sequential Monte Carlo Tree Search (TSMCTS). Across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14220","kind":"arxiv","version":3},"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/2511.14220/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":"2511.14220","created_at":"2026-05-22T01:03:50.643206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.14220v3","created_at":"2026-05-22T01:03:50.643206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14220","created_at":"2026-05-22T01:03:50.643206+00:00"},{"alias_kind":"pith_short_12","alias_value":"KURCTIWYFB57","created_at":"2026-05-22T01:03:50.643206+00:00"},{"alias_kind":"pith_short_16","alias_value":"KURCTIWYFB57EI4N","created_at":"2026-05-22T01:03:50.643206+00:00"},{"alias_kind":"pith_short_8","alias_value":"KURCTIWY","created_at":"2026-05-22T01:03:50.643206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16692","citing_title":"EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF","json":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF.json","graph_json":"https://pith.science/api/pith-number/KURCTIWYFB57EI4N3ECCGI26EF/graph.json","events_json":"https://pith.science/api/pith-number/KURCTIWYFB57EI4N3ECCGI26EF/events.json","paper":"https://pith.science/paper/KURCTIWY"},"agent_actions":{"view_html":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF","download_json":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF.json","view_paper":"https://pith.science/paper/KURCTIWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.14220&json=true","fetch_graph":"https://pith.science/api/pith-number/KURCTIWYFB57EI4N3ECCGI26EF/graph.json","fetch_events":"https://pith.science/api/pith-number/KURCTIWYFB57EI4N3ECCGI26EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF/action/storage_attestation","attest_author":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF/action/author_attestation","sign_citation":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF/action/citation_signature","submit_replication":"https://pith.science/pith/KURCTIWYFB57EI4N3ECCGI26EF/action/replication_record"}},"created_at":"2026-05-22T01:03:50.643206+00:00","updated_at":"2026-05-22T01:03:50.643206+00:00"}