{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CIYIJVKQ3V6P23EMVEOZWLIE4G","short_pith_number":"pith:CIYIJVKQ","schema_version":"1.0","canonical_sha256":"123084d550dd7cfd6c8ca91d9b2d04e19073c4e85e57ea44ab0c193d3e9c6c07","source":{"kind":"arxiv","id":"2503.00401","version":2},"attestation_state":"computed","paper":{"title":"Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.HC"],"primary_cat":"cs.CL","authors_text":"Gongshen Liu, Pengzhou Cheng, Tianjie Ju, Zheng Wu, Zhuosheng Zhang, Zongru Wu","submitted_at":"2025-03-01T08:29:59Z","abstract_excerpt":"Perception-enhanced pre-training, particularly through grounding techniques, is widely adopted to enhance the performance of graphical user interface (GUI) agents. However, in resource-constrained scenarios, the format discrepancy between coordinate-oriented grounding and action-oriented reasoning limits the effectiveness of grounding for reasoning tasks. To address this challenge, we propose a query-oriented pivot approach called query inference, which serves as a bridge between GUI grounding and reasoning. By inferring potential user queries from a screenshot and its associated element coord"},"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":"2503.00401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T08:29:59Z","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"title_canon_sha256":"a78f103bfb46632e1184228d1b9a75990894db43a560830418ad1c91c1a8571a","abstract_canon_sha256":"497fd1732e4903c3602805f0d173cfab9f3ec24a67ed0abd75e720107b1da8bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:03.346300Z","signature_b64":"/HlrTgAj+PycqYvMDQIO2EeYsI+VmQD8EkCuLT+XZWN4YdRLT9jAQL+BXAXA+ApFIxy75GO+oblezG6zo+XeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"123084d550dd7cfd6c8ca91d9b2d04e19073c4e85e57ea44ab0c193d3e9c6c07","last_reissued_at":"2026-07-05T10:24:03.345809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:03.345809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.HC"],"primary_cat":"cs.CL","authors_text":"Gongshen Liu, Pengzhou Cheng, Tianjie Ju, Zheng Wu, Zhuosheng Zhang, Zongru Wu","submitted_at":"2025-03-01T08:29:59Z","abstract_excerpt":"Perception-enhanced pre-training, particularly through grounding techniques, is widely adopted to enhance the performance of graphical user interface (GUI) agents. However, in resource-constrained scenarios, the format discrepancy between coordinate-oriented grounding and action-oriented reasoning limits the effectiveness of grounding for reasoning tasks. To address this challenge, we propose a query-oriented pivot approach called query inference, which serves as a bridge between GUI grounding and reasoning. By inferring potential user queries from a screenshot and its associated element coord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00401","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/2503.00401/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":"2503.00401","created_at":"2026-07-05T10:24:03.345867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00401v2","created_at":"2026-07-05T10:24:03.345867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00401","created_at":"2026-07-05T10:24:03.345867+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIYIJVKQ3V6P","created_at":"2026-07-05T10:24:03.345867+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIYIJVKQ3V6P23EM","created_at":"2026-07-05T10:24:03.345867+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIYIJVKQ","created_at":"2026-07-05T10:24:03.345867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03236","citing_title":"Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28629","citing_title":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07553","citing_title":"VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21620","citing_title":"UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G","json":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G.json","graph_json":"https://pith.science/api/pith-number/CIYIJVKQ3V6P23EMVEOZWLIE4G/graph.json","events_json":"https://pith.science/api/pith-number/CIYIJVKQ3V6P23EMVEOZWLIE4G/events.json","paper":"https://pith.science/paper/CIYIJVKQ"},"agent_actions":{"view_html":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G","download_json":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G.json","view_paper":"https://pith.science/paper/CIYIJVKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00401&json=true","fetch_graph":"https://pith.science/api/pith-number/CIYIJVKQ3V6P23EMVEOZWLIE4G/graph.json","fetch_events":"https://pith.science/api/pith-number/CIYIJVKQ3V6P23EMVEOZWLIE4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G/action/storage_attestation","attest_author":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G/action/author_attestation","sign_citation":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G/action/citation_signature","submit_replication":"https://pith.science/pith/CIYIJVKQ3V6P23EMVEOZWLIE4G/action/replication_record"}},"created_at":"2026-07-05T10:24:03.345867+00:00","updated_at":"2026-07-05T10:24:03.345867+00:00"}