{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XPQEDQ52F3GJ7IPFWOLIUFU6AK","short_pith_number":"pith:XPQEDQ52","canonical_record":{"source":{"id":"2507.19478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:59:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ad345452a5d62325efbf4b63942310fe5c7f167b099132aad1f37da668e7553a","abstract_canon_sha256":"53be7f39310da7aa9920551e61651262a5b1aff55c35bf486a45e4a10a5ced07"},"schema_version":"1.0"},"canonical_sha256":"bbe041c3ba2ecc9fa1e5b3968a169e028df195688e9d15e88e2b358805e66801","source":{"kind":"arxiv","id":"2507.19478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19478","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19478v1","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19478","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"XPQEDQ52F3GJ","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"XPQEDQ52F3GJ7IPF","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"XPQEDQ52","created_at":"2026-07-05T11:43:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XPQEDQ52F3GJ7IPFWOLIUFU6AK","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:59:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ad345452a5d62325efbf4b63942310fe5c7f167b099132aad1f37da668e7553a","abstract_canon_sha256":"53be7f39310da7aa9920551e61651262a5b1aff55c35bf486a45e4a10a5ced07"},"schema_version":"1.0"},"canonical_sha256":"bbe041c3ba2ecc9fa1e5b3968a169e028df195688e9d15e88e2b358805e66801","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:26.084649Z","signature_b64":"QnLSdQaRJHyg6nbxleqdeYo57voU6GKLtwyD5aTRU0e7vRF4Sob9McUlEfyTC+Dvu1aqA9hflTSlF5YoZWsVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe041c3ba2ecc9fa1e5b3968a169e028df195688e9d15e88e2b358805e66801","last_reissued_at":"2026-07-05T11:43:26.084084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:26.084084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19478","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":"2026-07-05T11:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nWgi/ddh6tsfHik2QGeFJgoGDdH0SzsVZ6CJ2TDHMIEBGY1OMDztyYMUsVLR3ljbfDDxzMavycqa6u3sTSIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:11:38.525998Z"},"content_sha256":"70f4f1a876d9bab88058e4e2defc8d927805f61bd24a97f31951600b8ec56651","schema_version":"1.0","event_id":"sha256:70f4f1a876d9bab88058e4e2defc8d927805f61bd24a97f31951600b8ec56651"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XPQEDQ52F3GJ7IPFWOLIUFU6AK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bowen Yang, Chenyu Yang, Haodong Duan, Jifeng Dai, Jingjing Xie, Jixuan Chen, Qingyun Li, Shiqian Su, Tianbao Xie, Weijie Su, Wei Shen, Weiyun Wang, Wenhai Wang, Xiangyu Yue, Xiangyu Zhao, Xiao Zhang, Xizhou Zhu, Xuan Dong, Xuehui Wang, Yanting Zhang, Yiqian Liu, Yuan Huang, Yue Yu, Zehao Li, Zhaoyang Liu, Zhe Chen, Zhenyu Wu, Zichen Ding","submitted_at":"2025-07-25T17:59:26Z","abstract_excerpt":"We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. In addition, we propose a novel Efficiency-Quality Area (EQA) metric to assess GUI agent execution efficiency in online automation scenarios. Through MMBench-GUI, we identify accurate visual grounding as a critical determinant of overall task success, emphasizing the substantial benefits of mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19478","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/2507.19478/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":"2026-07-05T11:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZdOtiOvDCcc/njrRzP//NoIZjblM5cIaEH6eCn11NeFr+DSBASFPEPfcM4cIIqPTJZm9SlVD79Om4f/nrUsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:11:38.526498Z"},"content_sha256":"dd9a54d9d89cc2e3f6314613f8d99eb010353b1f7b6c5bf8ae0ea5fb08cb9406","schema_version":"1.0","event_id":"sha256:dd9a54d9d89cc2e3f6314613f8d99eb010353b1f7b6c5bf8ae0ea5fb08cb9406"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK/bundle.json","state_url":"https://pith.science/