{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J25YCLGLPWDZ7L7ZQGYV24DXK7","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":"ace2547a1c8dfdfd4f7ec25f0db54e1e80bb3444486960f0dbcf555d83126bfd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T04:56:59Z","title_canon_sha256":"259dc522ff9733faddfc41ff31c65c3858ca619b6137a572b02cffca6efe8c0f"},"schema_version":"1.0","source":{"id":"2605.20246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20246","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20246v1","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20246","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"J25YCLGLPWDZ","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"J25YCLGLPWDZ7L7Z","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"J25YCLGL","created_at":"2026-05-21T00:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:3faa6318abf350ac348328d9343ced070e7b77a38ec78455f0de4f6d7d90b88e","target":"graph","created_at":"2026-05-21T00:04:22Z","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/2605.20246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely primarily on Supervised Fine-Tuning (SFT) with expert demonstrations, while the advanced reinforcement learning (RL) algorithm, specifically Group Relative Policy Optimization (GRPO), has not been effectively employed for multi-turn RL in these tasks because standard GRPO requires full trajectories as training samples which leads to excessively long context a","authors_text":"Jie Yang, Lechao Zhang, Shanzhe Lei, Wei Liu, Xin Tan, Xiongbin Wu, Xuhong Wang, Yuanjie Zheng, Zhihao Luo, Zhonglong Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T04:56:59Z","title":"GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20246","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:b726fd85c56619bcef3fbc688df7cd96ebc6fb8b0f3d102fa2ba4a7945545d41","target":"record","created_at":"2026-05-21T00:04:22Z","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":"ace2547a1c8dfdfd4f7ec25f0db54e1e80bb3444486960f0dbcf555d83126bfd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T04:56:59Z","title_canon_sha256":"259dc522ff9733faddfc41ff31c65c3858ca619b6137a572b02cffca6efe8c0f"},"schema_version":"1.0","source":{"id":"2605.20246","kind":"arxiv","version":1}},"canonical_sha256":"4ebb812ccb7d879faff981b15d707757c1b3fb9998f45a7d886a5e431c640373","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ebb812ccb7d879faff981b15d707757c1b3fb9998f45a7d886a5e431c640373","first_computed_at":"2026-05-21T00:04:22.569171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T00:04:22.569171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpe6y88qXb0ldUmF37pgQiFpR0zQ75gLwzbzq1MOndeMUZmww6X9W0ZU3snkXYEHB+A12XzWWPyL7/EX0jioBA==","signature_status":"signed_v1","signed_at":"2026-05-21T00:04:22.569668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b726fd85c56619bcef3fbc688df7cd96ebc6fb8b0f3d102fa2ba4a7945545d41","sha256:3faa6318abf350ac348328d9343ced070e7b77a38ec78455f0de4f6d7d90b88e"],"state_sha256":"1b21f3b624e09e5d3c2006945f88399d168c953c00e2f4d48b77c6e009fb46e3"}