{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:J25YCLGLPWDZ7L7ZQGYV24DXK7","short_pith_number":"pith:J25YCLGL","canonical_record":{"source":{"id":"2605.20246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T04:56:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"259dc522ff9733faddfc41ff31c65c3858ca619b6137a572b02cffca6efe8c0f","abstract_canon_sha256":"ace2547a1c8dfdfd4f7ec25f0db54e1e80bb3444486960f0dbcf555d83126bfd"},"schema_version":"1.0"},"canonical_sha256":"4ebb812ccb7d879faff981b15d707757c1b3fb9998f45a7d886a5e431c640373","source":{"kind":"arxiv","id":"2605.20246","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:J25YCLGLPWDZ7L7ZQGYV24DXK7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T04:56:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"259dc522ff9733faddfc41ff31c65c3858ca619b6137a572b02cffca6efe8c0f","abstract_canon_sha256":"ace2547a1c8dfdfd4f7ec25f0db54e1e80bb3444486960f0dbcf555d83126bfd"},"schema_version":"1.0"},"canonical_sha256":"4ebb812ccb7d879faff981b15d707757c1b3fb9998f45a7d886a5e431c640373","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T00:04:22.569668Z","signature_b64":"qpe6y88qXb0ldUmF37pgQiFpR0zQ75gLwzbzq1MOndeMUZmww6X9W0ZU3snkXYEHB+A12XzWWPyL7/EX0jioBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ebb812ccb7d879faff981b15d707757c1b3fb9998f45a7d886a5e431c640373","last_reissued_at":"2026-05-21T00:04:22.569171Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T00:04:22.569171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20246","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJGL1G8N3962pQp0NRJkym+1VFvaN8c5Alec8DpvcfZyDZZmRdxHvjzxhhAFzi5YZDJ51X5cW3TImW+2fqxMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:22:53.321680Z"},"content_sha256":"b726fd85c56619bcef3fbc688df7cd96ebc6fb8b0f3d102fa2ba4a7945545d41","schema_version":"1.0","event_id":"sha256:b726fd85c56619bcef3fbc688df7cd96ebc6fb8b0f3d102fa2ba4a7945545d41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:J25YCLGLPWDZ7L7ZQGYV24DXK7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Yang, Lechao Zhang, Shanzhe Lei, Wei Liu, Xin Tan, Xiongbin Wu, Xuhong Wang, Yuanjie Zheng, Zhihao Luo, Zhonglong Zheng","submitted_at":"2026-05-18T04:56:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20246","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.20246/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wfzP2VO8L5P9HJN+bMNLfFX12HJhev55//jxou6KRq7WRi3MHLVD2TUy7akhUAzXYOnkOy+fx0ZJcd41sKjBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:22:53.322427Z"},"content_sha256":"3faa6318abf350ac348328d9343ced070e7b77a38ec78455f0de4f6d7d90b88e","schema_version":"1.0","event_id":"sha256:3faa6318abf350ac348328d9343ced070e7b77a38ec78455f0de4f6d7d90b88e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7/bundle.json","state_url":"https://pith.science/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T07:22:53Z","links":{"resolver":"https://pith.science/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7","bundle":"https://pith.science/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7/bundle.json","state":"https://pith.science/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J25YCLGLPWDZ7L7ZQGYV24DXK7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ObwbQ1fm6SSpthm63eWbii9lG67DLgESRoAPQkNz1TAn7OwYCcD9tRE3CUgI2tD15GvKf3MWSgw9QqWtSghvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:22:53.326366Z","bundle_sha256":"bed5ffad346287e7626dbd0b39efa62ded092a8bddd1ae582bc598c88f43ae51"}}