{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GUALE2Q4D777SULKKITB7FOTIJ","short_pith_number":"pith:GUALE2Q4","canonical_record":{"source":{"id":"2504.06048","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T13:47:07Z","cross_cats_sorted":[],"title_canon_sha256":"f5522a0fc1f5225f290230d691736a6a8288bc0dc8271b60ac90fdd614bc5364","abstract_canon_sha256":"fd9c21e969d9f56befa4ed5dba95faa4d95b5278640b4fdfb60fed1033edecda"},"schema_version":"1.0"},"canonical_sha256":"3500b26a1c1ffff9516a52261f95d34270c66d92bf7560f5c355b0afd39c77cd","source":{"kind":"arxiv","id":"2504.06048","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06048","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06048v4","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06048","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"pith_short_12","alias_value":"GUALE2Q4D777","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"pith_short_16","alias_value":"GUALE2Q4D777SULK","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"pith_short_8","alias_value":"GUALE2Q4","created_at":"2026-07-05T11:33:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GUALE2Q4D777SULKKITB7FOTIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.06048","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T13:47:07Z","cross_cats_sorted":[],"title_canon_sha256":"f5522a0fc1f5225f290230d691736a6a8288bc0dc8271b60ac90fdd614bc5364","abstract_canon_sha256":"fd9c21e969d9f56befa4ed5dba95faa4d95b5278640b4fdfb60fed1033edecda"},"schema_version":"1.0"},"canonical_sha256":"3500b26a1c1ffff9516a52261f95d34270c66d92bf7560f5c355b0afd39c77cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:22.647394Z","signature_b64":"EclGMEkNi5CvRVeWRqhrHeAk4hJ4eA8bH8zPoxVlBXlYoWsCzX254ht/bJPVJj3kYx26p8EWG1fS1TRHHqFmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3500b26a1c1ffff9516a52261f95d34270c66d92bf7560f5c355b0afd39c77cd","last_reissued_at":"2026-07-05T11:33:22.646857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:22.646857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.06048","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MBnlRc6o0fhbIky0KeugQjmUAwF65HU6Kti1kWMA72oKWP1D1P7k3HGMWYkzmTdz576WOCbhC2J5Ftp+XTOLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:40:32.575056Z"},"content_sha256":"15d28792b84f6eb54bdd810de1237907a855570aa7f7779eb669edfb5336fc93","schema_version":"1.0","event_id":"sha256:15d28792b84f6eb54bdd810de1237907a855570aa7f7779eb669edfb5336fc93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GUALE2Q4D777SULKKITB7FOTIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trust-Region Twisted Policy Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinke He, Joery A. de Vries, Matthijs T. J. Spaan, Yaniv Oren","submitted_at":"2025-04-08T13:47:07Z","abstract_excerpt":"Monte-Carlo tree search (MCTS) has driven many recent breakthroughs in deep reinforcement learning (RL). However, scaling MCTS to parallel compute has proven challenging in practice which has motivated alternative planners like sequential Monte-Carlo (SMC). Many of these SMC methods adopt particle filters for smoothing through a reformulation of RL as a policy inference problem. Yet, persisting design choices of these particle filters often conflict with the aim of online planning in RL, which is to obtain a policy improvement at the start of planning. Drawing inspiration from MCTS, we tailor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06048","kind":"arxiv","version":4},"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/2504.06048/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":"2026-07-05T11:33:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1x/vdFaCc5OyPhI5YrdR1Z7J1lt01CfZKZkU9ehrT7zp1LbA/7cF7B3NL+0G4tNl761nqs4X/R90mL9dHEXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:40:32.575535Z"},"content_sha256":"279d2f06ce1646673c73fbef52f6fcb8daa3240d749c423598c766688016e31c","schema_version":"1.0","event_id":"sha256:279d2f06ce1646673c73fbef52f6fcb8daa3240d749c423598c766688016e31c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUALE2Q4D777SULKKITB7FOTIJ/bundle.json","state_url":"https://pith.science/pith/GUALE2Q4D777SULKKITB7FOTIