{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MX74S6UKUSS7CMOXV33MBVRN66","short_pith_number":"pith:MX74S6UK","canonical_record":{"source":{"id":"2503.04730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T08:29:17Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"c51140a32819d10d35ff5d96c19a1d61edb956afddb07a4dd4f4c02c90b4c338","abstract_canon_sha256":"9146c2de660dcaa173b26452b232fe05441acb4f66a6d7f7131f10e956840f77"},"schema_version":"1.0"},"canonical_sha256":"65ffc97a8aa4a5f131d7aef6c0d62df79d249b441f402c387fece4d1f76de597","source":{"kind":"arxiv","id":"2503.04730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04730","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04730v1","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04730","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"MX74S6UKUSS7","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"MX74S6UKUSS7CMOX","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"MX74S6UK","created_at":"2026-07-05T10:25:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MX74S6UKUSS7CMOXV33MBVRN66","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T08:29:17Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"c51140a32819d10d35ff5d96c19a1d61edb956afddb07a4dd4f4c02c90b4c338","abstract_canon_sha256":"9146c2de660dcaa173b26452b232fe05441acb4f66a6d7f7131f10e956840f77"},"schema_version":"1.0"},"canonical_sha256":"65ffc97a8aa4a5f131d7aef6c0d62df79d249b441f402c387fece4d1f76de597","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:47.389474Z","signature_b64":"N3//rlULiFdd35OmKb+YkOyudito7tvHgk24wkoScqixCRBirXOuJyDMuYS486/ODU4X2OLqbFP1ELEtnMC4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ffc97a8aa4a5f131d7aef6c0d62df79d249b441f402c387fece4d1f76de597","last_reissued_at":"2026-07-05T10:25:47.388939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:47.388939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04730","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpyRTbrHtH8n6qg4Qy5q92xGSzU1hMkNvUf+vS7QHFQx5Ca2qdYZ1RkjZdLHIvaTyrO35JNwJPTPIMBnZ/DoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:17:18.261911Z"},"content_sha256":"615b8fd9044cc73e60817ac85ac2c6b3ef813ab6cb8639917fc7d140a2286493","schema_version":"1.0","event_id":"sha256:615b8fd9044cc73e60817ac85ac2c6b3ef813ab6cb8639917fc7d140a2286493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MX74S6UKUSS7CMOXV33MBVRN66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WinClick: GUI Grounding with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Colby Banbury, Dan Zhao, Kazuhito Koishida, Tianyi Chen, Yinheng Li, Zheng Hui","submitted_at":"2025-01-27T08:29:17Z","abstract_excerpt":"Graphical User Interface (GUI) tasks are vital for automating workflows such as software testing, user interface navigation. For users, the GUI is the most intuitive platform for interacting with a computer. Previous work identified a key challenge in developing visual GUI agents: GUI grounding - the ability to accurately locate screen elements based on instructions. However, most existing GUI agents rely on structured data formats like DOM or HTML files in training or inferencing, which are inaccessible across all applications, particular in a general desktop environments such as Windows OS. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04730","kind":"arxiv","version":1},"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/2503.04730/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWdwqSbPQ4WC8B6ysujR6S8MmPLKGdFRsKkiFrOGYQvthWg2uTc0vISG8SIqu7tfewpAj+gHKk1EcYGTyieFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:17:18.262795Z"},"content_sha256":"09a85483b0b54f471924c5e392251deda8d3bcce04845b08af5b5fa137ebb733","schema_version":"1.0","event_id":"sha256:09a85483b0b54f471924c5e392251deda8d3bcce04845b08af5b5fa137ebb733"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MX74S6UKUSS7CMOXV33MBVRN66/bundle.json","state_url":"https://pith.science/pith/MX74S6UKUSS7CMOXV33MBVRN66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MX74S6UKUSS7CMOXV33MBVRN66/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:17:18Z","links":{"resolver":"https://pith.science/pith/MX74S6UKUSS7CMOXV33MBVRN66","bundle":"https://pith.science/pith/MX74S6UKUSS7CMOXV33MBVRN66/bundle.json","state":"https://pith.science/pith/MX74S6UKUSS7CMOXV33MBVRN66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MX74S6UKUSS7CMOXV33MBVRN66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MX74S6UKUSS7CMOXV33MBVRN66","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":"9146c2de660dcaa173b26452b232fe05441acb4f66a6d7f7131f10e956840f77","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T08:29:17Z","title_canon_sha256":"c51140a32819d10d35ff5d96c19a1d61edb956afddb07a4dd4f4c02c90b4c338"},"schema_version":"1.0","source":{"id":"2503.04730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04730","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04730v1","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04730","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"MX74S6UKUSS7","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"MX74S6UKUSS7CMOX","created_at":"2026-07-05T10:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"MX74S6UK","created_at":"2026-07-05T10:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:09a85483b0b54f471924c5e392251deda8d3bcce04845b08af5b5fa137ebb733","target":"graph","created_at":"2026-07-05T10:25:47Z","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/2503.04730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphical User Interface (GUI) tasks are vital for automating workflows such as software testing, user interface navigation. For users, the GUI is the most intuitive platform for interacting with a computer. Previous work identified a key challenge in developing visual GUI agents: GUI grounding - the ability to accurately locate screen elements based on instructions. However, most existing GUI agents rely on structured data formats like DOM or HTML files in training or inferencing, which are inaccessible across all applications, particular in a general desktop environments such as Windows OS. ","authors_text":"Colby Banbury, Dan Zhao, Kazuhito Koishida, Tianyi Chen, Yinheng Li, Zheng Hui","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T08:29:17Z","title":"WinClick: GUI Grounding with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04730","kind":"arxiv","version":1},"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":"sha256:615b8fd9044cc73e60817ac85ac2c6b3ef813ab6cb8639917fc7d140a2286493","target":"record","created_at":"2026-07-05T10:25:47Z","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":"9146c2de660dcaa173b26452b232fe05441acb4f66a6d7f7131f10e956840f77","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T08:29:17Z","title_canon_sha256":"c51140a32819d10d35ff5d96c19a1d61edb956afddb07a4dd4f4c02c90b4c338"},"schema_version":"1.0","source":{"id":"2503.04730","kind":"arxiv","version":1}},"canonical_sha256":"65ffc97a8aa4a5f131d7aef6c0d62df79d249b441f402c387fece4d1f76de597","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65ffc97a8aa4a5f131d7aef6c0d62df79d249b441f402c387fece4d1f76de597","first_computed_at":"2026-07-05T10:25:47.388939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:47.388939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N3//rlULiFdd35OmKb+YkOyudito7tvHgk24wkoScqixCRBirXOuJyDMuYS486/ODU4X2OLqbFP1ELEtnMC4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:47.389474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:615b8fd9044cc73e60817ac85ac2c6b3ef813ab6cb8639917fc7d140a2286493","sha256:09a85483b0b54f471924c5e392251deda8d3bcce04845b08af5b5fa137ebb733"],"state_sha256":"c2549eb2d9ef7316407b484d20758ff24ba38385d5ba37c8e454449c28c3019f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnAhL/tp1R+N7geMSVLt0fEHSdUJNDNtgFIPi7yrABLAQSpPnrQsOx1j4SA+dRg1UxvF/BFTd7l4Ft/w/lq4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:17:18.274950Z","bundle_sha256":"9cfd02080bfaa71301fdefa20bc59bd3543beaaa578bc7793ff4a3c273ca684f"}}