{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FGYNXYWJJYLQO76Y3GNOA4OYT5","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":"6ca03a283cf57d0649f4412b729ce19c4686f972c2eb0cf70734a9345e988879","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-09T12:06:43Z","title_canon_sha256":"937780ef59be5f89fb0e5ab15dc822b2a39e53443e583e57066425909a0ef09c"},"schema_version":"1.0","source":{"id":"2410.11871","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11871","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11871v3","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11871","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"FGYNXYWJJYLQ","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"FGYNXYWJJYLQO76Y","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"FGYNXYWJ","created_at":"2026-07-05T11:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:366f8aa025860ca7cc7b2fcf90cda2ecb4431fa6f0b7a70494f9495ceec14eaa","target":"graph","created_at":"2026-07-05T11:06:24Z","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/2410.11871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an UI agent for user interface (UI) interaction tasks, using Vision-Language Model Florence-2-Base. The agent's primary task is identifying the screen coordinates of the UI element corresponding to the user's command. It demonstrates very strong performance on Screenspot and OmniAct annotations, while maintaining a very small size of 0.27B parameters and minimal latency. Moreover, training needs small compute budget of 56 GPU-hours (worth about 40 USD). Relevant improvement comes from vision-specific multi-task training and MLLM-based data augmentation. We hope that decreased needs ","authors_text":"Adam Wiacek, Jakub Hoscilowicz, Krystian Zawistowski, Marcin Skorupa, Pawel Pawlowski, Sebastien Postansque, Wojciech Lapacz","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-09T12:06:43Z","title":"TinyClick: Single-Turn Agent for Empowering GUI Automation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11871","kind":"arxiv","version":3},"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":"sha256:18a50f8db04b20d92ef2eb15fff76b5ded3ca133b33196325290e776b763031a","target":"record","created_at":"2026-07-05T11:06:24Z","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":"6ca03a283cf57d0649f4412b729ce19c4686f972c2eb0cf70734a9345e988879","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-09T12:06:43Z","title_canon_sha256":"937780ef59be5f89fb0e5ab15dc822b2a39e53443e583e57066425909a0ef09c"},"schema_version":"1.0","source":{"id":"2410.11871","kind":"arxiv","version":3}},"canonical_sha256":"29b0dbe2c94e17077fd8d99ae071d89f793f82d2401229b25437303243ab6119","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29b0dbe2c94e17077fd8d99ae071d89f793f82d2401229b25437303243ab6119","first_computed_at":"2026-07-05T11:06:24.161920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:24.161920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xTZ2+ASYkMZh+46JOFN7tE1wv2elZG6q7w6kkrfub8nr5FJi+w2W9XAtE+kl89R9Su2xduSoWps8daI81YqOCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:24.162426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11871","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18a50f8db04b20d92ef2eb15fff76b5ded3ca133b33196325290e776b763031a","sha256:366f8aa025860ca7cc7b2fcf90cda2ecb4431fa6f0b7a70494f9495ceec14eaa"],"state_sha256":"3b2404d61dbae17fb0e44cdb9b6c8ad277c68191218bd7ee426d26b44142324a"}