{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JOLKPA55LMTNFEJS5NT7MV75U4","short_pith_number":"pith:JOLKPA55","schema_version":"1.0","canonical_sha256":"4b96a783bd5b26d29132eb67f657fda70598d10586df0d05fda7ba0551ce4c6f","source":{"kind":"arxiv","id":"2209.08199","version":4},"attestation_state":"computed","paper":{"title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.CL","authors_text":"Fedir Zubach, Gilles Baechler, Jason Lin, Jindong Chen, Maria Wang, Srinivas Sunkara, Victor Carbune, Yu-Chung Hsiao, Yun Zhu","submitted_at":"2022-09-16T23:49:00Z","abstract_excerpt":"We introduce ScreenQA, a novel benchmarking dataset designed to advance screen content understanding through question answering. The existing screen datasets are focused either on low-level structural and component understanding, or on a much higher-level composite task such as navigation and task completion for autonomous agents. ScreenQA attempts to bridge this gap. By annotating 86k question-answer pairs over the RICO dataset, we aim to benchmark the screen reading comprehension capacity, thereby laying the foundation for vision-based automation over screenshots. Our annotations encompass f"},"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":"2209.08199","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-16T23:49:00Z","cross_cats_sorted":["cs.CV","cs.HC"],"title_canon_sha256":"9500fe23338e8c43b8b8c6021efab9fd9a45b677f7e7ec839e5a6576cfbff3b1","abstract_canon_sha256":"a73fb2371a9ee3abb3685ded1410ed04a0a51c406d814fbfa4d8106933cf1ae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:11.974874Z","signature_b64":"QS6ECQsh0KvlgcHr9bIzw8eRxGP8DLiuCjtExVS5h1MROwK3+v7HYZCLoADdpGtNbqCDxDQJVEZgG6fDsBfABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b96a783bd5b26d29132eb67f657fda70598d10586df0d05fda7ba0551ce4c6f","last_reissued_at":"2026-07-05T10:11:11.974425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:11.974425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.CL","authors_text":"Fedir Zubach, Gilles Baechler, Jason Lin, Jindong Chen, Maria Wang, Srinivas Sunkara, Victor Carbune, Yu-Chung Hsiao, Yun Zhu","submitted_at":"2022-09-16T23:49:00Z","abstract_excerpt":"We introduce ScreenQA, a novel benchmarking dataset designed to advance screen content understanding through question answering. The existing screen datasets are focused either on low-level structural and component understanding, or on a much higher-level composite task such as navigation and task completion for autonomous agents. ScreenQA attempts to bridge this gap. By annotating 86k question-answer pairs over the RICO dataset, we aim to benchmark the screen reading comprehension capacity, thereby laying the foundation for vision-based automation over screenshots. Our annotations encompass f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08199","kind":"arxiv","version":4},"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/2209.08199/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":"2209.08199","created_at":"2026-07-05T10:11:11.974496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08199v4","created_at":"2026-07-05T10:11:11.974496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08199","created_at":"2026-07-05T10:11:11.974496+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOLKPA55LMTN","created_at":"2026-07-05T10:11:11.974496+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOLKPA55LMTNFEJS","created_at":"2026-07-05T10:11:11.974496+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOLKPA55","created_at":"2026-07-05T10:11:11.974496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13848","citing_title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05525","citing_title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4","json":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4.json","graph_json":"https://pith.science/api/pith-number/JOLKPA55LMTNFEJS5NT7MV75U4/graph.json","events_json":"https://pith.science/api/pith-number/JOLKPA55LMTNFEJS5NT7MV75U4/events.json","paper":"https://pith.science/paper/JOLKPA55"},"agent_actions":{"view_html":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4","download_json":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4.json","view_paper":"https://pith.science/paper/JOLKPA55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08199&json=true","fetch_graph":"https://pith.science/api/pith-number/JOLKPA55LMTNFEJS5NT7MV75U4/graph.json","fetch_events":"https://pith.science/api/pith-number/JOLKPA55LMTNFEJS5NT7MV75U4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4/action/storage_attestation","attest_author":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4/action/author_attestation","sign_citation":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4/action/citation_signature","submit_replication":"https://pith.science/pith/JOLKPA55LMTNFEJS5NT7MV75U4/action/replication_record"}},"created_at":"2026-07-05T10:11:11.974496+00:00","updated_at":"2026-07-05T10:11:11.974496+00:00"}