{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C6SLFMM6R4KNOWBG5OEWMWYGVH","short_pith_number":"pith:C6SLFMM6","schema_version":"1.0","canonical_sha256":"17a4b2b19e8f14d75826eb89665b06a9ca34c866cc2c3804b556c7ea0253b069","source":{"kind":"arxiv","id":"2410.11872","version":2},"attestation_state":"computed","paper":{"title":"ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.HC","authors_text":"Artur Janicki, Bartosz Kozakiewicz, Bartosz Maj, Jakub Hoscilowicz, Oleksii Tymoshchuk","submitted_at":"2024-10-09T14:49:02Z","abstract_excerpt":"With the growing reliance on digital devices equipped with graphical user interfaces (GUIs), such as computers and smartphones, the need for effective automation tools has become increasingly important. While multimodal large language models (MLLMs) like GPT-4V excel in many areas, they struggle with GUI interactions, limiting their effectiveness in automating everyday tasks. In this paper, we introduce ClickAgent, a novel framework for building autonomous agents. In ClickAgent, the MLLM handles reasoning and action planning, while a separate UI location model (e.g., SeeClick) identifies the r"},"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":"2410.11872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-09T14:49:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"830b5af1a6ba74efbc6fcd698be89713dc3ad417c085e4af558579ac4a698936","abstract_canon_sha256":"b8c8f9f73150e33368520730c254e5a56754ed540c6636c1552b5f53e37eeff9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:50.232041Z","signature_b64":"32VyuKncITpZHE+kqyzZRvQWHKUy+iRtHL1DxEVHdaPwLI+4Zirq31DPLekzTB1b5pRUjbq8Mkg0MPAt74EBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17a4b2b19e8f14d75826eb89665b06a9ca34c866cc2c3804b556c7ea0253b069","last_reissued_at":"2026-07-05T09:21:50.231564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:50.231564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.HC","authors_text":"Artur Janicki, Bartosz Kozakiewicz, Bartosz Maj, Jakub Hoscilowicz, Oleksii Tymoshchuk","submitted_at":"2024-10-09T14:49:02Z","abstract_excerpt":"With the growing reliance on digital devices equipped with graphical user interfaces (GUIs), such as computers and smartphones, the need for effective automation tools has become increasingly important. While multimodal large language models (MLLMs) like GPT-4V excel in many areas, they struggle with GUI interactions, limiting their effectiveness in automating everyday tasks. In this paper, we introduce ClickAgent, a novel framework for building autonomous agents. In ClickAgent, the MLLM handles reasoning and action planning, while a separate UI location model (e.g., SeeClick) identifies the r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11872","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/2410.11872/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":"2410.11872","created_at":"2026-07-05T09:21:50.231622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11872v2","created_at":"2026-07-05T09:21:50.231622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11872","created_at":"2026-07-05T09:21:50.231622+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6SLFMM6R4KN","created_at":"2026-07-05T09:21:50.231622+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6SLFMM6R4KNOWBG","created_at":"2026-07-05T09:21:50.231622+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6SLFMM6","created_at":"2026-07-05T09:21:50.231622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09278","citing_title":"Software Engineering for and with GUI Agent","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH","json":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH.json","graph_json":"https://pith.science/api/pith-number/C6SLFMM6R4KNOWBG5OEWMWYGVH/graph.json","events_json":"https://pith.science/api/pith-number/C6SLFMM6R4KNOWBG5OEWMWYGVH/events.json","paper":"https://pith.science/paper/C6SLFMM6"},"agent_actions":{"view_html":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH","download_json":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH.json","view_paper":"https://pith.science/paper/C6SLFMM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11872&json=true","fetch_graph":"https://pith.science/api/pith-number/C6SLFMM6R4KNOWBG5OEWMWYGVH/graph.json","fetch_events":"https://pith.science/api/pith-number/C6SLFMM6R4KNOWBG5OEWMWYGVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH/action/storage_attestation","attest_author":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH/action/author_attestation","sign_citation":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH/action/citation_signature","submit_replication":"https://pith.science/pith/C6SLFMM6R4KNOWBG5OEWMWYGVH/action/replication_record"}},"created_at":"2026-07-05T09:21:50.231622+00:00","updated_at":"2026-07-05T09:21:50.231622+00:00"}