{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LAXBKK4RLMB3YJIATXBQBGEEVS","short_pith_number":"pith:LAXBKK4R","schema_version":"1.0","canonical_sha256":"582e152b915b03bc25009dc3009884aca668fbc2719566da117fcd508f8c5708","source":{"kind":"arxiv","id":"2412.16256","version":2},"attestation_state":"computed","paper":{"title":"Aria-UI: Visual Grounding for GUI Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Bei Chen, Chao Huang, Dongxu Li, Junnan Li, Yue Wang, Yuhao Yang, Ziyang Luo","submitted_at":"2024-12-20T07:16:57Z","abstract_excerpt":"Digital agents for automating tasks across different platforms by directly manipulating the GUIs are increasingly important. For these agents, grounding from language instructions to target elements remains a significant challenge due to reliance on HTML or AXTree inputs. In this paper, we introduce Aria-UI, a large multimodal model specifically designed for GUI grounding. Aria-UI adopts a pure-vision approach, eschewing reliance on auxiliary inputs. To adapt to heterogeneous planning instructions, we propose a scalable data pipeline that synthesizes diverse and high-quality instruction sample"},"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":"2412.16256","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-12-20T07:16:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75dca2f5f58a99632c623317e90149c3fed66adc8a1635abe32d5882eb27c18e","abstract_canon_sha256":"e7c9b83753a3bd4a98952d91e823f85e8ce3d4e49d6d0d7b030771723c1068c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:18.762609Z","signature_b64":"IQeE/u9c5A8hZhCbIp1pFNFMNoNSRT5/lxV9URQthOPODbOzjw8zkmNn+71j9J0+lUujAvF0k49yHzeiECgRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582e152b915b03bc25009dc3009884aca668fbc2719566da117fcd508f8c5708","last_reissued_at":"2026-07-05T11:33:18.762043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:18.762043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aria-UI: Visual Grounding for GUI Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Bei Chen, Chao Huang, Dongxu Li, Junnan Li, Yue Wang, Yuhao Yang, Ziyang Luo","submitted_at":"2024-12-20T07:16:57Z","abstract_excerpt":"Digital agents for automating tasks across different platforms by directly manipulating the GUIs are increasingly important. For these agents, grounding from language instructions to target elements remains a significant challenge due to reliance on HTML or AXTree inputs. In this paper, we introduce Aria-UI, a large multimodal model specifically designed for GUI grounding. Aria-UI adopts a pure-vision approach, eschewing reliance on auxiliary inputs. To adapt to heterogeneous planning instructions, we propose a scalable data pipeline that synthesizes diverse and high-quality instruction sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16256","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/2412.16256/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":"2412.16256","created_at":"2026-07-05T11:33:18.762112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16256v2","created_at":"2026-07-05T11:33:18.762112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16256","created_at":"2026-07-05T11:33:18.762112+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAXBKK4RLMB3","created_at":"2026-07-05T11:33:18.762112+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAXBKK4RLMB3YJIA","created_at":"2026-07-05T11:33:18.762112+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAXBKK4R","created_at":"2026-07-05T11:33:18.762112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00390","citing_title":"Zamba2-VL Technical Report","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31270","citing_title":"Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.10887","citing_title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":219,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14239","citing_title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05791","citing_title":"GTA1: GUI Test-time Scaling Agent","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21858","citing_title":"ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08560","citing_title":"ZAYA1-VL-8B Technical Report","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14262","citing_title":"GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21375","citing_title":"VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS","json":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS.json","graph_json":"https://pith.science/api/pith-number/LAXBKK4RLMB3YJIATXBQBGEEVS/graph.json","events_json":"https://pith.science/api/pith-number/LAXBKK4RLMB3YJIATXBQBGEEVS/events.json","paper":"https://pith.science/paper/LAXBKK4R"},"agent_actions":{"view_html":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS","download_json":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS.json","view_paper":"https://pith.science/paper/LAXBKK4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16256&json=true","fetch_graph":"https://pith.science/api/pith-number/LAXBKK4RLMB3YJIATXBQBGEEVS/graph.json","fetch_events":"https://pith.science/api/pith-number/LAXBKK4RLMB3YJIATXBQBGEEVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS/action/storage_attestation","attest_author":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS/action/author_attestation","sign_citation":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS/action/citation_signature","submit_replication":"https://pith.science/pith/LAXBKK4RLMB3YJIATXBQBGEEVS/action/replication_record"}},"created_at":"2026-07-05T11:33:18.762112+00:00","updated_at":"2026-07-05T11:33:18.762112+00:00"}