{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JV3XXMOYDD5Q2V3DGSJBSFIEKI","short_pith_number":"pith:JV3XXMOY","canonical_record":{"source":{"id":"2410.13824","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:48:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dfbb8927467a899bed5ebada7f9d8ee2bd38920f3725978502bf2bbefedcacfc","abstract_canon_sha256":"cbf0e7d918474435bd5824b7262a6e3271281b3b3d7afc1437d53b7e68b33154"},"schema_version":"1.0"},"canonical_sha256":"4d777bb1d818fb0d57633492191504522de9b1a03082659caecad7140bad846e","source":{"kind":"arxiv","id":"2410.13824","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13824","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13824v3","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13824","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"JV3XXMOYDD5Q","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"JV3XXMOYDD5Q2V3D","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"JV3XXMOY","created_at":"2026-07-05T09:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JV3XXMOYDD5Q2V3DGSJBSFIEKI","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13824","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:48:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dfbb8927467a899bed5ebada7f9d8ee2bd38920f3725978502bf2bbefedcacfc","abstract_canon_sha256":"cbf0e7d918474435bd5824b7262a6e3271281b3b3d7afc1437d53b7e68b33154"},"schema_version":"1.0"},"canonical_sha256":"4d777bb1d818fb0d57633492191504522de9b1a03082659caecad7140bad846e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:49.756070Z","signature_b64":"HXQ2a0MQmaDHbAssxJ+WZZ302uBDXXi/9aK/UQvW91hur8EqOJ6SnAwA9GiCrreLm7GSy76WsaUTf7SyNk3FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d777bb1d818fb0d57633492191504522de9b1a03082659caecad7140bad846e","last_reissued_at":"2026-07-05T09:31:49.755392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:49.755392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13824","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HajSeyVRLl48u8jTvQJlGwc87px6E6YTkphevfIGwYeemt3mbXcAQYeawVF530Kw47kRGW6e3S/3lje6vdowBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:49:23.994276Z"},"content_sha256":"302feed893b5872d26ab245193236c4cc252a689c79b7d2a7aad0e6d33ceaa60","schema_version":"1.0","event_id":"sha256:302feed893b5872d26ab245193236c4cc252a689c79b7d2a7aad0e6d33ceaa60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JV3XXMOYDD5Q2V3DGSJBSFIEKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Webpage UIs for Text-Rich Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenyan Xiong, Graham Neubig, Junpeng Liu, Tianyue Ou, Wai Lam, Wenhu Chen, Xiang Yue, Yifan Song, Yuxiao Qu","submitted_at":"2024-10-17T17:48:54Z","abstract_excerpt":"Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To enhance this capability, we propose synthesizing general multimodal instructions from webpage UIs using text-based large language models (LLMs). Despite lacking direct visual input, text-based LLMs are able to process structured text representations from webpage accessibility trees. These instructions are then paired with UI screenshots to train multimodal models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13824","kind":"arxiv","version":3},"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/2410.13824/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":"2026-07-05T09:31:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M9Xtq+mXfFt0OWGCh0rm2wE7+88kdl7vu813lfEX+/5a5iO6C48/yYd/Y1HSkR+4bt9CI+o4vIlft/r48N0tDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:49:23.995344Z"},"content_sha256":"62a7b5eaab1b91906f747ac22e541660becea9b01e8bafba160e90ef4b4ab95e","schema_version":"1.0","event_id":"sha256:62a7b5eaab1b91906f747ac22e541660becea9b01e8bafba160e90ef4b4ab95e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI/bundle.json","state_url":"https://pith.science/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI/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":"2026-08-14T10:49:23Z","links":{"resolver":"https://pith.science/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI","bundle":"https://pith.science/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI/bundle.json","state":"https://pith.science/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JV3XXMOYDD5Q2V3DGSJBSFIEKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JV3XXMOYDD5Q2V3DGSJBSFIEKI","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":"cbf0e7d918474435bd5824b7262a6e3271281b3b3d7afc1437d53b7e68b33154","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:48:54Z","title_canon_sha256":"dfbb8927467a899bed5ebada7f9d8ee2bd38920f3725978502bf2bbefedcacfc"},"schema_version":"1.0","source":{"id":"2410.13824","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13824","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13824v3","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13824","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"JV3XXMOYDD5Q","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"JV3XXMOYDD5Q2V3D","created_at":"2026-07-05T09:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"JV3XXMOY","created_at":"2026-07-05T09:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:62a7b5eaab1b91906f747ac22e541660becea9b01e8bafba160e90ef4b4ab95e","target":"graph","created_at":"2026-07-05T09:31:49Z","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/2410.13824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To enhance this capability, we propose synthesizing general multimodal instructions from webpage UIs using text-based large language models (LLMs). Despite lacking direct visual input, text-based LLMs are able to process structured text representations from webpage accessibility trees. These instructions are then paired with UI screenshots to train multimodal models","authors_text":"Chenyan Xiong, Graham Neubig, Junpeng Liu, Tianyue Ou, Wai Lam, Wenhu Chen, Xiang Yue, Yifan Song, Yuxiao Qu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:48:54Z","title":"Harnessing Webpage UIs for Text-Rich Visual Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13824","kind":"arxiv","version":3},"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":"sha256:302feed893b5872d26ab245193236c4cc252a689c79b7d2a7aad0e6d33ceaa60","target":"record","created_at":"2026-07-05T09:31:49Z","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":"cbf0e7d918474435bd5824b7262a6e3271281b3b3d7afc1437d53b7e68b33154","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:48:54Z","title_canon_sha256":"dfbb8927467a899bed5ebada7f9d8ee2bd38920f3725978502bf2bbefedcacfc"},"schema_version":"1.0","source":{"id":"2410.13824","kind":"arxiv","version":3}},"canonical_sha256":"4d777bb1d818fb0d57633492191504522de9b1a03082659caecad7140bad846e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d777bb1d818fb0d57633492191504522de9b1a03082659caecad7140bad846e","first_computed_at":"2026-07-05T09:31:49.755392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:49.755392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXQ2a0MQmaDHbAssxJ+WZZ302uBDXXi/9aK/UQvW91hur8EqOJ6SnAwA9GiCrreLm7GSy76WsaUTf7SyNk3FDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:49.756070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13824","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:302feed893b5872d26ab245193236c4cc252a689c79b7d2a7aad0e6d33ceaa60","sha256:62a7b5eaab1b91906f747ac22e541660becea9b01e8bafba160e90ef4b4ab95e"],"state_sha256":"ade54a2e51f04ce433b239d0e46c419afa7ff530fafaf964cff1f92c8495472d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2W3fEm7gGc2ajMG/DlgKWtljSjaD+wSCUKjq44meslU/mcj8rhLN5o2xJXh7LLUaiQJrH8UJzx6r3Mc8LCDtBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:49:24.002148Z","bundle_sha256":"57298c8ee27cd539b11d01092529f6b9120e3a54634dda701fb8592005761ab4"}}