{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TWOLITLO5WT43YCJSFALFKWX4C","short_pith_number":"pith:TWOLITLO","schema_version":"1.0","canonical_sha256":"9d9cb44d6eeda7cde0499140b2aad7e09c860a037f5fde511e52cf5a876b2474","source":{"kind":"arxiv","id":"2603.23559","version":2},"attestation_state":"computed","paper":{"title":"CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CR","authors_text":"Chenkai Wang, Gang Wang, Haoyu Zhai, Huan Zhang, Lingming Zhang, Rui Yang, Yuxi Chen","submitted_at":"2026-03-23T23:35:59Z","abstract_excerpt":"GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that perceive raw screenshots and directly interact with digital devices. Despite rapid progress on general GUI tasks, CAPTCHA solving remains a major challenge. On the other hand, although specialized CAPTCHA solving pipelines exist, they cannot handle general GUI tasks. To address this gap, we introduce ReCAP: a CAPTCHA-capable native GUI agent that solves modern, interactive CAPTCHA challenges while retaining general GUI-agent performance. We first develop a dynamic CAPTCHA system"},"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":"2603.23559","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-03-23T23:35:59Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"91cfdd13b7f68686032f122ef1154940f4680379305ea520e243b228a760bfc8","abstract_canon_sha256":"8d799dfbfc749c1bd982c78c8c09bb7657073a710ce1c88fefee3faf343e8012"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:18.946578Z","signature_b64":"dSVI0byr6vWZLA5j4Abe/OColXCSfRkANT2Cv4kroBckyk/9y5Fbz/cUqjlIkPBuNWL4np5eo1M/86UNTvRdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d9cb44d6eeda7cde0499140b2aad7e09c860a037f5fde511e52cf5a876b2474","last_reissued_at":"2026-06-30T02:17:18.945832Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:18.945832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CR","authors_text":"Chenkai Wang, Gang Wang, Haoyu Zhai, Huan Zhang, Lingming Zhang, Rui Yang, Yuxi Chen","submitted_at":"2026-03-23T23:35:59Z","abstract_excerpt":"GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that perceive raw screenshots and directly interact with digital devices. Despite rapid progress on general GUI tasks, CAPTCHA solving remains a major challenge. On the other hand, although specialized CAPTCHA solving pipelines exist, they cannot handle general GUI tasks. To address this gap, we introduce ReCAP: a CAPTCHA-capable native GUI agent that solves modern, interactive CAPTCHA challenges while retaining general GUI-agent performance. We first develop a dynamic CAPTCHA system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23559","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/2603.23559/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":"2603.23559","created_at":"2026-06-30T02:17:18.945921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.23559v2","created_at":"2026-06-30T02:17:18.945921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23559","created_at":"2026-06-30T02:17:18.945921+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWOLITLO5WT4","created_at":"2026-06-30T02:17:18.945921+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWOLITLO5WT43YCJ","created_at":"2026-06-30T02:17:18.945921+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWOLITLO","created_at":"2026-06-30T02:17:18.945921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C","json":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C.json","graph_json":"https://pith.science/api/pith-number/TWOLITLO5WT43YCJSFALFKWX4C/graph.json","events_json":"https://pith.science/api/pith-number/TWOLITLO5WT43YCJSFALFKWX4C/events.json","paper":"https://pith.science/paper/TWOLITLO"},"agent_actions":{"view_html":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C","download_json":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C.json","view_paper":"https://pith.science/paper/TWOLITLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.23559&json=true","fetch_graph":"https://pith.science/api/pith-number/TWOLITLO5WT43YCJSFALFKWX4C/graph.json","fetch_events":"https://pith.science/api/pith-number/TWOLITLO5WT43YCJSFALFKWX4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C/action/storage_attestation","attest_author":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C/action/author_attestation","sign_citation":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C/action/citation_signature","submit_replication":"https://pith.science/pith/TWOLITLO5WT43YCJSFALFKWX4C/action/replication_record"}},"created_at":"2026-06-30T02:17:18.945921+00:00","updated_at":"2026-06-30T02:17:18.945921+00:00"}