{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FTS3ES6LIBR37E5FOHXTBNLCA6","short_pith_number":"pith:FTS3ES6L","schema_version":"1.0","canonical_sha256":"2ce5b24bcb4063bf93a571ef30b56207be03e2ff23b52c1d392269d246945043","source":{"kind":"arxiv","id":"2605.26144","version":1},"attestation_state":"computed","paper":{"title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.SE","authors_text":"Jiawei (Joe) Zhou, Jingdi Chen, JunJia Guo, Yuhang Yao","submitted_at":"2026-05-22T20:29:12Z","abstract_excerpt":"We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with "},"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":"2605.26144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-22T20:29:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e2624a3836aab389d223536debbebe16cb58175e599651f59cad6e5eb98e58c2","abstract_canon_sha256":"2cea0df84d0199853f197af33d4eb5e29b82c7c7a1405efa9f500f5a35158155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T00:04:26.098917Z","signature_b64":"orSQsWsd+xbuvGdpVIxoZsmoJ/kYrdAqgoXINDONRMQWM3Z/jZQFyyeVyxWLew5ZS62kxlIcSzFy0D+wLxGVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ce5b24bcb4063bf93a571ef30b56207be03e2ff23b52c1d392269d246945043","last_reissued_at":"2026-05-27T00:04:26.098008Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T00:04:26.098008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.SE","authors_text":"Jiawei (Joe) Zhou, Jingdi Chen, JunJia Guo, Yuhang Yao","submitted_at":"2026-05-22T20:29:12Z","abstract_excerpt":"We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26144","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/2605.26144/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":"2605.26144","created_at":"2026-05-27T00:04:26.098132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26144v1","created_at":"2026-05-27T00:04:26.098132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26144","created_at":"2026-05-27T00:04:26.098132+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTS3ES6LIBR3","created_at":"2026-05-27T00:04:26.098132+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTS3ES6LIBR37E5F","created_at":"2026-05-27T00:04:26.098132+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTS3ES6L","created_at":"2026-05-27T00:04:26.098132+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/FTS3ES6LIBR37E5FOHXTBNLCA6","json":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6.json","graph_json":"https://pith.science/api/pith-number/FTS3ES6LIBR37E5FOHXTBNLCA6/graph.json","events_json":"https://pith.science/api/pith-number/FTS3ES6LIBR37E5FOHXTBNLCA6/events.json","paper":"https://pith.science/paper/FTS3ES6L"},"agent_actions":{"view_html":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6","download_json":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6.json","view_paper":"https://pith.science/paper/FTS3ES6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26144&json=true","fetch_graph":"https://pith.science/api/pith-number/FTS3ES6LIBR37E5FOHXTBNLCA6/graph.json","fetch_events":"https://pith.science/api/pith-number/FTS3ES6LIBR37E5FOHXTBNLCA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6/action/storage_attestation","attest_author":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6/action/author_attestation","sign_citation":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6/action/citation_signature","submit_replication":"https://pith.science/pith/FTS3ES6LIBR37E5FOHXTBNLCA6/action/replication_record"}},"created_at":"2026-05-27T00:04:26.098132+00:00","updated_at":"2026-05-27T00:04:26.098132+00:00"}