{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HF2KUOY5IKZPI5TDQTIXUI74P7","short_pith_number":"pith:HF2KUOY5","schema_version":"1.0","canonical_sha256":"3974aa3b1d42b2f4766384d17a23fc7fe00a4b7a89fb428a110c0819a35bfc93","source":{"kind":"arxiv","id":"2601.02430","version":3},"attestation_state":"computed","paper":{"title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenxu Liu, Tao Xie, Wei Yang, Yingjie Fu, Ying Zhang","submitted_at":"2026-01-05T05:23:07Z","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"},"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":"2601.02430","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-01-05T05:23:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7741d2eef2a3a3d664a754115088a5da7fd7f0633ae148533a64d25d8ccf0fab","abstract_canon_sha256":"fbdcc10f2edea1a5e6484befa284e8264d043cd534e10efbdd60cb2da75c6e05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:12:20.435780Z","signature_b64":"+td3lR6D2riMqYM4zx8YLzj2HZAGxPWoPIz9FlHoHY141GTPTTsfzPmO9EpYxtAGKRggXCrm3IBwR0eBgWjhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3974aa3b1d42b2f4766384d17a23fc7fe00a4b7a89fb428a110c0819a35bfc93","last_reissued_at":"2026-08-03T01:12:20.433936Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:12:20.433936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenxu Liu, Tao Xie, Wei Yang, Yingjie Fu, Ying Zhang","submitted_at":"2026-01-05T05:23:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.02430","kind":"arxiv","version":3},"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/2601.02430/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":"2601.02430","created_at":"2026-08-03T01:12:20.434914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.02430v3","created_at":"2026-08-03T01:12:20.434914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.02430","created_at":"2026-08-03T01:12:20.434914+00:00"},{"alias_kind":"pith_short_12","alias_value":"HF2KUOY5IKZP","created_at":"2026-08-03T01:12:20.434914+00:00"},{"alias_kind":"pith_short_16","alias_value":"HF2KUOY5IKZPI5TD","created_at":"2026-08-03T01:12:20.434914+00:00"},{"alias_kind":"pith_short_8","alias_value":"HF2KUOY5","created_at":"2026-08-03T01:12:20.434914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.01869","citing_title":"WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26807","citing_title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30000","citing_title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00750","citing_title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17637","citing_title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17637","citing_title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04637","citing_title":"SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7","json":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7.json","graph_json":"https://pith.science/api/pith-number/HF2KUOY5IKZPI5TDQTIXUI74P7/graph.json","events_json":"https://pith.science/api/pith-number/HF2KUOY5IKZPI5TDQTIXUI74P7/events.json","paper":"https://pith.science/paper/HF2KUOY5"},"agent_actions":{"view_html":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7","download_json":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7.json","view_paper":"https://pith.science/paper/HF2KUOY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.02430&json=true","fetch_graph":"https://pith.science/api/pith-number/HF2KUOY5IKZPI5TDQTIXUI74P7/graph.json","fetch_events":"https://pith.science/api/pith-number/HF2KUOY5IKZPI5TDQTIXUI74P7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7/action/storage_attestation","attest_author":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7/action/author_attestation","sign_citation":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7/action/citation_signature","submit_replication":"https://pith.science/pith/HF2KUOY5IKZPI5TDQTIXUI74P7/action/replication_record"}},"created_at":"2026-08-03T01:12:20.434914+00:00","updated_at":"2026-08-03T01:12:20.434914+00:00"}