{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KXDKCZVVFLXI5T3B2XNMGMVZPM","short_pith_number":"pith:KXDKCZVV","canonical_record":{"source":{"id":"2406.11317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T08:30:55Z","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"title_canon_sha256":"48b47f7bafb0bbcf20d3685e14cb0c5678cd649c6bc34f06bf9b1771d9f59790","abstract_canon_sha256":"b7613ae5ff5395e7fc2f41b516959034acdd5a27ec23ce33bb8566330cb37a21"},"schema_version":"1.0"},"canonical_sha256":"55c6a166b52aee8ecf61d5dac332b97b1dd28083ae2e15f406ec396dc438f65d","source":{"kind":"arxiv","id":"2406.11317","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11317","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11317v2","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11317","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"KXDKCZVVFLXI","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"KXDKCZVVFLXI5T3B","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"KXDKCZVV","created_at":"2026-07-05T11:12:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KXDKCZVVFLXI5T3B2XNMGMVZPM","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T08:30:55Z","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"title_canon_sha256":"48b47f7bafb0bbcf20d3685e14cb0c5678cd649c6bc34f06bf9b1771d9f59790","abstract_canon_sha256":"b7613ae5ff5395e7fc2f41b516959034acdd5a27ec23ce33bb8566330cb37a21"},"schema_version":"1.0"},"canonical_sha256":"55c6a166b52aee8ecf61d5dac332b97b1dd28083ae2e15f406ec396dc438f65d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:18.153923Z","signature_b64":"b4bY7/AUG85dvZlo+cneVyog/YYsHZnNcKcWUIo3uUGLQA+qzW1OwBHMg17ZOGKvcaDFsyIo3zfaZtoqm/DVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55c6a166b52aee8ecf61d5dac332b97b1dd28083ae2e15f406ec396dc438f65d","last_reissued_at":"2026-07-05T11:12:18.153412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:18.153412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11317","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Oyzi66L+KWWEV132U2lw51Fbvbth8A7lNQLKzGZoTrW0SQNwldZer08Uo02I1vsp5XS0tjci9ylS85tUF9TAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:49:11.563582Z"},"content_sha256":"bdbfdb4ea540e4a8a7ab98431dbd45a122d2743d90a88fb4090ed5f4b0745f4d","schema_version":"1.0","event_id":"sha256:bdbfdb4ea540e4a8a7ab98431dbd45a122d2743d90a88fb4090ed5f4b0745f4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KXDKCZVVFLXI5T3B2XNMGMVZPM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GUICourse: From General Vision Language Models to Versatile GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.HC"],"primary_cat":"cs.AI","authors_text":"Chongyi Wang, Guirong Chen, Jinyi Hu, Junbo Cui, Junjie Fang, Jun Liu, Maosong Sun, Wentong Chen, Yankai Lin, Yuan Yao, Yue Zhao, Yujia Qin, Yupeng Huo, Zhiyuan Liu","submitted_at":"2024-06-17T08:30:55Z","abstract_excerpt":"Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to help humans finish GUI navigation tasks. However, current VLMs are challenged in terms of fundamental abilities (OCR and grounding) and GUI knowledge (the functions and control methods of GUI elements), preventing them from becoming practical GUI agents. To solve these challenges, we contribute GUICourse, a suite of datasets to train visual-based GUI "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11317","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/2406.11317/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":"2026-07-05T11:12:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MxXwRSXFW6G6OpNUorO5vMHOF4+niROPTHfTmotLpXv9S1utd2HCOa7FqqYNcO6CJ2WF0ZCWq+75OhPMd9fuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:49:11.564476Z"},"content_sha256":"6b6ff3afdc515e16ccac9738a1ee48b144324660befaa8557310e40e4b21c618","schema_version":"1.0","event_id":"sha256:6b6ff3afdc515e16ccac9738a1ee48b144324660befaa8557310e40e4b21c618"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM/bundle.json","state_url":"https://pith.science/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM/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":"2026-08-18T08:49:11Z","links":{"resolver":"https://pith.science/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM","bundle":"https://pith.science/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM/bundle.json","state":"https://pith.science/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXDKCZVVFLXI5T3B2XNMGMVZPM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KXDKCZVVFLXI5T3B2XNMGMVZPM","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":"b7613ae5ff5395e7fc2f41b516959034acdd5a27ec23ce33bb8566330cb37a21","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T08:30:55Z","title_canon_sha256":"48b47f7bafb0bbcf20d3685e14cb0c5678cd649c6bc34f06bf9b1771d9f59790"},"schema_version":"1.0","source":{"id":"2406.11317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11317","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11317v2","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11317","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"KXDKCZVVFLXI","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"KXDKCZVVFLXI5T3B","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"KXDKCZVV","created_at":"2026-07-05T11:12:18Z"}],"graph_snapshots":[{"event_id":"sha256:6b6ff3afdc515e16ccac9738a1ee48b144324660befaa8557310e40e4b21c618","target":"graph","created_at":"2026-07-05T11:12:18Z","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/2406.11317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to help humans finish GUI navigation tasks. However, current VLMs are challenged in terms of fundamental abilities (OCR and grounding) and GUI knowledge (the functions and control methods of GUI elements), preventing them from becoming practical GUI agents. To solve these challenges, we contribute GUICourse, a suite of datasets to train visual-based GUI ","authors_text":"Chongyi Wang, Guirong Chen, Jinyi Hu, Junbo Cui, Junjie Fang, Jun Liu, Maosong Sun, Wentong Chen, Yankai Lin, Yuan Yao, Yue Zhao, Yujia Qin, Yupeng Huo, Zhiyuan Liu","cross_cats":["cs.CL","cs.CV","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T08:30:55Z","title":"GUICourse: From General Vision Language Models to Versatile GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11317","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:bdbfdb4ea540e4a8a7ab98431dbd45a122d2743d90a88fb4090ed5f4b0745f4d","target":"record","created_at":"2026-07-05T11:12:18Z","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":"b7613ae5ff5395e7fc2f41b516959034acdd5a27ec23ce33bb8566330cb37a21","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T08:30:55Z","title_canon_sha256":"48b47f7bafb0bbcf20d3685e14cb0c5678cd649c6bc34f06bf9b1771d9f59790"},"schema_version":"1.0","source":{"id":"2406.11317","kind":"arxiv","version":2}},"canonical_sha256":"55c6a166b52aee8ecf61d5dac332b97b1dd28083ae2e15f406ec396dc438f65d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55c6a166b52aee8ecf61d5dac332b97b1dd28083ae2e15f406ec396dc438f65d","first_computed_at":"2026-07-05T11:12:18.153412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:18.153412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b4bY7/AUG85dvZlo+cneVyog/YYsHZnNcKcWUIo3uUGLQA+qzW1OwBHMg17ZOGKvcaDFsyIo3zfaZtoqm/DVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:18.153923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdbfdb4ea540e4a8a7ab98431dbd45a122d2743d90a88fb4090ed5f4b0745f4d","sha256:6b6ff3afdc515e16ccac9738a1ee48b144324660befaa8557310e40e4b21c618"],"state_sha256":"c787ed7b73458041c653280856e9ae5da8b09c0d3d9cdb14f873c87ed1cc5bda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bt7aXrD940UUmjhiN6dCppBSPMxZ8DjszhSEQhZYZYVMiPp7LwgvNwKiJidHghutRqePDjSPb3/c3ZUa65KEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:49:11.572724Z","bundle_sha256":"26294566a2d2ea5ae1dfbb9967f93fcac0ae4bedbce0408bb8cad333aaf25b7a"}}