{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CT4TDGWEX7444HTKENDYFTSIOX","short_pith_number":"pith:CT4TDGWE","schema_version":"1.0","canonical_sha256":"14f9319ac4bff9ce1e6a234782ce4875f4421968809b532d93c3c2b12de6c266","source":{"kind":"arxiv","id":"2509.11548","version":2},"attestation_state":"computed","paper":{"title":"How Auxiliary Reasoning Unleashes GUI Grounding in VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Yang, Ling Zhong, Manni Duan, Min Yu, Tongxiao Ruan, Weiming Li, Yan Shao, Yuhan Wang, Yujing Lu","submitted_at":"2025-09-15T03:28:29Z","abstract_excerpt":"Graphical user interface (GUI) grounding is a fundamental task for building GUI agents. However, general vision-language models (VLMs) struggle with this task due to a lack of specific optimization. We identify a key gap in this paper: while VLMs exhibit significant latent grounding potential, as demonstrated by their performance measured by Pointing Game, they underperform when tasked with outputting explicit coordinates. To address this discrepancy and bypass the high data and annotation costs of current fine-tuning approaches, we propose three zero-shot auxiliary reasoning methods. By provi"},"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":"2509.11548","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-15T03:28:29Z","cross_cats_sorted":[],"title_canon_sha256":"77cad5b45b5af412c3b07c765480c2a03399512d5787041c6defe3a6263b4274","abstract_canon_sha256":"2c9414d170b168423456e1cb1212ac7b67c01aad345f5ed0141d74743eabf79e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:17.171911Z","signature_b64":"6hFck3+xuiBzd/eyggwKNDut9rdsVXbMxrUdcU0W7xlBZwFbAWb1BcRLuLN3DKzYEXwWez3fVu2pCAjDODXqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f9319ac4bff9ce1e6a234782ce4875f4421968809b532d93c3c2b12de6c266","last_reissued_at":"2026-06-11T01:09:17.170828Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:17.170828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Auxiliary Reasoning Unleashes GUI Grounding in VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Yang, Ling Zhong, Manni Duan, Min Yu, Tongxiao Ruan, Weiming Li, Yan Shao, Yuhan Wang, Yujing Lu","submitted_at":"2025-09-15T03:28:29Z","abstract_excerpt":"Graphical user interface (GUI) grounding is a fundamental task for building GUI agents. However, general vision-language models (VLMs) struggle with this task due to a lack of specific optimization. We identify a key gap in this paper: while VLMs exhibit significant latent grounding potential, as demonstrated by their performance measured by Pointing Game, they underperform when tasked with outputting explicit coordinates. To address this discrepancy and bypass the high data and annotation costs of current fine-tuning approaches, we propose three zero-shot auxiliary reasoning methods. By provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.11548","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/2509.11548/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":"2509.11548","created_at":"2026-06-11T01:09:17.170985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.11548v2","created_at":"2026-06-11T01:09:17.170985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.11548","created_at":"2026-06-11T01:09:17.170985+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT4TDGWEX744","created_at":"2026-06-11T01:09:17.170985+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT4TDGWEX7444HTK","created_at":"2026-06-11T01:09:17.170985+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT4TDGWE","created_at":"2026-06-11T01:09:17.170985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX","json":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX.json","graph_json":"https://pith.science/api/pith-number/CT4TDGWEX7444HTKENDYFTSIOX/graph.json","events_json":"https://pith.science/api/pith-number/CT4TDGWEX7444HTKENDYFTSIOX/events.json","paper":"https://pith.science/paper/CT4TDGWE"},"agent_actions":{"view_html":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX","download_json":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX.json","view_paper":"https://pith.science/paper/CT4TDGWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.11548&json=true","fetch_graph":"https://pith.science/api/pith-number/CT4TDGWEX7444HTKENDYFTSIOX/graph.json","fetch_events":"https://pith.science/api/pith-number/CT4TDGWEX7444HTKENDYFTSIOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX/action/storage_attestation","attest_author":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX/action/author_attestation","sign_citation":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX/action/citation_signature","submit_replication":"https://pith.science/pith/CT4TDGWEX7444HTKENDYFTSIOX/action/replication_record"}},"created_at":"2026-06-11T01:09:17.170985+00:00","updated_at":"2026-06-11T01:09:17.170985+00:00"}