{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X5JRE3LZCOVOMMI65Z6CXJME7W","short_pith_number":"pith:X5JRE3LZ","schema_version":"1.0","canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","source":{"kind":"arxiv","id":"2310.04716","version":1},"attestation_state":"computed","paper":{"title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenxuan Xie, Xiaoyi Zhang, Yan Lu, Zhizheng Zhang","submitted_at":"2023-10-07T07:22:41Z","abstract_excerpt":"Recent popularity of Large Language Models (LLMs) has opened countless possibilities in automating numerous AI tasks by connecting LLMs to various domain-specific models or APIs, where LLMs serve as dispatchers while domain-specific models or APIs are action executors. Despite the vast numbers of domain-specific models/APIs, they still struggle to comprehensively cover super diverse automation demands in the interaction between human and User Interfaces (UIs). In this work, we build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automati"},"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":"2310.04716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T07:22:41Z","cross_cats_sorted":[],"title_canon_sha256":"16aad16cd27bb14cbd50bf30f2b099fedec4d824e054f3a3b0b211e74a428fd1","abstract_canon_sha256":"5fdd2f1bca99efc0eb0215f74edd16fa88c75a3207bbd1336b88bccb1a4c7a60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:22.030119Z","signature_b64":"aM9k91D9yl5T9rchGSZU5Nt2uh1zWkaZP0jW+ymi92s/JPzy6EC2J564cwR771x+5zyvW0D/5aivPd4lbFxaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","last_reissued_at":"2026-07-05T06:58:22.029707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:22.029707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenxuan Xie, Xiaoyi Zhang, Yan Lu, Zhizheng Zhang","submitted_at":"2023-10-07T07:22:41Z","abstract_excerpt":"Recent popularity of Large Language Models (LLMs) has opened countless possibilities in automating numerous AI tasks by connecting LLMs to various domain-specific models or APIs, where LLMs serve as dispatchers while domain-specific models or APIs are action executors. Despite the vast numbers of domain-specific models/APIs, they still struggle to comprehensively cover super diverse automation demands in the interaction between human and User Interfaces (UIs). In this work, we build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04716","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/2310.04716/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":"2310.04716","created_at":"2026-07-05T06:58:22.029763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04716v1","created_at":"2026-07-05T06:58:22.029763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04716","created_at":"2026-07-05T06:58:22.029763+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5JRE3LZCOVO","created_at":"2026-07-05T06:58:22.029763+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5JRE3LZCOVOMMI6","created_at":"2026-07-05T06:58:22.029763+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5JRE3LZ","created_at":"2026-07-05T06:58:22.029763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.09373","citing_title":"LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W","json":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W.json","graph_json":"https://pith.science/api/pith-number/X5JRE3LZCOVOMMI65Z6CXJME7W/graph.json","events_json":"https://pith.science/api/pith-number/X5JRE3LZCOVOMMI65Z6CXJME7W/events.json","paper":"https://pith.science/paper/X5JRE3LZ"},"agent_actions":{"view_html":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W","download_json":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W.json","view_paper":"https://pith.science/paper/X5JRE3LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04716&json=true","fetch_graph":"https://pith.science/api/pith-number/X5JRE3LZCOVOMMI65Z6CXJME7W/graph.json","fetch_events":"https://pith.science/api/pith-number/X5JRE3LZCOVOMMI65Z6CXJME7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/action/storage_attestation","attest_author":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/action/author_attestation","sign_citation":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/action/citation_signature","submit_replication":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/action/replication_record"}},"created_at":"2026-07-05T06:58:22.029763+00:00","updated_at":"2026-07-05T06:58:22.029763+00:00"}