{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:73Q4LGIBHAQ2NTYZNPSPOY73DI","short_pith_number":"pith:73Q4LGIB","schema_version":"1.0","canonical_sha256":"fee1c599013821a6cf196be4f763fb1a13b3c9300996d69f7b0f0f200fd5e06b","source":{"kind":"arxiv","id":"2211.07615","version":2},"attestation_state":"computed","paper":{"title":"UGIF: UI Grounded Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Partha Talukdar, Sagar Gubbi Venkatesh, Srini Narayanan","submitted_at":"2022-11-14T18:36:19Z","abstract_excerpt":"Smartphone users often find it difficult to navigate myriad menus to perform common tasks such as \"How to block calls from unknown numbers?\". Currently, help documents with step-by-step instructions are manually written to aid the user. The user experience can be further enhanced by grounding the instructions in the help document to the UI and overlaying a tutorial on the phone UI. To build such tutorials, several natural language processing components including retrieval, parsing, and grounding are necessary, but there isn't any relevant dataset for such a task. Thus, we introduce UGIF-DataSe"},"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":"2211.07615","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T18:36:19Z","cross_cats_sorted":[],"title_canon_sha256":"a400c2c1d272ba42de1afaf8a0b77f661d68f0f94946a2e9b8608f581447fdf5","abstract_canon_sha256":"bc122c6dc5956aadcda57734908be1cbc220c6e05a55509844b60046ccc98ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:39.068807Z","signature_b64":"bRr2uccl+AMJi7E7O27c/FW7ohNd4RJpd2kERalTjtBEG/dMDXhouz2TCBF33wD+sTgtMNhVZF51JZzlncqlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fee1c599013821a6cf196be4f763fb1a13b3c9300996d69f7b0f0f200fd5e06b","last_reissued_at":"2026-07-05T06:12:39.068382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:39.068382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UGIF: UI Grounded Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Partha Talukdar, Sagar Gubbi Venkatesh, Srini Narayanan","submitted_at":"2022-11-14T18:36:19Z","abstract_excerpt":"Smartphone users often find it difficult to navigate myriad menus to perform common tasks such as \"How to block calls from unknown numbers?\". Currently, help documents with step-by-step instructions are manually written to aid the user. The user experience can be further enhanced by grounding the instructions in the help document to the UI and overlaying a tutorial on the phone UI. To build such tutorials, several natural language processing components including retrieval, parsing, and grounding are necessary, but there isn't any relevant dataset for such a task. Thus, we introduce UGIF-DataSe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07615","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/2211.07615/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":"2211.07615","created_at":"2026-07-05T06:12:39.068440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07615v2","created_at":"2026-07-05T06:12:39.068440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07615","created_at":"2026-07-05T06:12:39.068440+00:00"},{"alias_kind":"pith_short_12","alias_value":"73Q4LGIBHAQ2","created_at":"2026-07-05T06:12:39.068440+00:00"},{"alias_kind":"pith_short_16","alias_value":"73Q4LGIBHAQ2NTYZ","created_at":"2026-07-05T06:12:39.068440+00:00"},{"alias_kind":"pith_short_8","alias_value":"73Q4LGIB","created_at":"2026-07-05T06:12:39.068440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07972","citing_title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17817","citing_title":"Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI","json":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI.json","graph_json":"https://pith.science/api/pith-number/73Q4LGIBHAQ2NTYZNPSPOY73DI/graph.json","events_json":"https://pith.science/api/pith-number/73Q4LGIBHAQ2NTYZNPSPOY73DI/events.json","paper":"https://pith.science/paper/73Q4LGIB"},"agent_actions":{"view_html":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI","download_json":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI.json","view_paper":"https://pith.science/paper/73Q4LGIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07615&json=true","fetch_graph":"https://pith.science/api/pith-number/73Q4LGIBHAQ2NTYZNPSPOY73DI/graph.json","fetch_events":"https://pith.science/api/pith-number/73Q4LGIBHAQ2NTYZNPSPOY73DI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI/action/storage_attestation","attest_author":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI/action/author_attestation","sign_citation":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI/action/citation_signature","submit_replication":"https://pith.science/pith/73Q4LGIBHAQ2NTYZNPSPOY73DI/action/replication_record"}},"created_at":"2026-07-05T06:12:39.068440+00:00","updated_at":"2026-07-05T06:12:39.068440+00:00"}