{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RPGMKVZ6FHKMMK4RZFAWILSNXR","short_pith_number":"pith:RPGMKVZ6","schema_version":"1.0","canonical_sha256":"8bccc5573e29d4c62b91c941642e4dbc72b6ebdbaf39420b3f6a9eb1cec9e9b1","source":{"kind":"arxiv","id":"2506.13832","version":2},"attestation_state":"computed","paper":{"title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bing Zhao, Dandan Wang, Hongda Zhu, Jingzhe Ding, Siyao Liu, Tong Liu, Yanan Liu, Yiwen Zhang, Zhaojian Li","submitted_at":"2025-06-16T03:20:31Z","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 "},"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":"2506.13832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-16T03:20:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d745853fbed578046b1e6f3692a534474fb23dd9b045a35ad78ab8bede689cf","abstract_canon_sha256":"80c3682808dcc97a0ea312cda43f336b82c207e769ef6e5a6c3609ab2a03c15c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:30.740770Z","signature_b64":"Er+RwPAbB6+Nl9zJYJYc96b63Cx+Ml777UyBkdb9m6Hio3g/tyPGjJ+a8m9egb3MspWg0aIsJ1xGcAPfahc/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bccc5573e29d4c62b91c941642e4dbc72b6ebdbaf39420b3f6a9eb1cec9e9b1","last_reissued_at":"2026-07-05T11:23:30.740261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:30.740261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bing Zhao, Dandan Wang, Hongda Zhu, Jingzhe Ding, Siyao Liu, Tong Liu, Yanan Liu, Yiwen Zhang, Zhaojian Li","submitted_at":"2025-06-16T03:20:31Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13832","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/2506.13832/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":"2506.13832","created_at":"2026-07-05T11:23:30.740322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13832v2","created_at":"2026-07-05T11:23:30.740322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13832","created_at":"2026-07-05T11:23:30.740322+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPGMKVZ6FHKM","created_at":"2026-07-05T11:23:30.740322+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPGMKVZ6FHKMMK4R","created_at":"2026-07-05T11:23:30.740322+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPGMKVZ6","created_at":"2026-07-05T11:23:30.740322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05920","citing_title":"Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01869","citing_title":"WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30000","citing_title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19750","citing_title":"Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18394","citing_title":"OpenGame: Open Agentic Coding for Games","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR","json":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR.json","graph_json":"https://pith.science/api/pith-number/RPGMKVZ6FHKMMK4RZFAWILSNXR/graph.json","events_json":"https://pith.science/api/pith-number/RPGMKVZ6FHKMMK4RZFAWILSNXR/events.json","paper":"https://pith.science/paper/RPGMKVZ6"},"agent_actions":{"view_html":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR","download_json":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR.json","view_paper":"https://pith.science/paper/RPGMKVZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13832&json=true","fetch_graph":"https://pith.science/api/pith-number/RPGMKVZ6FHKMMK4RZFAWILSNXR/graph.json","fetch_events":"https://pith.science/api/pith-number/RPGMKVZ6FHKMMK4RZFAWILSNXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR/action/storage_attestation","attest_author":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR/action/author_attestation","sign_citation":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR/action/citation_signature","submit_replication":"https://pith.science/pith/RPGMKVZ6FHKMMK4RZFAWILSNXR/action/replication_record"}},"created_at":"2026-07-05T11:23:30.740322+00:00","updated_at":"2026-07-05T11:23:30.740322+00:00"}