{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5HKDSMBZ3WKFVM43SHIPRNYLDP","short_pith_number":"pith:5HKDSMBZ","schema_version":"1.0","canonical_sha256":"e9d4393039dd945ab39b91d0f8b70b1bc7bd539c02b05f3b14c3d7fc1131c37a","source":{"kind":"arxiv","id":"2505.17399","version":2},"attestation_state":"computed","paper":{"title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyu Sun, Huichen Will Wang, Jiawei Gu, Linjie Li, Yu Cheng","submitted_at":"2025-05-23T02:16:11Z","abstract_excerpt":"Front-end engineering involves a complex workflow where engineers conceptualize designs, translate them into code, and iteratively refine the implementation. While recent benchmarks primarily focus on converting visual designs to code, we present FullFront, a benchmark designed to evaluate Multimodal Large Language Models (MLLMs) \\textbf{across the full front-end development pipeline}. FullFront assesses three fundamental tasks that map directly to the front-end engineering pipeline: Webpage Design (conceptualization phase), Webpage Perception QA (comprehension of visual organization and eleme"},"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":"2505.17399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T02:16:11Z","cross_cats_sorted":[],"title_canon_sha256":"72a24f9b7a60702f79199d3d26e990f2b28d4671bc442b16b699a3933600942f","abstract_canon_sha256":"2d8cc9c4a4a20c03900ae55aaa9a34e121df4e88687b3000155276738a9c2cdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:47.761452Z","signature_b64":"98w1TuthnigjpK0JUahlfWvd7p4iEGZxH+0RQ4BRP8mGlk3GDeiDIDShCM1xYuPTs8cKJ7yBuvM+PP9W9GgmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d4393039dd945ab39b91d0f8b70b1bc7bd539c02b05f3b14c3d7fc1131c37a","last_reissued_at":"2026-07-05T11:09:47.760913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:47.760913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyu Sun, Huichen Will Wang, Jiawei Gu, Linjie Li, Yu Cheng","submitted_at":"2025-05-23T02:16:11Z","abstract_excerpt":"Front-end engineering involves a complex workflow where engineers conceptualize designs, translate them into code, and iteratively refine the implementation. While recent benchmarks primarily focus on converting visual designs to code, we present FullFront, a benchmark designed to evaluate Multimodal Large Language Models (MLLMs) \\textbf{across the full front-end development pipeline}. FullFront assesses three fundamental tasks that map directly to the front-end engineering pipeline: Webpage Design (conceptualization phase), Webpage Perception QA (comprehension of visual organization and eleme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17399","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/2505.17399/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":"2505.17399","created_at":"2026-07-05T11:09:47.760975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17399v2","created_at":"2026-07-05T11:09:47.760975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17399","created_at":"2026-07-05T11:09:47.760975+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HKDSMBZ3WKF","created_at":"2026-07-05T11:09:47.760975+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HKDSMBZ3WKFVM43","created_at":"2026-07-05T11:09:47.760975+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HKDSMBZ","created_at":"2026-07-05T11:09:47.760975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26807","citing_title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30000","citing_title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15309","citing_title":"MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP","json":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP.json","graph_json":"https://pith.science/api/pith-number/5HKDSMBZ3WKFVM43SHIPRNYLDP/graph.json","events_json":"https://pith.science/api/pith-number/5HKDSMBZ3WKFVM43SHIPRNYLDP/events.json","paper":"https://pith.science/paper/5HKDSMBZ"},"agent_actions":{"view_html":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP","download_json":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP.json","view_paper":"https://pith.science/paper/5HKDSMBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17399&json=true","fetch_graph":"https://pith.science/api/pith-number/5HKDSMBZ3WKFVM43SHIPRNYLDP/graph.json","fetch_events":"https://pith.science/api/pith-number/5HKDSMBZ3WKFVM43SHIPRNYLDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP/action/storage_attestation","attest_author":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP/action/author_attestation","sign_citation":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP/action/citation_signature","submit_replication":"https://pith.science/pith/5HKDSMBZ3WKFVM43SHIPRNYLDP/action/replication_record"}},"created_at":"2026-07-05T11:09:47.760975+00:00","updated_at":"2026-07-05T11:09:47.760975+00:00"}