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUALE2Q4D777SULKKITB7FOTIJ/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":"2026-08-03T16:40:32Z","links":{"resolver":"https://pith.science/pith/GUALE2Q4D777SULKKITB7FOTIJ","bundle":"https://pith.science/pith/GUALE2Q4D777SULKKITB7FOTIJ/bundle.json","state":"https://pith.science/pith/GUALE2Q4D777SULKKITB7FOTIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUALE2Q4D777SULKKITB7FOTIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GUALE2Q4D777SULKKITB7FOTIJ","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":"fd9c21e969d9f56befa4ed5dba95faa4d95b5278640b4fdfb60fed1033edecda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T13:47:07Z","title_canon_sha256":"f5522a0fc1f5225f290230d691736a6a8288bc0dc8271b60ac90fdd614bc5364"},"schema_version":"1.0","source":{"id":"2504.06048","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06048","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06048v4","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06048","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"pith_short_12","alias_value":"GUALE2Q4D777","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"pith_short_16","alias_value":"GUALE2Q4D777SULK","created_at":"2026-07-05T11:33:22Z"},{"alias_kind":"pith_short_8","alias_value":"GUALE2Q4","created_at":"2026-07-05T11:33:22Z"}],"graph_snapshots":[{"event_id":"sha256:279d2f06ce1646673c73fbef52f6fcb8daa3240d749c423598c766688016e31c","target":"graph","created_at":"2026-07-05T11:33:22Z","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/2504.06048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monte-Carlo tree search (MCTS) has driven many recent breakthroughs in deep reinforcement learning (RL). However, scaling MCTS to parallel compute has proven challenging in practice which has motivated alternative planners like sequential Monte-Carlo (SMC). Many of these SMC methods adopt particle filters for smoothing through a reformulation of RL as a policy inference problem. Yet, persisting design choices of these particle filters often conflict with the aim of online planning in RL, which is to obtain a policy improvement at the start of planning. Drawing inspiration from MCTS, we tailor ","authors_text":"Jinke He, Joery A. de Vries, Matthijs T. J. Spaan, Yaniv Oren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T13:47:07Z","title":"Trust-Region Twisted Policy Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06048","kind":"arxiv","version":4},"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":"sha256:15d28792b84f6eb54bdd810de1237907a855570aa7f7779eb669edfb5336fc93","target":"record","created_at":"2026-07-05T11:33:22Z","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":"fd9c21e969d9f56befa4ed5dba95faa4d95b5278640b4fdfb60fed1033edecda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T13:47:07Z","title_canon_sha256":"f5522a0fc1f5225f290230d691736a6a8288bc0dc8271b60ac90fdd614bc5364"},"schema_version":"1.0","source":{"id":"2504.06048","kind":"arxiv","version":4}},"canonical_sha256":"3500b26a1c1ffff9516a52261f95d34270c66d92bf7560f5c355b0afd39c77cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3500b26a1c1ffff9516a52261f95d34270c66d92bf7560f5c355b0afd39c77cd","first_computed_at":"2026-07-05T11:33:22.646857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:22.646857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EclGMEkNi5CvRVeWRqhrHeAk4hJ4eA8bH8zPoxVlBXlYoWsCzX254ht/bJPVJj3kYx26p8EWG1fS1TRHHqFmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:22.647394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.06048","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15d28792b84f6eb54bdd810de1237907a855570aa7f7779eb669edfb5336fc93","sha256:279d2f06ce1646673c73fbef52f6fcb8daa3240d749c423598c766688016e31c"],"state_sha256":"23b1593ff4212363b7abf08cd88d67ca8c1137a944ddc280b4fcbfd3d15e2f1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yQPsQ3ZhBT2QiMLryMF1fk0OVCR4SeU+oqKuBoYQnALnLBfFYWy0DpZnht+AJWN/8BQruAinlQ93muR2TpdNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:40:32.579140Z","bundle_sha256":"c66751e002413c4df42b9d3a81fc48b93081e138a3e72687606baf9784dc0cee"}}