{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5WLNJWNQGMVEBZXVAN7SOXXOCJ","short_pith_number":"pith:5WLNJWNQ","canonical_record":{"source":{"id":"2406.10819","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T06:56:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b1a7e50c574f204f44a08ea94424d1a27f6ef40ef589fd414ff7f959c8b31657","abstract_canon_sha256":"acd3119d8a435a1d4ef8a8ad155ce978bae69424cf9204c214e15ad0c41605fc"},"schema_version":"1.0"},"canonical_sha256":"ed96d4d9b0332a40e6f5037f275eee124560f3a662fe631c7c0760cb106d402e","source":{"kind":"arxiv","id":"2406.10819","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10819","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10819v2","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10819","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_12","alias_value":"5WLNJWNQGMVE","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_16","alias_value":"5WLNJWNQGMVEBZXV","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_8","alias_value":"5WLNJWNQ","created_at":"2026-07-05T10:37:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5WLNJWNQGMVEBZXVAN7SOXXOCJ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10819","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T06:56:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b1a7e50c574f204f44a08ea94424d1a27f6ef40ef589fd414ff7f959c8b31657","abstract_canon_sha256":"acd3119d8a435a1d4ef8a8ad155ce978bae69424cf9204c214e15ad0c41605fc"},"schema_version":"1.0"},"canonical_sha256":"ed96d4d9b0332a40e6f5037f275eee124560f3a662fe631c7c0760cb106d402e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:27.428256Z","signature_b64":"YUnBM6lK+wfQQnBVJsdkV9qrUg5IB8rdtMQdNU0UB2QWjV44uda2NmeddghRZ8lCr9RqXXuZ4HAk1eBwX98uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed96d4d9b0332a40e6f5037f275eee124560f3a662fe631c7c0760cb106d402e","last_reissued_at":"2026-07-05T10:37:27.427339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:27.427339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10819","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":"2026-07-05T10:37:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bMslzvmyeeHUEHHBGBHeGf1h+9KuA1Y/Dv2S7S880/qxG9BjIRaRg7PhVq389nwlIc4xYy2tUWkoIDH8ZvNWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:21:01.343666Z"},"content_sha256":"36eec80c701100607836d74b438bc36e859c494ff15fbb9468adbed13195ed31","schema_version":"1.0","event_id":"sha256:36eec80c701100607836d74b438bc36e859c494ff15fbb9468adbed13195ed31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5WLNJWNQGMVEBZXVAN7SOXXOCJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenlong Wang, Chujie Gao, Dongping Chen, Huichi Zhou, Jianfeng Gao, Jingyu Tang, Lichao Sun, Liuyi Chen, Pan Zhou, Qihui Zhang, Siyuan Wu, Tianshuo Zhou, Yao Wan, Yi Gui, Yilin Bai, Yiqiang Li, Yue Huang, Yue Yu, Zhen Li, Zhigang He","submitted_at":"2024-06-16T06:56:53Z","abstract_excerpt":"Recently, Multimodal Large Language Models (MLLMs) have been used as agents to control keyboard and mouse inputs by directly perceiving the Graphical User Interface (GUI) and generating corresponding commands. However, current agents primarily demonstrate strong understanding capabilities in static environments and are mainly applied to relatively simple domains, such as Web or mobile interfaces. We argue that a robust GUI agent should be capable of perceiving temporal information on the GUI, including dynamic Web content and multi-step tasks. Additionally, it should possess a comprehensive un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10819","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/2406.10819/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":"2026-07-05T10:37:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BA6+IfB+8I+qJ0bI4fnrYzIskYGKmbDxJ9S2nG306y/sAgAArYjkWAFnYEAyTi4MVuV0mWy8tZbPFEYFhZApDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:21:01.344738Z"},"content_sha256":"6dda4cbe4a29493b7a3cf28b77ac71c0ce82deb066241c83ad9f6101a418df2b","schema_version":"1.0","event_id":"sha256:6dda4cbe4a29493b7a3cf28b77ac71c0ce82deb066241c83ad9f6101a418df2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ/bundle.json","state_url":"https://pith.science/