{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YA4QFGJYBKC4VG5Y6OKWXERNQH","short_pith_number":"pith:YA4QFGJY","schema_version":"1.0","canonical_sha256":"c0390299380a85ca9bb8f3956b922d81de7a265f89e654c0d3c62b578225d914","source":{"kind":"arxiv","id":"2408.03507","version":1},"attestation_state":"computed","paper":{"title":"GUI Element Detection Using SOTA YOLO Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CV","authors_text":"Seyed Shayan Daneshvar, Shaowei Wang","submitted_at":"2024-08-07T02:18:39Z","abstract_excerpt":"Detection of Graphical User Interface (GUI) elements is a crucial task for automatic code generation from images and sketches, GUI testing, and GUI search. Recent studies have leveraged both old-fashioned and modern computer vision (CV) techniques. Oldfashioned methods utilize classic image processing algorithms (e.g. edge detection and contour detection) and modern methods use mature deep learning solutions for general object detection tasks. GUI element detection, however, is a domain-specific case of object detection, in which objects overlap more often, and are located very close to each o"},"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":"2408.03507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T02:18:39Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"851fd32ee93fff7a71c9609d5a2e63aa5819b0b631cc91d1b0968f6b67d07a55","abstract_canon_sha256":"3818b12e3c82598e92d229467c077e5d7ba9048a6ef4a7d0d522fdc01f055812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:59.542853Z","signature_b64":"gW6wcfkAqxrxHLp3lt7N+RkfMZro+zADFminqcuqhLERuXTHSS1YJnkwvultqUXmi1X2s/qSZu+Q73XkJ5gmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0390299380a85ca9bb8f3956b922d81de7a265f89e654c0d3c62b578225d914","last_reissued_at":"2026-07-05T08:52:59.542371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:59.542371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUI Element Detection Using SOTA YOLO Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CV","authors_text":"Seyed Shayan Daneshvar, Shaowei Wang","submitted_at":"2024-08-07T02:18:39Z","abstract_excerpt":"Detection of Graphical User Interface (GUI) elements is a crucial task for automatic code generation from images and sketches, GUI testing, and GUI search. Recent studies have leveraged both old-fashioned and modern computer vision (CV) techniques. Oldfashioned methods utilize classic image processing algorithms (e.g. edge detection and contour detection) and modern methods use mature deep learning solutions for general object detection tasks. GUI element detection, however, is a domain-specific case of object detection, in which objects overlap more often, and are located very close to each o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03507","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/2408.03507/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":"2408.03507","created_at":"2026-07-05T08:52:59.542430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03507v1","created_at":"2026-07-05T08:52:59.542430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03507","created_at":"2026-07-05T08:52:59.542430+00:00"},{"alias_kind":"pith_short_12","alias_value":"YA4QFGJYBKC4","created_at":"2026-07-05T08:52:59.542430+00:00"},{"alias_kind":"pith_short_16","alias_value":"YA4QFGJYBKC4VG5Y","created_at":"2026-07-05T08:52:59.542430+00:00"},{"alias_kind":"pith_short_8","alias_value":"YA4QFGJY","created_at":"2026-07-05T08:52:59.542430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06934","citing_title":"Multi-modal user interface control detection using cross-attention","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH","json":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH.json","graph_json":"https://pith.science/api/pith-number/YA4QFGJYBKC4VG5Y6OKWXERNQH/graph.json","events_json":"https://pith.science/api/pith-number/YA4QFGJYBKC4VG5Y6OKWXERNQH/events.json","paper":"https://pith.science/paper/YA4QFGJY"},"agent_actions":{"view_html":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH","download_json":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH.json","view_paper":"https://pith.science/paper/YA4QFGJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03507&json=true","fetch_graph":"https://pith.science/api/pith-number/YA4QFGJYBKC4VG5Y6OKWXERNQH/graph.json","fetch_events":"https://pith.science/api/pith-number/YA4QFGJYBKC4VG5Y6OKWXERNQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH/action/storage_attestation","attest_author":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH/action/author_attestation","sign_citation":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH/action/citation_signature","submit_replication":"https://pith.science/pith/YA4QFGJYBKC4VG5Y6OKWXERNQH/action/replication_record"}},"created_at":"2026-07-05T08:52:59.542430+00:00","updated_at":"2026-07-05T08:52:59.542430+00:00"}