{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WIH2RIX74YJIA64SZ3QKM2OK3B","short_pith_number":"pith:WIH2RIX7","canonical_record":{"source":{"id":"2406.20098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:59:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"02dd0154f6ac84f16609e00a1b096e6a7ac894788b55d21938fa3192bc6c8b92","abstract_canon_sha256":"e35bd794c25625340ff109adedb11c9316645539107acf100ad5606c9fa468ed"},"schema_version":"1.0"},"canonical_sha256":"b20fa8a2ffe612807b92cee0a669cad85e27188a2897436ed2e793f1abf76d53","source":{"kind":"arxiv","id":"2406.20098","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20098","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20098v2","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20098","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"WIH2RIX74YJI","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"WIH2RIX74YJIA64S","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"WIH2RIX7","created_at":"2026-07-05T09:36:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WIH2RIX74YJIA64SZ3QKM2OK3B","target":"record","payload":{"canonical_record":{"source":{"id":"2406.20098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:59:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"02dd0154f6ac84f16609e00a1b096e6a7ac894788b55d21938fa3192bc6c8b92","abstract_canon_sha256":"e35bd794c25625340ff109adedb11c9316645539107acf100ad5606c9fa468ed"},"schema_version":"1.0"},"canonical_sha256":"b20fa8a2ffe612807b92cee0a669cad85e27188a2897436ed2e793f1abf76d53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:12.942991Z","signature_b64":"tlhsB306tcV9t/GygBjUMmQjopBgej2ldSA3CVIJM7ysjrFW40obOOwr6myJEjFG7Sy76ugeDMBPPWrY+qMLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b20fa8a2ffe612807b92cee0a669cad85e27188a2897436ed2e793f1abf76d53","last_reissued_at":"2026-07-05T09:36:12.942452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:12.942452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.20098","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6s23Mj5KGFIGWiSOd9nS0HpNAf9zfSf0DEem1SWXp6SAy39h9a6KQBtWEGxdu0/aZpNiQMCk1RFDSs43jT4lBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:46:26.432412Z"},"content_sha256":"88f123634f25bb0711be277226514ebb9b682b22ba0540b94fb7809a866d9694","schema_version":"1.0","event_id":"sha256:88f123634f25bb0711be277226514ebb9b682b22ba0540b94fb7809a866d9694"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WIH2RIX74YJIA64SZ3QKM2OK3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Eric P. Xing, Haokun Lin, Haonan Li, Jinhong Wang, Junbo Li, Mingkai Deng, Mohammad Qazim Bhat, Preslav Nakov, Rusiru Thushara, Sukmin Yun, Tianhua Tao, Timothy Baldwin, Xiaodan Liang, Yongxin Wang, Zhengzhong Liu, Zhiqiang Shen, Zutao Jiang","submitted_at":"2024-06-28T17:59:46Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio in a variety of understanding and generation tasks. However, current MLLMs are surprisingly poor at understanding webpage screenshots and generating their corresponding HTML code. To address this problem, we propose $\\texttt{Web2Code}$, a benchmark consisting of a new large-scale webpage-to-code dataset for instruction tuning and an evaluation framework for the webpage understanding and HTML code translation abilities of MLLMs. For dataset construction, we leverage pretraine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20098","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/2406.20098/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0G2NBVl+/uDp4CLu9FumMEm0Qh1AqG3bAF/Mr8FUG58DBYadchfPOVUWcNc9KybDc67M2U/aoYI41E+cjc3bAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:46:26.432788Z"},"content_sha256":"98ce7a779adbd465bff567a033ca0f5079d0c88d83b839ebc5dce659596f3acb","schema_version":"1.0","event_id":"sha256:98ce7a779adbd465bff567a033ca0f5079d0c88d83b839ebc5dce659596f3acb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIH2RIX74YJIA64SZ3QKM2OK3B/bundle.json","state_url":"https://pith.science/pith/WIH2RIX74YJIA64SZ3QKM2OK3