{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BHWLSZW7LHTYRPMQZDFPEJRABL","short_pith_number":"pith:BHWLSZW7","schema_version":"1.0","canonical_sha256":"09ecb966df59e788bd90c8caf226200ac9dd3f3a855135a0facb2d916e677b35","source":{"kind":"arxiv","id":"2601.18197","version":2},"attestation_state":"computed","paper":{"title":"GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Qin, Jiahui Yang, Jian Luan, Pei Fu, Ruoceng Zhang, Shaojie Zhang, Shaokang Wang, Xiuwen Xi, Ying Huang, Zhenbo Luo","submitted_at":"2026-01-26T06:29:41Z","abstract_excerpt":"While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen content, and executing tasks, a critical challenge persists: the irreversibility of agent operations-where a single erroneous action can trigger catastrophic deviations. To address this, we propose the \\textbf{G}UI \\textbf{A}ction Cr\\textbf{i}tic's Dat\\textbf{a} Flywheel System (GAIA), a training framework that enables the models to have iterative critic capabilities, which are used to improve the Test-Time Scaling (TTS) of basic GUI agents' perfo"},"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":"2601.18197","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T06:29:41Z","cross_cats_sorted":[],"title_canon_sha256":"ba98cb62cf18f2f5d92d3d1d776e504b300f1d6fcc9b0eb506eca5e007f93c38","abstract_canon_sha256":"247341036704857b693b70fd19ba937845ec9fbd47d93aeee68f6bffc0416768"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:28.216073Z","signature_b64":"nH+rckBaUfJYsTT+zQ+UhElXZBI73eWLx8qBO+jrClu6+ci6/wND8naxjjLglRQCpwv0x9jdgT3SiaKlUFQdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ecb966df59e788bd90c8caf226200ac9dd3f3a855135a0facb2d916e677b35","last_reissued_at":"2026-06-29T01:14:28.215481Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:28.215481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Qin, Jiahui Yang, Jian Luan, Pei Fu, Ruoceng Zhang, Shaojie Zhang, Shaokang Wang, Xiuwen Xi, Ying Huang, Zhenbo Luo","submitted_at":"2026-01-26T06:29:41Z","abstract_excerpt":"While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen content, and executing tasks, a critical challenge persists: the irreversibility of agent operations-where a single erroneous action can trigger catastrophic deviations. To address this, we propose the \\textbf{G}UI \\textbf{A}ction Cr\\textbf{i}tic's Dat\\textbf{a} Flywheel System (GAIA), a training framework that enables the models to have iterative critic capabilities, which are used to improve the Test-Time Scaling (TTS) of basic GUI agents' perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18197","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/2601.18197/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":"2601.18197","created_at":"2026-06-29T01:14:28.215544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18197v2","created_at":"2026-06-29T01:14:28.215544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18197","created_at":"2026-06-29T01:14:28.215544+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHWLSZW7LHTY","created_at":"2026-06-29T01:14:28.215544+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHWLSZW7LHTYRPMQ","created_at":"2026-06-29T01:14:28.215544+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHWLSZW7","created_at":"2026-06-29T01:14:28.215544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.14311","citing_title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14311","citing_title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","ref_index":112,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL","json":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL.json","graph_json":"https://pith.science/api/pith-number/BHWLSZW7LHTYRPMQZDFPEJRABL/graph.json","events_json":"https://pith.science/api/pith-number/BHWLSZW7LHTYRPMQZDFPEJRABL/events.json","paper":"https://pith.science/paper/BHWLSZW7"},"agent_actions":{"view_html":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL","download_json":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL.json","view_paper":"https://pith.science/paper/BHWLSZW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18197&json=true","fetch_graph":"https://pith.science/api/pith-number/BHWLSZW7LHTYRPMQZDFPEJRABL/graph.json","fetch_events":"https://pith.science/api/pith-number/BHWLSZW7LHTYRPMQZDFPEJRABL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL/action/storage_attestation","attest_author":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL/action/author_attestation","sign_citation":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL/action/citation_signature","submit_replication":"https://pith.science/pith/BHWLSZW7LHTYRPMQZDFPEJRABL/action/replication_record"}},"created_at":"2026-06-29T01:14:28.215544+00:00","updated_at":"2026-06-29T01:14:28.215544+00:00"}