{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HC3QEBQA7XEB5ZI4EG3WOQ7OEW","short_pith_number":"pith:HC3QEBQA","schema_version":"1.0","canonical_sha256":"38b7020600fdc81ee51c21b76743ee2597683c39e1aa01dc6b078fa4ac7491cb","source":{"kind":"arxiv","id":"2608.03474","version":1},"attestation_state":"computed","paper":{"title":"MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Wan, Haohan Liu, Qiming Li, Shujie Hu, Songxiang Liu, Xiaocheng Feng","submitted_at":"2026-08-04T11:14:00Z","abstract_excerpt":"Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, overlooking the iterative workflow of real-world frontend engineering, where developers repeatedly reconstruct missing regions and modify localized elements within existing codebases. To bridge this gap, we introduce MT-Web2Code, the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification, which contains 102 tas"},"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":"2608.03474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T11:14:00Z","cross_cats_sorted":[],"title_canon_sha256":"867f12f46902bf0949383bc19fe4fa5e8fac026b8e6bea07f5cae625bca071a0","abstract_canon_sha256":"1c9b73acf86a0232049f6e2e81455f42d9d27ded8c407e72fd398713eb212205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:55.443045Z","signature_b64":"efogvpMZW7mrsbIuyTr5bPiYzcv90X7eJTUnUJtpB28Cr26G5d4lGsti0t3BYtQ3NxDcPcXHxq1v1yH2Ro/sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b7020600fdc81ee51c21b76743ee2597683c39e1aa01dc6b078fa4ac7491cb","last_reissued_at":"2026-08-05T01:35:55.441586Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:55.441586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Wan, Haohan Liu, Qiming Li, Shujie Hu, Songxiang Liu, Xiaocheng Feng","submitted_at":"2026-08-04T11:14:00Z","abstract_excerpt":"Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, overlooking the iterative workflow of real-world frontend engineering, where developers repeatedly reconstruct missing regions and modify localized elements within existing codebases. To bridge this gap, we introduce MT-Web2Code, the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification, which contains 102 tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03474","kind":"arxiv","version":1},"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/2608.03474/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":"2608.03474","created_at":"2026-08-05T01:35:55.442067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03474v1","created_at":"2026-08-05T01:35:55.442067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03474","created_at":"2026-08-05T01:35:55.442067+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC3QEBQA7XEB","created_at":"2026-08-05T01:35:55.442067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC3QEBQA7XEB5ZI4","created_at":"2026-08-05T01:35:55.442067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC3QEBQA","created_at":"2026-08-05T01:35:55.442067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW","json":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW.json","graph_json":"https://pith.science/api/pith-number/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/graph.json","events_json":"https://pith.science/api/pith-number/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/events.json","paper":"https://pith.science/paper/HC3QEBQA"},"agent_actions":{"view_html":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW","download_json":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW.json","view_paper":"https://pith.science/paper/HC3QEBQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03474&json=true","fetch_graph":"https://pith.science/api/pith-number/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/graph.json","fetch_events":"https://pith.science/api/pith-number/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/action/storage_attestation","attest_author":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/action/author_attestation","sign_citation":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/action/citation_signature","submit_replication":"https://pith.science/pith/HC3QEBQA7XEB5ZI4EG3WOQ7OEW/action/replication_record"}},"created_at":"2026-08-05T01:35:55.442067+00:00","updated_at":"2026-08-05T01:35:55.442067+00:00"}