{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TWOLITLO5WT43YCJSFALFKWX4C","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":"8d799dfbfc749c1bd982c78c8c09bb7657073a710ce1c88fefee3faf343e8012","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-03-23T23:35:59Z","title_canon_sha256":"91cfdd13b7f68686032f122ef1154940f4680379305ea520e243b228a760bfc8"},"schema_version":"1.0","source":{"id":"2603.23559","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.23559","created_at":"2026-06-30T02:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2603.23559v2","created_at":"2026-06-30T02:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23559","created_at":"2026-06-30T02:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"TWOLITLO5WT4","created_at":"2026-06-30T02:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"TWOLITLO5WT43YCJ","created_at":"2026-06-30T02:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"TWOLITLO","created_at":"2026-06-30T02:17:18Z"}],"graph_snapshots":[{"event_id":"sha256:a6a67e58434714807565d7fa2e6fdd1499e5f6555883b51f1469564debf71826","target":"graph","created_at":"2026-06-30T02:17:18Z","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/2603.23559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenkai Wang, Gang Wang, Haoyu Zhai, Huan Zhang, Lingming Zhang, Rui Yang, Yuxi Chen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-03-23T23:35:59Z","title":"CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23559","kind":"arxiv","version":2},"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":"sha256:76d0eedbe79015c6a0e6f01131453bc944b58d0cb13b0909031a8ee812c9360c","target":"record","created_at":"2026-06-30T02:17:18Z","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":"8d799dfbfc749c1bd982c78c8c09bb7657073a710ce1c88fefee3faf343e8012","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-03-23T23:35:59Z","title_canon_sha256":"91cfdd13b7f68686032f122ef1154940f4680379305ea520e243b228a760bfc8"},"schema_version":"1.0","source":{"id":"2603.23559","kind":"arxiv","version":2}},"canonical_sha256":"9d9cb44d6eeda7cde0499140b2aad7e09c860a037f5fde511e52cf5a876b2474","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d9cb44d6eeda7cde0499140b2aad7e09c860a037f5fde511e52cf5a876b2474","first_computed_at":"2026-06-30T02:17:18.945832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:18.945832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dSVI0byr6vWZLA5j4Abe/OColXCSfRkANT2Cv4kroBckyk/9y5Fbz/cUqjlIkPBuNWL4np5eo1M/86UNTvRdBA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:18.946578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.23559","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76d0eedbe79015c6a0e6f01131453bc944b58d0cb13b0909031a8ee812c9360c","sha256:a6a67e58434714807565d7fa2e6fdd1499e5f6555883b51f1469564debf71826"],"state_sha256":"58f68ffd710bbdffe01a00506c90dcd5613b284c5bff8446fa2f57f59ce9b312"}