{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCHC4UNNYUZC6UWSITS5N6ATJK","short_pith_number":"pith:FCHC4UNN","schema_version":"1.0","canonical_sha256":"288e2e51adc5322f52d244e5d6f8134a9b753bc7eb70b0cb6d2f3ed13f8a9aae","source":{"kind":"arxiv","id":"2503.11069","version":2},"attestation_state":"computed","paper":{"title":"API Agents vs. GUI Agents: Divergence and Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Chaoyun Zhang, Dongmei Zhang, Liqun Li, Qingwei Lin, Saravan Rajmohan, Shilin He, Si Qin, Yu Kang","submitted_at":"2025-03-14T04:26:21Z","abstract_excerpt":"Large language models (LLMs) have evolved beyond simple text generation to power software agents that directly translate natural language commands into tangible actions. While API-based LLM agents initially rose to prominence for their robust automation capabilities and seamless integration with programmatic endpoints, recent progress in multimodal LLM research has enabled GUI-based LLM agents that interact with graphical user interfaces in a human-like manner. Although these two paradigms share the goal of enabling LLM-driven task automation, they diverge significantly in architectural comple"},"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":"2503.11069","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-14T04:26:21Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"b02ee60e80b8e9a4aa3745b43f4295f193b8fc4d1b49f885131f74a463e89615","abstract_canon_sha256":"3006c43e3b1fcdaa8621b9938ceb6994239dfda39e4a421574ffe031a6895cf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:42.764102Z","signature_b64":"OQxqKCnv91s3CXHqyfdi0TopylFLRX0f28/FTssZyK2YJmCH/bcQQxQxnDPSbjxziZnoDjxcmiWvRei0tqX2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"288e2e51adc5322f52d244e5d6f8134a9b753bc7eb70b0cb6d2f3ed13f8a9aae","last_reissued_at":"2026-07-05T11:25:42.763590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:42.763590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"API Agents vs. GUI Agents: Divergence and Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Chaoyun Zhang, Dongmei Zhang, Liqun Li, Qingwei Lin, Saravan Rajmohan, Shilin He, Si Qin, Yu Kang","submitted_at":"2025-03-14T04:26:21Z","abstract_excerpt":"Large language models (LLMs) have evolved beyond simple text generation to power software agents that directly translate natural language commands into tangible actions. While API-based LLM agents initially rose to prominence for their robust automation capabilities and seamless integration with programmatic endpoints, recent progress in multimodal LLM research has enabled GUI-based LLM agents that interact with graphical user interfaces in a human-like manner. Although these two paradigms share the goal of enabling LLM-driven task automation, they diverge significantly in architectural comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11069","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/2503.11069/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":"2503.11069","created_at":"2026-07-05T11:25:42.763657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11069v2","created_at":"2026-07-05T11:25:42.763657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11069","created_at":"2026-07-05T11:25:42.763657+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCHC4UNNYUZC","created_at":"2026-07-05T11:25:42.763657+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCHC4UNNYUZC6UWS","created_at":"2026-07-05T11:25:42.763657+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCHC4UNN","created_at":"2026-07-05T11:25:42.763657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23978","citing_title":"LLM Agents Are the Antidote to Walled Gardens","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06477","citing_title":"MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2510.24168","citing_title":"MGA: Memory-Driven GUI Agent for Observation-Centric Interaction","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14290","citing_title":"Web Agents Should Adopt the Plan-Then-Execute Paradigm","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12481","citing_title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04820","citing_title":"ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK","json":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK.json","graph_json":"https://pith.science/api/pith-number/FCHC4UNNYUZC6UWSITS5N6ATJK/graph.json","events_json":"https://pith.science/api/pith-number/FCHC4UNNYUZC6UWSITS5N6ATJK/events.json","paper":"https://pith.science/paper/FCHC4UNN"},"agent_actions":{"view_html":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK","download_json":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK.json","view_paper":"https://pith.science/paper/FCHC4UNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11069&json=true","fetch_graph":"https://pith.science/api/pith-number/FCHC4UNNYUZC6UWSITS5N6ATJK/graph.json","fetch_events":"https://pith.science/api/pith-number/FCHC4UNNYUZC6UWSITS5N6ATJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK/action/storage_attestation","attest_author":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK/action/author_attestation","sign_citation":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK/action/citation_signature","submit_replication":"https://pith.science/pith/FCHC4UNNYUZC6UWSITS5N6ATJK/action/replication_record"}},"created_at":"2026-07-05T11:25:42.763657+00:00","updated_at":"2026-07-05T11:25:42.763657+00:00"}