{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W2YIAKPGBXJZHVJ3ELOT7CZ2GF","short_pith_number":"pith:W2YIAKPG","schema_version":"1.0","canonical_sha256":"b6b08029e60dd393d53b22dd3f8b3a3140af44cfb266f5aef6aa3d6103aa8a9b","source":{"kind":"arxiv","id":"2505.15810","version":2},"attestation_state":"computed","paper":{"title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jun Xu, Kaiwen Zhou, Qinglin Jia, Shuai Wang, Sunhao Dai, Yuqi Zhou","submitted_at":"2025-05-21T17:59:09Z","abstract_excerpt":"Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update-each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.15810","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T17:59:09Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"b4e6353ec72af923bb5d93c60ff13a06f0ab6982d9c960d38f5fb54b77441f45","abstract_canon_sha256":"616e2b3cd17c90847ce3d8ff2355b9279bfd45a34967edc127f2e46041b0aafa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:25.683957Z","signature_b64":"qO1ALL5AcQypHhgI2/EoPJrhSNN4+22QBscUUsgwNBP+fQDgsr8LTlrdNchBLtmNvXpkIaIref5qrDZMK5W4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6b08029e60dd393d53b22dd3f8b3a3140af44cfb266f5aef6aa3d6103aa8a9b","last_reissued_at":"2026-07-05T11:07:25.683483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:25.683483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jun Xu, Kaiwen Zhou, Qinglin Jia, Shuai Wang, Sunhao Dai, Yuqi Zhou","submitted_at":"2025-05-21T17:59:09Z","abstract_excerpt":"Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update-each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15810","kind":"arxiv","version":2},"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/2505.15810/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.15810","created_at":"2026-07-05T11:07:25.683537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15810v2","created_at":"2026-07-05T11:07:25.683537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15810","created_at":"2026-07-05T11:07:25.683537+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2YIAKPGBXJZ","created_at":"2026-07-05T11:07:25.683537+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2YIAKPGBXJZHVJ3","created_at":"2026-07-05T11:07:25.683537+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2YIAKPG","created_at":"2026-07-05T11:07:25.683537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27330","citing_title":"Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10522","citing_title":"GUI-AC: Enhancing Continual Learning in GUI Agents","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09711","citing_title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28629","citing_title":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30884","citing_title":"GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17933","citing_title":"AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07553","citing_title":"VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21982","citing_title":"RISK: A Framework for GUI Agents in E-commerce Risk Management","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05791","citing_title":"GTA1: GUI Test-time Scaling Agent","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21858","citing_title":"ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00642","citing_title":"Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24348","citing_title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06664","citing_title":"BAMI: Training-Free Bias Mitigation in GUI Grounding","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00642","citing_title":"Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07505","citing_title":"LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13602","citing_title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13531","citing_title":"RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02630","citing_title":"AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF","json":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF.json","graph_json":"https://pith.science/api/pith-number/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/graph.json","events_json":"https://pith.science/api/pith-number/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/events.json","paper":"https://pith.science/paper/W2YIAKPG"},"agent_actions":{"view_html":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF","download_json":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF.json","view_paper":"https://pith.science/paper/W2YIAKPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15810&json=true","fetch_graph":"https://pith.science/api/pith-number/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/graph.json","fetch_events":"https://pith.science/api/pith-number/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/action/storage_attestation","attest_author":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/action/author_attestation","sign_citation":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/action/citation_signature","submit_replication":"https://pith.science/pith/W2YIAKPGBXJZHVJ3ELOT7CZ2GF/action/replication_record"}},"created_at":"2026-07-05T11:07:25.683537+00:00","updated_at":"2026-07-05T11:07:25.683537+00:00"}