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIH2RIX74YJIA64SZ3QKM2OK3B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-17T02:46:26Z","links":{"resolver":"https://pith.science/pith/WIH2RIX74YJIA64SZ3QKM2OK3B","bundle":"https://pith.science/pith/WIH2RIX74YJIA64SZ3QKM2OK3B/bundle.json","state":"https://pith.science/pith/WIH2RIX74YJIA64SZ3QKM2OK3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIH2RIX74YJIA64SZ3QKM2OK3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WIH2RIX74YJIA64SZ3QKM2OK3B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e35bd794c25625340ff109adedb11c9316645539107acf100ad5606c9fa468ed","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:59:46Z","title_canon_sha256":"02dd0154f6ac84f16609e00a1b096e6a7ac894788b55d21938fa3192bc6c8b92"},"schema_version":"1.0","source":{"id":"2406.20098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20098","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20098v2","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20098","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"WIH2RIX74YJI","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"WIH2RIX74YJIA64S","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"WIH2RIX7","created_at":"2026-07-05T09:36:12Z"}],"graph_snapshots":[{"event_id":"sha256:98ce7a779adbd465bff567a033ca0f5079d0c88d83b839ebc5dce659596f3acb","target":"graph","created_at":"2026-07-05T09:36:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.20098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio in a variety of understanding and generation tasks. However, current MLLMs are surprisingly poor at understanding webpage screenshots and generating their corresponding HTML code. To address this problem, we propose $\\texttt{Web2Code}$, a benchmark consisting of a new large-scale webpage-to-code dataset for instruction tuning and an evaluation framework for the webpage understanding and HTML code translation abilities of MLLMs. For dataset construction, we leverage pretraine","authors_text":"Eric P. Xing, Haokun Lin, Haonan Li, Jinhong Wang, Junbo Li, Mingkai Deng, Mohammad Qazim Bhat, Preslav Nakov, Rusiru Thushara, Sukmin Yun, Tianhua Tao, Timothy Baldwin, Xiaodan Liang, Yongxin Wang, Zhengzhong Liu, Zhiqiang Shen, Zutao Jiang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:59:46Z","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20098","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:88f123634f25bb0711be277226514ebb9b682b22ba0540b94fb7809a866d9694","target":"record","created_at":"2026-07-05T09:36:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e35bd794c25625340ff109adedb11c9316645539107acf100ad5606c9fa468ed","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:59:46Z","title_canon_sha256":"02dd0154f6ac84f16609e00a1b096e6a7ac894788b55d21938fa3192bc6c8b92"},"schema_version":"1.0","source":{"id":"2406.20098","kind":"arxiv","version":2}},"canonical_sha256":"b20fa8a2ffe612807b92cee0a669cad85e27188a2897436ed2e793f1abf76d53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b20fa8a2ffe612807b92cee0a669cad85e27188a2897436ed2e793f1abf76d53","first_computed_at":"2026-07-05T09:36:12.942452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:12.942452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tlhsB306tcV9t/GygBjUMmQjopBgej2ldSA3CVIJM7ysjrFW40obOOwr6myJEjFG7Sy76ugeDMBPPWrY+qMLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:12.942991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.20098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88f123634f25bb0711be277226514ebb9b682b22ba0540b94fb7809a866d9694","sha256:98ce7a779adbd465bff567a033ca0f5079d0c88d83b839ebc5dce659596f3acb"],"state_sha256":"29dfb42eabb530debbe81fa34610581c1cb6ec446dc124befbd8444c388f796d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9kBpqdYhx7MKHsmfOAQHZgu8OJutjeuOiLjrGOp3i3KNcvK7Zap7L4hl9EHSHrXhNxbbK2k0DoUT/Z2MXXBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T02:46:26.434872Z","bundle_sha256":"6a7680ddd2c58834e5d31e0a227b766366dadffb294e838fc5eee5bd9f7163da"}}