{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OEZM3DVHJYPXLTTSA4G7AZZEOZ","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":"3fff2eed1032d787cff8180b0e97a008324aa1bcdb5543172c2091e5f0adb030","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-05T16:45:38Z","title_canon_sha256":"d9983ba03e97f4443791a67e52f9b4c4d1eb2097e4c3df1e5ba846f21f8118b3"},"schema_version":"1.0","source":{"id":"2510.04280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.04280","created_at":"2026-05-22T01:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2510.04280v2","created_at":"2026-05-22T01:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04280","created_at":"2026-05-22T01:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"OEZM3DVHJYPX","created_at":"2026-05-22T01:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"OEZM3DVHJYPXLTTS","created_at":"2026-05-22T01:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"OEZM3DVH","created_at":"2026-05-22T01:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:5ca905b1a8944713d861e3788b10321db53ea85a9b8f0dcc6b3dadb975636cfb","target":"graph","created_at":"2026-05-22T01:03:15Z","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/2510.04280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective exploration remains a central challenge in model-based reinforcement learning (MBRL), particularly in high-dimensional continuous control tasks where sample efficiency is crucial. A prominent line of recent work leverages learned policies as proposal distributions for Model-Predictive Path Integral (MPPI) planning. Initial approaches update the sampling policy independently of the planner distribution, typically maximizing a learned value function with deterministic policy gradient and entropy regularization. However, because the states encountered during training depend on the MPPI ","authors_text":"\\'Alvaro Serra-Gomez, Daniel Jarne Ornia, Dhruva Tirumala, Thomas Moerland","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-05T16:45:38Z","title":"A KL-regularization Framework for Learning to Plan with Adaptive Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04280","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":"sha256:8394f9b735e6457671516f91962a61cb7507d6d13c5b4d0e93ceed2db4fd0584","target":"record","created_at":"2026-05-22T01:03:15Z","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":"3fff2eed1032d787cff8180b0e97a008324aa1bcdb5543172c2091e5f0adb030","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-05T16:45:38Z","title_canon_sha256":"d9983ba03e97f4443791a67e52f9b4c4d1eb2097e4c3df1e5ba846f21f8118b3"},"schema_version":"1.0","source":{"id":"2510.04280","kind":"arxiv","version":2}},"canonical_sha256":"7132cd8ea74e1f75ce72070df06724766c8ce65b077b7ad98519e398905f2120","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7132cd8ea74e1f75ce72070df06724766c8ce65b077b7ad98519e398905f2120","first_computed_at":"2026-05-22T01:03:15.685490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:15.685490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ewQBssXyQV2poYZpp98G/FgoJvNEOV+0VLADju0hzXvgHx01dAWvjBbe8A/DfKIekHPXDbItpzGbO8IF+RmcAw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:15.686374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.04280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8394f9b735e6457671516f91962a61cb7507d6d13c5b4d0e93ceed2db4fd0584","sha256:5ca905b1a8944713d861e3788b10321db53ea85a9b8f0dcc6b3dadb975636cfb"],"state_sha256":"a3f8b179d03d302bb52cc8bf93142cb61cb3da75f61c95d85c506bfe1e888b1e"}