{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3FP7KC53RJ4SWWRIGNT7YKNSQS","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":"af7518854d2c84f51ecd9b1a15df6948493053d2dd12297dd62c2857864d5729","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-23T16:28:36Z","title_canon_sha256":"926330fe307f16fc22983a0673606fd9c21be72b69b8195afd1b849a61aaca3b"},"schema_version":"1.0","source":{"id":"2603.22169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.22169","created_at":"2026-06-23T02:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"2603.22169v2","created_at":"2026-06-23T02:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22169","created_at":"2026-06-23T02:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"3FP7KC53RJ4S","created_at":"2026-06-23T02:13:22Z"},{"alias_kind":"pith_short_16","alias_value":"3FP7KC53RJ4SWWRI","created_at":"2026-06-23T02:13:22Z"},{"alias_kind":"pith_short_8","alias_value":"3FP7KC53","created_at":"2026-06-23T02:13:22Z"}],"graph_snapshots":[{"event_id":"sha256:b7edbd8f8a2f84c33fbd18700fa82fed304735d95796bfd0675ff07bedc32fa6","target":"graph","created_at":"2026-06-23T02:13:22Z","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/2603.22169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment. In our framework, executable Behavior Trees are repeatedly refined by a Large Language Model actor using structured natural-language feedback produced by a Vision-Language Model critic that observes the physical robot and execution traces. Unlike conventional reinforcement learning, policy u","authors_text":"Artem Trandofilov, Daniia Zinniatullina, Dmitrii Maliukov, Dmitrii Plotnikov, Dmitrij Kosenkov, Dzmitry Tsetserukou, Georgii Gazaryan, Iaroslav Kolomiets, Kirill Bogatikov, Miguel Altamirano Cabrera, Mikhail Konenkov, Timofei Kozlov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-23T16:28:36Z","title":"Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22169","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:e697056f7fbd5c9eb1588ab3ecea337666d4e36e9863dc03375072a546cc2b82","target":"record","created_at":"2026-06-23T02:13:22Z","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":"af7518854d2c84f51ecd9b1a15df6948493053d2dd12297dd62c2857864d5729","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-23T16:28:36Z","title_canon_sha256":"926330fe307f16fc22983a0673606fd9c21be72b69b8195afd1b849a61aaca3b"},"schema_version":"1.0","source":{"id":"2603.22169","kind":"arxiv","version":2}},"canonical_sha256":"d95ff50bbb8a792b5a283367fc29b2849678b7493dbe0d1af9d0d738db678af2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d95ff50bbb8a792b5a283367fc29b2849678b7493dbe0d1af9d0d738db678af2","first_computed_at":"2026-06-23T02:13:22.948001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:22.948001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3I15y+S2MWHemPNkEFHOQta/kQTxgCrIq6Ik5AncIfkd9OJTJeQjzF+e8mIqJX5LcqBK8E96dCDlrSXe9f+nAw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:22.948432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.22169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e697056f7fbd5c9eb1588ab3ecea337666d4e36e9863dc03375072a546cc2b82","sha256:b7edbd8f8a2f84c33fbd18700fa82fed304735d95796bfd0675ff07bedc32fa6"],"state_sha256":"bb47a2b4c62fa34b5e4220b11430b4caae14a8dcaedc552682b256dcabdb7283"}