{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ROSR2MAJMMJWLBKOMQINLFOFNK","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":"5b3754dbf5083cf3c70f8f95b9117d084ce23584044edf67d4536e7b22afbe3c","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T08:22:39Z","title_canon_sha256":"c440a778a7924b5c9e69419610664f07e8dc82bbd8633b8fd96772e0c0f1ba9e"},"schema_version":"1.0","source":{"id":"2603.11653","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11653","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11653v2","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11653","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"ROSR2MAJMMJW","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"ROSR2MAJMMJWLBKO","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"ROSR2MAJ","created_at":"2026-06-02T02:04:15Z"}],"graph_snapshots":[{"event_id":"sha256:28f303a69e3665e0d56bce91a6b2521a22d6bfad62b8509958f9eb36d0c11368","target":"graph","created_at":"2026-06-02T02:04:15Z","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/2603.11653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of CRL for large pretrained VLAs across diverse lifelong RL benchmarks. We find that, contrary to established belief, simple Seq. FT with low-rank adaptation (LoRA","authors_text":"Bo Liu, Chen Tang, Jay Shim, Jiaheng Hu, Peter Stone, Roberto Martin-Martin, Yoonchang Sung","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T08:22:39Z","title":"Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11653","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":"sha256:1e648ef844146a0f6511cad04904df95dd0303bc63a189ea0fe5011dab1d9f2f","target":"record","created_at":"2026-06-02T02:04:15Z","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":"5b3754dbf5083cf3c70f8f95b9117d084ce23584044edf67d4536e7b22afbe3c","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T08:22:39Z","title_canon_sha256":"c440a778a7924b5c9e69419610664f07e8dc82bbd8633b8fd96772e0c0f1ba9e"},"schema_version":"1.0","source":{"id":"2603.11653","kind":"arxiv","version":2}},"canonical_sha256":"8ba51d3009631365854e6410d595c56aac029ff6c19462b5f872dae6a269dd4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ba51d3009631365854e6410d595c56aac029ff6c19462b5f872dae6a269dd4e","first_computed_at":"2026-06-02T02:04:15.942415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:15.942415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bekc9VZ2qRzeIrhvJqUI/233EBhjnN/+cHQAxj5JByGjHoqz+uaosGQn7YJIXCBAb67N7uOI4oL+b0zV1vs3Ag==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:15.942934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.11653","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e648ef844146a0f6511cad04904df95dd0303bc63a189ea0fe5011dab1d9f2f","sha256:28f303a69e3665e0d56bce91a6b2521a22d6bfad62b8509958f9eb36d0c11368"],"state_sha256":"d69c39eea5e9844f7634e043273c8ae770fde9c2f620314de1f318e35624fba9"}