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ/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":"2026-08-04T10:21:01Z","links":{"resolver":"https://pith.science/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ","bundle":"https://pith.science/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ/bundle.json","state":"https://pith.science/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WLNJWNQGMVEBZXVAN7SOXXOCJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WLNJWNQGMVEBZXVAN7SOXXOCJ","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":"acd3119d8a435a1d4ef8a8ad155ce978bae69424cf9204c214e15ad0c41605fc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T06:56:53Z","title_canon_sha256":"b1a7e50c574f204f44a08ea94424d1a27f6ef40ef589fd414ff7f959c8b31657"},"schema_version":"1.0","source":{"id":"2406.10819","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10819","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10819v2","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10819","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_12","alias_value":"5WLNJWNQGMVE","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_16","alias_value":"5WLNJWNQGMVEBZXV","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_8","alias_value":"5WLNJWNQ","created_at":"2026-07-05T10:37:27Z"}],"graph_snapshots":[{"event_id":"sha256:6dda4cbe4a29493b7a3cf28b77ac71c0ce82deb066241c83ad9f6101a418df2b","target":"graph","created_at":"2026-07-05T10:37:27Z","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/2406.10819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Multimodal Large Language Models (MLLMs) have been used as agents to control keyboard and mouse inputs by directly perceiving the Graphical User Interface (GUI) and generating corresponding commands. However, current agents primarily demonstrate strong understanding capabilities in static environments and are mainly applied to relatively simple domains, such as Web or mobile interfaces. We argue that a robust GUI agent should be capable of perceiving temporal information on the GUI, including dynamic Web content and multi-step tasks. Additionally, it should possess a comprehensive un","authors_text":"Chenlong Wang, Chujie Gao, Dongping Chen, Huichi Zhou, Jianfeng Gao, Jingyu Tang, Lichao Sun, Liuyi Chen, Pan Zhou, Qihui Zhang, Siyuan Wu, Tianshuo Zhou, Yao Wan, Yi Gui, Yilin Bai, Yiqiang Li, Yue Huang, Yue Yu, Zhen Li, Zhigang He","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T06:56:53Z","title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10819","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":"sha256:36eec80c701100607836d74b438bc36e859c494ff15fbb9468adbed13195ed31","target":"record","created_at":"2026-07-05T10:37:27Z","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":"acd3119d8a435a1d4ef8a8ad155ce978bae69424cf9204c214e15ad0c41605fc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T06:56:53Z","title_canon_sha256":"b1a7e50c574f204f44a08ea94424d1a27f6ef40ef589fd414ff7f959c8b31657"},"schema_version":"1.0","source":{"id":"2406.10819","kind":"arxiv","version":2}},"canonical_sha256":"ed96d4d9b0332a40e6f5037f275eee124560f3a662fe631c7c0760cb106d402e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed96d4d9b0332a40e6f5037f275eee124560f3a662fe631c7c0760cb106d402e","first_computed_at":"2026-07-05T10:37:27.427339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:27.427339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YUnBM6lK+wfQQnBVJsdkV9qrUg5IB8rdtMQdNU0UB2QWjV44uda2NmeddghRZ8lCr9RqXXuZ4HAk1eBwX98uBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:27.428256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10819","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36eec80c701100607836d74b438bc36e859c494ff15fbb9468adbed13195ed31","sha256:6dda4cbe4a29493b7a3cf28b77ac71c0ce82deb066241c83ad9f6101a418df2b"],"state_sha256":"bd84077e1073b4458756af85312fcdfc6a77e900277fde4ab599a025d60f503c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"prOMzLgDHYPSspZptENpZ62Xrz3ztm/N/Acyh8BvaMGyhBV1xeT6UegrGr67N57XpvqwnIcFfdBb3IfkLKAyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:21:01.350768Z","bundle_sha256":"c3e72dcc56df3737c043783153adcdc88d68139461affd093e1b21e5579590c9"}}