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK/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":"2026-08-05T02:11:38Z","links":{"resolver":"https://pith.science/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK","bundle":"https://pith.science/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK/bundle.json","state":"https://pith.science/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPQEDQ52F3GJ7IPFWOLIUFU6AK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPQEDQ52F3GJ7IPFWOLIUFU6AK","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":"53be7f39310da7aa9920551e61651262a5b1aff55c35bf486a45e4a10a5ced07","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:59:26Z","title_canon_sha256":"ad345452a5d62325efbf4b63942310fe5c7f167b099132aad1f37da668e7553a"},"schema_version":"1.0","source":{"id":"2507.19478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19478","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19478v1","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19478","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"XPQEDQ52F3GJ","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"XPQEDQ52F3GJ7IPF","created_at":"2026-07-05T11:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"XPQEDQ52","created_at":"2026-07-05T11:43:26Z"}],"graph_snapshots":[{"event_id":"sha256:dd9a54d9d89cc2e3f6314613f8d99eb010353b1f7b6c5bf8ae0ea5fb08cb9406","target":"graph","created_at":"2026-07-05T11:43:26Z","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/2507.19478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. In addition, we propose a novel Efficiency-Quality Area (EQA) metric to assess GUI agent execution efficiency in online automation scenarios. Through MMBench-GUI, we identify accurate visual grounding as a critical determinant of overall task success, emphasizing the substantial benefits of mo","authors_text":"Bowen Yang, Chenyu Yang, Haodong Duan, Jifeng Dai, Jingjing Xie, Jixuan Chen, Qingyun Li, Shiqian Su, Tianbao Xie, Weijie Su, Wei Shen, Weiyun Wang, Wenhai Wang, Xiangyu Yue, Xiangyu Zhao, Xiao Zhang, Xizhou Zhu, Xuan Dong, Xuehui Wang, Yanting Zhang, Yiqian Liu, Yuan Huang, Yue Yu, Zehao Li, Zhaoyang Liu, Zhe Chen, Zhenyu Wu, Zichen Ding","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:59:26Z","title":"MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19478","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":"sha256:70f4f1a876d9bab88058e4e2defc8d927805f61bd24a97f31951600b8ec56651","target":"record","created_at":"2026-07-05T11:43:26Z","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":"53be7f39310da7aa9920551e61651262a5b1aff55c35bf486a45e4a10a5ced07","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:59:26Z","title_canon_sha256":"ad345452a5d62325efbf4b63942310fe5c7f167b099132aad1f37da668e7553a"},"schema_version":"1.0","source":{"id":"2507.19478","kind":"arxiv","version":1}},"canonical_sha256":"bbe041c3ba2ecc9fa1e5b3968a169e028df195688e9d15e88e2b358805e66801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbe041c3ba2ecc9fa1e5b3968a169e028df195688e9d15e88e2b358805e66801","first_computed_at":"2026-07-05T11:43:26.084084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:26.084084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnLSdQaRJHyg6nbxleqdeYo57voU6GKLtwyD5aTRU0e7vRF4Sob9McUlEfyTC+Dvu1aqA9hflTSlF5YoZWsVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:26.084649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70f4f1a876d9bab88058e4e2defc8d927805f61bd24a97f31951600b8ec56651","sha256:dd9a54d9d89cc2e3f6314613f8d99eb010353b1f7b6c5bf8ae0ea5fb08cb9406"],"state_sha256":"8adb2fecd1f71bfbaf696a83ceb382e9905cb8d7d4988ec7e7e1d3dc0f74acdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VlFgWwB0CA+TEuW4IeHr1ENoYBxaB3OhT9jEJz3sx12k7hX8yglMVd8gvVR0/X6HRgsT++DehxzLsxA2fGr6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:11:38.530463Z","bundle_sha256":"4c2aa3685c953c9f00b5583d437044ca0a1aa0279db7f342750af195320f571b"}}