{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T32VTLJGEBRGRVHT3DUNJF4ZFX","short_pith_number":"pith:T32VTLJG","schema_version":"1.0","canonical_sha256":"9ef559ad26206268d4f3d8e8d497992de1af7e456112fb96bf6064f60aca31c4","source":{"kind":"arxiv","id":"2606.03220","version":1},"attestation_state":"computed","paper":{"title":"WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Junjie Wang, Ruining Hu, Ruixu Zhang, Shouwei Ruan, Yiyao Yu, Yubin Wang, Yuhan Sun, Yuhan Suo, Yujiu Yang, Yuxiang Zhang, Yuxin Meng","submitted_at":"2026-06-02T06:29:40Z","abstract_excerpt":"Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a page works. We introduce WebRISE, which compiles task requirements into Interaction Contract Graphs (ICGs) of observable states, user-intent transitions, and DOM/visual assertions for implementation-agnostic browser execution. WebRISE spans 442 tasks across five input modalities (Text, Markdown, Sketch, Image, Video), with 5,495 transitions and 5,271 requirement checks that separate user-stated functions from implicit pr"},"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":"2606.03220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T06:29:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"924fd1cd7f80aafe40bb8289d04d11759ced19272c1bf9892dda0fa68c6d2633","abstract_canon_sha256":"6cfc0eceaefc55f0317460f8a7ee110143488eb76a24a5916fb2d203e30eb6ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:35.258363Z","signature_b64":"KLOnv1NC2E646OsuKs68WX8mbvAMvWCQmq+WA3dq0iRobkePs01fYopbACugC8zld9+2SAi6agcTzTaEGPOQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ef559ad26206268d4f3d8e8d497992de1af7e456112fb96bf6064f60aca31c4","last_reissued_at":"2026-06-03T01:05:35.257932Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:35.257932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Junjie Wang, Ruining Hu, Ruixu Zhang, Shouwei Ruan, Yiyao Yu, Yubin Wang, Yuhan Sun, Yuhan Suo, Yujiu Yang, Yuxiang Zhang, Yuxin Meng","submitted_at":"2026-06-02T06:29:40Z","abstract_excerpt":"Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a page works. We introduce WebRISE, which compiles task requirements into Interaction Contract Graphs (ICGs) of observable states, user-intent transitions, and DOM/visual assertions for implementation-agnostic browser execution. WebRISE spans 442 tasks across five input modalities (Text, Markdown, Sketch, Image, Video), with 5,495 transitions and 5,271 requirement checks that separate user-stated functions from implicit pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03220","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/2606.03220/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":"2606.03220","created_at":"2026-06-03T01:05:35.257996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03220v1","created_at":"2026-06-03T01:05:35.257996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03220","created_at":"2026-06-03T01:05:35.257996+00:00"},{"alias_kind":"pith_short_12","alias_value":"T32VTLJGEBRG","created_at":"2026-06-03T01:05:35.257996+00:00"},{"alias_kind":"pith_short_16","alias_value":"T32VTLJGEBRGRVHT","created_at":"2026-06-03T01:05:35.257996+00:00"},{"alias_kind":"pith_short_8","alias_value":"T32VTLJG","created_at":"2026-06-03T01:05:35.257996+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/T32VTLJGEBRGRVHT3DUNJF4ZFX","json":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX.json","graph_json":"https://pith.science/api/pith-number/T32VTLJGEBRGRVHT3DUNJF4ZFX/graph.json","events_json":"https://pith.science/api/pith-number/T32VTLJGEBRGRVHT3DUNJF4ZFX/events.json","paper":"https://pith.science/paper/T32VTLJG"},"agent_actions":{"view_html":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX","download_json":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX.json","view_paper":"https://pith.science/paper/T32VTLJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03220&json=true","fetch_graph":"https://pith.science/api/pith-number/T32VTLJGEBRGRVHT3DUNJF4ZFX/graph.json","fetch_events":"https://pith.science/api/pith-number/T32VTLJGEBRGRVHT3DUNJF4ZFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX/action/storage_attestation","attest_author":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX/action/author_attestation","sign_citation":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX/action/citation_signature","submit_replication":"https://pith.science/pith/T32VTLJGEBRGRVHT3DUNJF4ZFX/action/replication_record"}},"created_at":"2026-06-03T01:05:35.257996+00:00","updated_at":"2026-06-03T01:05:35.257996+00:00"}