{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4LPIUM4K4ZSICKQY6IRO7PWX4Z","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":"6a780f055d99d88f21a3742af55e51ef83c9b5ec17d346d4109e5536c2d6c10b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T07:00:46Z","title_canon_sha256":"4258df22b44040723a5bb8c47a5789ff9bc51b62bc6fbc449fb4a20c9e4ae093"},"schema_version":"1.0","source":{"id":"2412.15606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15606","created_at":"2026-07-05T10:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15606v2","created_at":"2026-07-05T10:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15606","created_at":"2026-07-05T10:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"4LPIUM4K4ZSI","created_at":"2026-07-05T10:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"4LPIUM4K4ZSICKQY","created_at":"2026-07-05T10:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"4LPIUM4K","created_at":"2026-07-05T10:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:04b13ba71b203fb3210d86221d4d96f444209f2ce3c45b4d2b0ec1030cdacf63","target":"graph","created_at":"2026-07-05T10:08:26Z","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/2412.15606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-modal tool-usage data and tunes a vision-language model (VLM) as the controller for powerful tool-usage reasoning. To preserve the data quality, we prompt the GPT-4o mini model to generate queries, files, and trajectories, followed by query-file and trajectory verifiers. Based on the data synthesis pipe","authors_text":"Bofei Zhang, Pengxiang Li, Qing Li, Song-Chun Zhu, Tao Yuan, Xiaojian Ma, Yue Fan, Yunde Jia, Yuwei Wu, Zhi Gao","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T07:00:46Z","title":"Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15606","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":"sha256:324306679d0a9efa41fae88d6c86eb5bc721e4ab1500f7ee955ebfe23cf3b9b7","target":"record","created_at":"2026-07-05T10:08:26Z","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":"6a780f055d99d88f21a3742af55e51ef83c9b5ec17d346d4109e5536c2d6c10b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T07:00:46Z","title_canon_sha256":"4258df22b44040723a5bb8c47a5789ff9bc51b62bc6fbc449fb4a20c9e4ae093"},"schema_version":"1.0","source":{"id":"2412.15606","kind":"arxiv","version":2}},"canonical_sha256":"e2de8a338ae664812a18f222efbed7e669689ce6d9807d8e607b9d03afae0760","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2de8a338ae664812a18f222efbed7e669689ce6d9807d8e607b9d03afae0760","first_computed_at":"2026-07-05T10:08:26.605350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:26.605350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mptRWRE+Q643XjssjspKIsRwWc+CbSheuK4ls60mRBvq3DmVAMc5bYSZb3obot0uSXOOHZfEKgmPqyTFnImqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:26.605843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:324306679d0a9efa41fae88d6c86eb5bc721e4ab1500f7ee955ebfe23cf3b9b7","sha256:04b13ba71b203fb3210d86221d4d96f444209f2ce3c45b4d2b0ec1030cdacf63"],"state_sha256":"1a4446eb00d6de50404f79bd600dd68c974c7aad52596b0615e2d3140fd88c9b"}