{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LAXBKK4RLMB3YJIATXBQBGEEVS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e7c9b83753a3bd4a98952d91e823f85e8ce3d4e49d6d0d7b030771723c1068c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-12-20T07:16:57Z","title_canon_sha256":"75dca2f5f58a99632c623317e90149c3fed66adc8a1635abe32d5882eb27c18e"},"schema_version":"1.0","source":{"id":"2412.16256","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16256","created_at":"2026-07-05T11:33:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16256v2","created_at":"2026-07-05T11:33:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16256","created_at":"2026-07-05T11:33:18Z"},{"alias_kind":"pith_short_12","alias_value":"LAXBKK4RLMB3","created_at":"2026-07-05T11:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"LAXBKK4RLMB3YJIA","created_at":"2026-07-05T11:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"LAXBKK4R","created_at":"2026-07-05T11:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:a69ac661dd39b509088066ccbabe61be06b1dd8792d1ada8dec272d7a268893f","target":"graph","created_at":"2026-07-05T11:33:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.16256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bei Chen, Chao Huang, Dongxu Li, Junnan Li, Yue Wang, Yuhao Yang, Ziyang Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-12-20T07:16:57Z","title":"Aria-UI: Visual Grounding for GUI Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16256","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5e6205e25472aa82fb6f325581a46bca8c497af0213a4b0a506b1b81c37e81f5","target":"record","created_at":"2026-07-05T11:33:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e7c9b83753a3bd4a98952d91e823f85e8ce3d4e49d6d0d7b030771723c1068c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-12-20T07:16:57Z","title_canon_sha256":"75dca2f5f58a99632c623317e90149c3fed66adc8a1635abe32d5882eb27c18e"},"schema_version":"1.0","source":{"id":"2412.16256","kind":"arxiv","version":2}},"canonical_sha256":"582e152b915b03bc25009dc3009884aca668fbc2719566da117fcd508f8c5708","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"582e152b915b03bc25009dc3009884aca668fbc2719566da117fcd508f8c5708","first_computed_at":"2026-07-05T11:33:18.762043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:18.762043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQeE/u9c5A8hZhCbIp1pFNFMNoNSRT5/lxV9URQthOPODbOzjw8zkmNn+71j9J0+lUujAvF0k49yHzeiECgRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:18.762609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16256","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e6205e25472aa82fb6f325581a46bca8c497af0213a4b0a506b1b81c37e81f5","sha256:a69ac661dd39b509088066ccbabe61be06b1dd8792d1ada8dec272d7a268893f"],"state_sha256":"0df55a687ed0c949760dacbda01f28e8692c360ec1e31ec4b8899bcdfdf79691"}