{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HWACJUX5EHYAKLYJFJJAFDMKEM","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":"ed41b7410f4e88a668803cc4904ce2c19efdb3e3a120c5c35375f273feafaa03","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-28T03:41:25Z","title_canon_sha256":"3ee65763365c75cf9b06270945537634714df483d1745f81842623edefd4e838"},"schema_version":"1.0","source":{"id":"2409.19226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19226","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19226v1","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19226","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"HWACJUX5EHYA","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"HWACJUX5EHYAKLYJ","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"HWACJUX5","created_at":"2026-07-05T09:13:12Z"}],"graph_snapshots":[{"event_id":"sha256:19968b7d19148ce057f08367797a2747d3e44df4f7f200953c6365fcb7cd77a8","target":"graph","created_at":"2026-07-05T09:13:12Z","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/2409.19226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The real world is unpredictable. Therefore, to solve long-horizon decision-making problems with autonomous robots, we must construct agents that are capable of adapting to changes in the environment during deployment. Model-based planning approaches can enable robots to solve complex, long-horizon tasks in a variety of environments. However, such approaches tend to be brittle when deployed into an environment featuring a novel situation that their underlying model does not account for. In this work, we propose to learn a ``bridge policy'' via Reinforcement Learning (RL) to adapt to such novelt","authors_text":"Alicia Li, Leslie Kaelbling, Nishanth Kumar, Tom\\'as Lozano-P\\'erez","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-28T03:41:25Z","title":"Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19226","kind":"arxiv","version":1},"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":"sha256:0e9b277eb46675ad076d5316cb4bd065891a8b9f2999bd72aed5110799069328","target":"record","created_at":"2026-07-05T09:13:12Z","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":"ed41b7410f4e88a668803cc4904ce2c19efdb3e3a120c5c35375f273feafaa03","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-28T03:41:25Z","title_canon_sha256":"3ee65763365c75cf9b06270945537634714df483d1745f81842623edefd4e838"},"schema_version":"1.0","source":{"id":"2409.19226","kind":"arxiv","version":1}},"canonical_sha256":"3d8024d2fd21f0052f092a52028d8a230ed233e0a7437a8f38b72c9cbcf911fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d8024d2fd21f0052f092a52028d8a230ed233e0a7437a8f38b72c9cbcf911fc","first_computed_at":"2026-07-05T09:13:12.401573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:12.401573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wQZiJgH9+DzuIbkOxgv4VYrGo2TP5SAufezrjFtRFrLd8MMbxsKMukmJj63IaT8TDZWz9363/LNksRcZ/Hj2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:12.402057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e9b277eb46675ad076d5316cb4bd065891a8b9f2999bd72aed5110799069328","sha256:19968b7d19148ce057f08367797a2747d3e44df4f7f200953c6365fcb7cd77a8"],"state_sha256":"9127a9bcdd4f14f0a4297207095ea835ce3bc4df072b344edf28830ca3fd0658"}