{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DSBORCOQO533CNZU7AIJLCMOYQ","short_pith_number":"pith:DSBORCOQ","schema_version":"1.0","canonical_sha256":"1c82e889d07777b13734f81095898ec417a90b24a7f2d4c1af226f5c74570533","source":{"kind":"arxiv","id":"2309.11436","version":4},"attestation_state":"computed","paper":{"title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Aston Zhang, Zhuosheng Zhang","submitted_at":"2023-09-20T16:12:32Z","abstract_excerpt":"Autonomous graphical user interface (GUI) agents aim to facilitate task automation by interacting with the user interface without manual intervention. Recent studies have investigated eliciting the capabilities of large language models (LLMs) for effective engagement in diverse environments. To align with the input-output requirement of LLMs, most existing approaches are developed under a sandbox setting where they rely on external tools and application-specific APIs to parse the environment into textual elements and interpret the predicted actions. Consequently, those approaches often grapple"},"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":"2309.11436","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T16:12:32Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"24ffd7fbf9b293473f66af4a6c7d196cb838de57eca8388e1c38d90283a2c9c9","abstract_canon_sha256":"ff3a306fed8cbb7c53defd785ebb22d00c81da3c3c96b13ab37fa29502afd67e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:33.886748Z","signature_b64":"K/XkSzPrJnGgLiBUWPp8Pwgjw7ZHu9Jo80eC4WLe3BN24v9+U9rGgf1544P7EfYHRmYKyD2z+QttZd37FJIaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c82e889d07777b13734f81095898ec417a90b24a7f2d4c1af226f5c74570533","last_reissued_at":"2026-07-05T08:28:33.886255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:33.886255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Aston Zhang, Zhuosheng Zhang","submitted_at":"2023-09-20T16:12:32Z","abstract_excerpt":"Autonomous graphical user interface (GUI) agents aim to facilitate task automation by interacting with the user interface without manual intervention. Recent studies have investigated eliciting the capabilities of large language models (LLMs) for effective engagement in diverse environments. To align with the input-output requirement of LLMs, most existing approaches are developed under a sandbox setting where they rely on external tools and application-specific APIs to parse the environment into textual elements and interpret the predicted actions. Consequently, those approaches often grapple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11436","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/2309.11436/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":"2309.11436","created_at":"2026-07-05T08:28:33.886328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11436v4","created_at":"2026-07-05T08:28:33.886328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11436","created_at":"2026-07-05T08:28:33.886328+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSBORCOQO533","created_at":"2026-07-05T08:28:33.886328+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSBORCOQO533CNZU","created_at":"2026-07-05T08:28:33.886328+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSBORCOQ","created_at":"2026-07-05T08:28:33.886328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21740","citing_title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":241,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27761","citing_title":"AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":107,"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":103,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08516","citing_title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ","json":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ.json","graph_json":"https://pith.science/api/pith-number/DSBORCOQO533CNZU7AIJLCMOYQ/graph.json","events_json":"https://pith.science/api/pith-number/DSBORCOQO533CNZU7AIJLCMOYQ/events.json","paper":"https://pith.science/paper/DSBORCOQ"},"agent_actions":{"view_html":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ","download_json":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ.json","view_paper":"https://pith.science/paper/DSBORCOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11436&json=true","fetch_graph":"https://pith.science/api/pith-number/DSBORCOQO533CNZU7AIJLCMOYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DSBORCOQO533CNZU7AIJLCMOYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ/action/storage_attestation","attest_author":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ/action/author_attestation","sign_citation":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ/action/citation_signature","submit_replication":"https://pith.science/pith/DSBORCOQO533CNZU7AIJLCMOYQ/action/replication_record"}},"created_at":"2026-07-05T08:28:33.886328+00:00","updated_at":"2026-07-05T08:28:33.886328+00:00"}