{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MZMXOMOWSI7VDVMSVATAYEC725","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":"35b502b18555f3030f0b8a62621926b3b7423089f3e5a613165fb905e6306e01","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T07:52:02Z","title_canon_sha256":"85bb3548e30364f897796db3d5a0663fb4d60e8057bb50db50269f759ad04f2f"},"schema_version":"1.0","source":{"id":"2502.18906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18906","created_at":"2026-07-05T10:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18906v1","created_at":"2026-07-05T10:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18906","created_at":"2026-07-05T10:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"MZMXOMOWSI7V","created_at":"2026-07-05T10:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"MZMXOMOWSI7VDVMS","created_at":"2026-07-05T10:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"MZMXOMOW","created_at":"2026-07-05T10:20:22Z"}],"graph_snapshots":[{"event_id":"sha256:bdad79723dff929325dc7a6849bcc56329a96c3146e279ee759932af8e3c8fd3","target":"graph","created_at":"2026-07-05T10:20:22Z","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/2502.18906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training Vision-Language Models (VLMs) for Graphical User Interfaces (GUI) agents via Reinforcement Learning (RL) faces critical challenges: environment-based RL requires costly interactions, while environment-free methods struggle with distribution shift and reward generalization. We propose an environment-free RL framework that decouples value estimation from policy optimization by leveraging a pretrained Value Environment Model (VEM). VEM predicts state-action values directly from offline data, distilling human-like priors about GUI interaction outcomes without requiring next-state predicti","authors_text":"Chaoyun Zhang, Dongmei Zhang, Fangkai Yang, Jiani Zheng, Lingrui Mei, Lu Wang, Qingwei Lin, Qi Zhang, Saravan Rajmohan, Wenjie Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T07:52:02Z","title":"VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18906","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:e495560360878cc9acb218e8196250af1d19721ccbd4a31a5fc051550886ab89","target":"record","created_at":"2026-07-05T10:20:22Z","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":"35b502b18555f3030f0b8a62621926b3b7423089f3e5a613165fb905e6306e01","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T07:52:02Z","title_canon_sha256":"85bb3548e30364f897796db3d5a0663fb4d60e8057bb50db50269f759ad04f2f"},"schema_version":"1.0","source":{"id":"2502.18906","kind":"arxiv","version":1}},"canonical_sha256":"66597731d6923f51d592a8260c105fd758264cc405bee22e56d07cf2387b2f2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66597731d6923f51d592a8260c105fd758264cc405bee22e56d07cf2387b2f2d","first_computed_at":"2026-07-05T10:20:22.836341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:22.836341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ETL9zlfxF+WSSZwUdiQt83uhAGkKvqVxU6GOeQyWC9RNOnUAqxPZL92duxnI4OZwb9yedP3QkJs/dNAJ5hWyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:22.836827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e495560360878cc9acb218e8196250af1d19721ccbd4a31a5fc051550886ab89","sha256:bdad79723dff929325dc7a6849bcc56329a96c3146e279ee759932af8e3c8fd3"],"state_sha256":"7329b9794516b60eb56162c264b3ac2f16e45f31cc6fb9666e836f5b1d9db2c6"}