{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RPGMKVZ6FHKMMK4RZFAWILSNXR","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":"80c3682808dcc97a0ea312cda43f336b82c207e769ef6e5a6c3609ab2a03c15c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-16T03:20:31Z","title_canon_sha256":"1d745853fbed578046b1e6f3692a534474fb23dd9b045a35ad78ab8bede689cf"},"schema_version":"1.0","source":{"id":"2506.13832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13832","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13832v2","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13832","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"RPGMKVZ6FHKM","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"RPGMKVZ6FHKMMK4R","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"RPGMKVZ6","created_at":"2026-07-05T11:23:30Z"}],"graph_snapshots":[{"event_id":"sha256:97d63764a4b7c2ca16c2b6ab1ae94ea78de3e61ba42e1a0da9befc704ca9ec90","target":"graph","created_at":"2026-07-05T11:23:30Z","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/2506.13832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly simplistic, test cases often lack rigor, and end-to-end validation is absent. These issues hinder the accurate assessment of model performance. To address these challenges, we present FrontendBench, a benchmark co-developed by humans and LLMs. FrontendBench categorizes tasks based on code functionality and incorporates interactive test scenarios, enabling a more comprehensive and practical evaluation of front-end code ","authors_text":"Bing Zhao, Dandan Wang, Hongda Zhu, Jingzhe Ding, Siyao Liu, Tong Liu, Yanan Liu, Yiwen Zhang, Zhaojian Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-16T03:20:31Z","title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13832","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":"sha256:9da92bee5be389540438a730f6fba393538f3b66ef31b5229a16d36405b57d7a","target":"record","created_at":"2026-07-05T11:23:30Z","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":"80c3682808dcc97a0ea312cda43f336b82c207e769ef6e5a6c3609ab2a03c15c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-16T03:20:31Z","title_canon_sha256":"1d745853fbed578046b1e6f3692a534474fb23dd9b045a35ad78ab8bede689cf"},"schema_version":"1.0","source":{"id":"2506.13832","kind":"arxiv","version":2}},"canonical_sha256":"8bccc5573e29d4c62b91c941642e4dbc72b6ebdbaf39420b3f6a9eb1cec9e9b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bccc5573e29d4c62b91c941642e4dbc72b6ebdbaf39420b3f6a9eb1cec9e9b1","first_computed_at":"2026-07-05T11:23:30.740261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:30.740261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Er+RwPAbB6+Nl9zJYJYc96b63Cx+Ml777UyBkdb9m6Hio3g/tyPGjJ+a8m9egb3MspWg0aIsJ1xGcAPfahc/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:30.740770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9da92bee5be389540438a730f6fba393538f3b66ef31b5229a16d36405b57d7a","sha256:97d63764a4b7c2ca16c2b6ab1ae94ea78de3e61ba42e1a0da9befc704ca9ec90"],"state_sha256":"361be60e7029728f0ae7c9c94c4ffbf829107bc32176c647277eff5043b602d5"}