{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AA7GL5KXVTYVHWY54PX552YUML","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":"4d68848ea18ef0dd65b420d356dc1c2633b621d7b5e02267588fb55496faa3e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T06:24:32Z","title_canon_sha256":"ed26386cbd81ea34d56e9e16692e71e19aca7fece765d9a0c6b78902173f602f"},"schema_version":"1.0","source":{"id":"2505.16282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16282","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16282v1","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16282","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"AA7GL5KXVTYV","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_16","alias_value":"AA7GL5KXVTYVHWY5","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_8","alias_value":"AA7GL5KX","created_at":"2026-07-05T11:07:32Z"}],"graph_snapshots":[{"event_id":"sha256:2ed772236c42d83041d42b5bf446746c74c267aac46ec84db6bf18e7ae45472d","target":"graph","created_at":"2026-07-05T11:07:32Z","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/2505.16282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While recent works have advanced multi-turn reinforcement learning (RL) for reasoning and tool-using capabilities in LLMs, their application to GUI-based agents remains relatively underexplored due to the difficulty of sparse rewards, delayed feedback, and high rollout costs. In this paper, we investigate end-to-end policy optimization for vision-language-based GUI a","authors_text":"Chi-Wing Fu, Fanbin Lu, Jiaya Jia, Shu Liu, Zhisheng Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T06:24:32Z","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16282","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:c7d1e9186ef13fdbd097b1dd1aff5d2d3e1545bbbc67747c517a73687b672e06","target":"record","created_at":"2026-07-05T11:07:32Z","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":"4d68848ea18ef0dd65b420d356dc1c2633b621d7b5e02267588fb55496faa3e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T06:24:32Z","title_canon_sha256":"ed26386cbd81ea34d56e9e16692e71e19aca7fece765d9a0c6b78902173f602f"},"schema_version":"1.0","source":{"id":"2505.16282","kind":"arxiv","version":1}},"canonical_sha256":"003e65f557acf153db1de3efdeeb1462ec2f5398660df54af3b137d16fb9a459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"003e65f557acf153db1de3efdeeb1462ec2f5398660df54af3b137d16fb9a459","first_computed_at":"2026-07-05T11:07:32.689825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:32.689825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hLYsQ0AYob1cAUxt/IYhI5JZ6IRLijw7lfs12RUFk6f2arROG7AfcgRoowvca70GJSQxBrpNuiREG+9J4yIiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:32.690257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7d1e9186ef13fdbd097b1dd1aff5d2d3e1545bbbc67747c517a73687b672e06","sha256:2ed772236c42d83041d42b5bf446746c74c267aac46ec84db6bf18e7ae45472d"],"state_sha256":"be9b66f5c6212f25a52c4a4a39c992c112a16428ad25517f68eacf4539e60ea5"}