{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2YGT4HD53KNFLKW6IQNWOSLDN2","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":"2a2874c677d98147ee30c335c0130499ea85c1a35e91c43d5821f8f5cfba7fca","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-17T07:31:11Z","title_canon_sha256":"0859daba9430ca1e2a440709410446fc94e2fafd08093842b0990acb64f3608a"},"schema_version":"1.0","source":{"id":"2508.14104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14104","created_at":"2026-07-05T11:56:25Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14104v1","created_at":"2026-07-05T11:56:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14104","created_at":"2026-07-05T11:56:25Z"},{"alias_kind":"pith_short_12","alias_value":"2YGT4HD53KNF","created_at":"2026-07-05T11:56:25Z"},{"alias_kind":"pith_short_16","alias_value":"2YGT4HD53KNFLKW6","created_at":"2026-07-05T11:56:25Z"},{"alias_kind":"pith_short_8","alias_value":"2YGT4HD5","created_at":"2026-07-05T11:56:25Z"}],"graph_snapshots":[{"event_id":"sha256:fd63acc93aaf456050dc7c2ab01581714a5ec7ef30244d38d7f398b60b7f220f","target":"graph","created_at":"2026-07-05T11:56:25Z","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/2508.14104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) and code agents in software development are rapidly evolving from generating isolated code snippets to producing full-fledged software applications with graphical interfaces, interactive logic, and dynamic behaviors. However, current benchmarks fall short in evaluating such production-ready software, as they often rely on static checks or binary pass/fail scripts, failing to capture the interactive behaviors and runtime dynamics that define real-world usability - qualities that only emerge when an application is actively used. This is the blind spot of current eval","authors_text":"Chenglin Wu, Haoming Tang, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Mingchen Zhuge, Sirui Hong, Siyuan Lu, Tianyang Liu, Xiangru Tang, Xianhao Lin, Yongxin Ni, Yupeng Xie, Yutong Bian","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-17T07:31:11Z","title":"You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14104","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:cafbd7ab73d62fbddb04c67aacf0448218478778bbba0ede3f07d52f03704b62","target":"record","created_at":"2026-07-05T11:56:25Z","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":"2a2874c677d98147ee30c335c0130499ea85c1a35e91c43d5821f8f5cfba7fca","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-17T07:31:11Z","title_canon_sha256":"0859daba9430ca1e2a440709410446fc94e2fafd08093842b0990acb64f3608a"},"schema_version":"1.0","source":{"id":"2508.14104","kind":"arxiv","version":1}},"canonical_sha256":"d60d3e1c7dda9a55aade441b6749636e82f34446ec6efad7f4ff359759cd4311","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d60d3e1c7dda9a55aade441b6749636e82f34446ec6efad7f4ff359759cd4311","first_computed_at":"2026-07-05T11:56:25.212685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:25.212685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m8L2MXvzpNQwMKBMGYVpDwdHVNku2YqrLUTApQ/7u90D9A/fa2TJ2ZtDMmEH1/U7mkl/wSJoFLedvddJDZpMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:25.213170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cafbd7ab73d62fbddb04c67aacf0448218478778bbba0ede3f07d52f03704b62","sha256:fd63acc93aaf456050dc7c2ab01581714a5ec7ef30244d38d7f398b60b7f220f"],"state_sha256":"8108a53e05b69643ba6d1ef4c97ef3c8f73201b61dbf20803cd5860c6c6f9af7"}