{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HF2KUOY5IKZPI5TDQTIXUI74P7","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":"fbdcc10f2edea1a5e6484befa284e8264d043cd534e10efbdd60cb2da75c6e05","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-01-05T05:23:07Z","title_canon_sha256":"7741d2eef2a3a3d664a754115088a5da7fd7f0633ae148533a64d25d8ccf0fab"},"schema_version":"1.0","source":{"id":"2601.02430","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.02430","created_at":"2026-08-03T01:12:20Z"},{"alias_kind":"arxiv_version","alias_value":"2601.02430v3","created_at":"2026-08-03T01:12:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.02430","created_at":"2026-08-03T01:12:20Z"},{"alias_kind":"pith_short_12","alias_value":"HF2KUOY5IKZP","created_at":"2026-08-03T01:12:20Z"},{"alias_kind":"pith_short_16","alias_value":"HF2KUOY5IKZPI5TD","created_at":"2026-08-03T01:12:20Z"},{"alias_kind":"pith_short_8","alias_value":"HF2KUOY5","created_at":"2026-08-03T01:12:20Z"}],"graph_snapshots":[{"event_id":"sha256:1e6270f32aa57d311b66e715a50a4b2caae1545579d3213dc7d180591ca77aac","target":"graph","created_at":"2026-08-03T01:12:20Z","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/2601.02430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and commercial potential. However, building a benchmark for LLM-generated web apps remains challenging due to the need for real-world user requirements, generalizable evaluation metrics without relying on ground-truth implementations or test cases, and interpretable evaluation results. To address these challenges, we introduce WebCoderBench, the first real-world-collected, generalizable, and interpretable benchmark for web app generation. WebCoderBench comprise","authors_text":"Chenxu Liu, Tao Xie, Wei Yang, Yingjie Fu, Ying Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-01-05T05:23:07Z","title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.02430","kind":"arxiv","version":3},"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:e8d36429e9ab9ed7f89b9a5595d20774e546c26a38248a758d826813a99bf069","target":"record","created_at":"2026-08-03T01:12:20Z","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":"fbdcc10f2edea1a5e6484befa284e8264d043cd534e10efbdd60cb2da75c6e05","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-01-05T05:23:07Z","title_canon_sha256":"7741d2eef2a3a3d664a754115088a5da7fd7f0633ae148533a64d25d8ccf0fab"},"schema_version":"1.0","source":{"id":"2601.02430","kind":"arxiv","version":3}},"canonical_sha256":"3974aa3b1d42b2f4766384d17a23fc7fe00a4b7a89fb428a110c0819a35bfc93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3974aa3b1d42b2f4766384d17a23fc7fe00a4b7a89fb428a110c0819a35bfc93","first_computed_at":"2026-08-03T01:12:20.433936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:12:20.433936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+td3lR6D2riMqYM4zx8YLzj2HZAGxPWoPIz9FlHoHY141GTPTTsfzPmO9EpYxtAGKRggXCrm3IBwR0eBgWjhDg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:12:20.435780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.02430","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8d36429e9ab9ed7f89b9a5595d20774e546c26a38248a758d826813a99bf069","sha256:1e6270f32aa57d311b66e715a50a4b2caae1545579d3213dc7d180591ca77aac"],"state_sha256":"8a76e8964cb58f9329817c866e21e0a5f6ec2a16c7b1ff57bbada83886308e5d"}