{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MB6WHGETVQFP756JN6QQIRPP76","short_pith_number":"pith:MB6WHGET","canonical_record":{"source":{"id":"2408.06327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:44:17Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ae8ef57dbf112370835b7d2939117ef5796c9de295a8a0e177525721e8bfb0a9","abstract_canon_sha256":"1da290cab9d0f62ac82f58a318eba145ba520c661970f32b1659aca69eaa1fef"},"schema_version":"1.0"},"canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","source":{"kind":"arxiv","id":"2408.06327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06327","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06327v1","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06327","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"MB6WHGETVQFP","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"MB6WHGETVQFP756J","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"MB6WHGET","created_at":"2026-07-05T08:54:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MB6WHGETVQFP756JN6QQIRPP76","target":"record","payload":{"canonical_record":{"source":{"id":"2408.06327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:44:17Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ae8ef57dbf112370835b7d2939117ef5796c9de295a8a0e177525721e8bfb0a9","abstract_canon_sha256":"1da290cab9d0f62ac82f58a318eba145ba520c661970f32b1659aca69eaa1fef"},"schema_version":"1.0"},"canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:39.208241Z","signature_b64":"A0iZd3vwnUchU/WgMvyARtW8TCtUe7NqRTmXV/xDivYyKo9xBWCOWr4ZTFmXiYAorsKjt3xsERWdMTeknqK3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","last_reissued_at":"2026-07-05T08:54:39.207756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:39.207756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.06327","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":"2026-07-05T08:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZmKnalWCM0lhc/TxWA42hWqfo4AcxL5ru+b/+qvQVmtZzc8PYeKFM9/9V7cR6EtcwhOVrxYus6nfkmYtl0KLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T13:48:10.219575Z"},"content_sha256":"ec683b9b6d0c3c3adbdabe141219b30921101df924025e97080230c447e09937","schema_version":"1.0","event_id":"sha256:ec683b9b6d0c3c3adbdabe141219b30921101df924025e97080230c447e09937"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MB6WHGETVQFP756JN6QQIRPP76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aohan Zeng, Chan Hee Song, Hanchen Zhang, Hanlin Zhao, Hanyu Lai, Hao Yu, Iat Long Iong, Jiadai Sun, Jie Tang, Lihang Pan, Ming Ding, Qinkai Zheng, Shudan Zhang, Shuntian Yao, Siyi Cheng, Tianjie Zhang, Wenyi Hong, Xiao Liu, Xiaotao Gu, Xinyi Liu, Xinyue Yang, Xixuan Song, Xueqiao Sun, Yifan Xu, Yu Gu, Yu Su, Yuxiao Dong, Yu Yang, Zehan Qi, Zhengxiao Du","submitted_at":"2024-08-12T17:44:17Z","abstract_excerpt":"Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06327","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/2408.06327/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":"2026-07-05T08:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XjoIAT/eBD0UKbd/t7/CgDs391jUg5uRXpVAdiTmYOknBOS8L62s6+kSLpo5pXaIbpZ3B71PYZFWpjsr99vAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T13:48:10.219980Z"},"content_sha256":"cb157be45a80f0271fba655ea52f7fb5c401dfda2ae1754a467042d0ff8ccbbc","schema_version":"1.0","event_id":"sha256:cb157be45a80f0271fba655ea52f7fb5c401dfda2ae1754a467042d0ff8ccbbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/bundle.json","state_url":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MB6WHGETVQFP756JN6QQIRPP76/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":"2026-07-11T13:48:10Z","links":{"resolver":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76","bundle":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/bundle.json","state":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MB6WHGETVQFP756JN6QQIRPP76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MB6WHGETVQFP756JN6QQIRPP76","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":"1da290cab9d0f62ac82f58a318eba145ba520c661970f32b1659aca69eaa1fef","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:44:17Z","title_canon_sha256":"ae8ef57dbf112370835b7d2939117ef5796c9de295a8a0e177525721e8bfb0a9"},"schema_version":"1.0","source":{"id":"2408.06327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06327","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06327v1","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06327","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"MB6WHGETVQFP","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"MB6WHGETVQFP756J","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"MB6WHGET","created_at":"2026-07-05T08:54:39Z"}],"graph_snapshots":[{"event_id":"sha256:cb157be45a80f0271fba655ea52f7fb5c401dfda2ae1754a467042d0ff8ccbbc","target":"graph","created_at":"2026-07-05T08:54:39Z","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/2408.06327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual fou","authors_text":"Aohan Zeng, Chan Hee Song, Hanchen Zhang, Hanlin Zhao, Hanyu Lai, Hao Yu, Iat Long Iong, Jiadai Sun, Jie Tang, Lihang Pan, Ming Ding, Qinkai Zheng, Shudan Zhang, Shuntian Yao, Siyi Cheng, Tianjie Zhang, Wenyi Hong, Xiao Liu, Xiaotao Gu, Xinyi Liu, Xinyue Yang, Xixuan Song, Xueqiao Sun, Yifan Xu, Yu Gu, Yu Su, Yuxiao Dong, Yu Yang, Zehan Qi, Zhengxiao Du","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:44:17Z","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06327","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:ec683b9b6d0c3c3adbdabe141219b30921101df924025e97080230c447e09937","target":"record","created_at":"2026-07-05T08:54:39Z","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":"1da290cab9d0f62ac82f58a318eba145ba520c661970f32b1659aca69eaa1fef","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:44:17Z","title_canon_sha256":"ae8ef57dbf112370835b7d2939117ef5796c9de295a8a0e177525721e8bfb0a9"},"schema_version":"1.0","source":{"id":"2408.06327","kind":"arxiv","version":1}},"canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","first_computed_at":"2026-07-05T08:54:39.207756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:39.207756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0iZd3vwnUchU/WgMvyARtW8TCtUe7NqRTmXV/xDivYyKo9xBWCOWr4ZTFmXiYAorsKjt3xsERWdMTeknqK3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:39.208241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec683b9b6d0c3c3adbdabe141219b30921101df924025e97080230c447e09937","sha256:cb157be45a80f0271fba655ea52f7fb5c401dfda2ae1754a467042d0ff8ccbbc"],"state_sha256":"e1a5772d5aa8f53cf08cae84b64a7b9d13a3042d5f809da081eb18c8e1030d31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JrCe6yNNXkPdrcOWB/GSQ8FQGmpDllKsFLAIuxCrjrEi9XtIvrzH7cizWWsqNspzxbRbclvul32aprp36YKTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T13:48:10.222393Z","bundle_sha256":"7e0aaacf746538cdceaced1e68390c6b5f033a398ee44721710da65b023a74e7"}}