{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W2CG4GPBFMRGXJFKFI3XQHA7A6","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":"3546d74051ec9dbf42322bd6c3becc5d135e0756150712e39288731c2f235b26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T15:39:14Z","title_canon_sha256":"6d6d134021f6e19049339f7e7ded1390fe4ec3dce2e8c7fa44b32403a25f0bc9"},"schema_version":"1.0","source":{"id":"2507.21924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21924","created_at":"2026-07-05T11:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21924v1","created_at":"2026-07-05T11:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21924","created_at":"2026-07-05T11:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"W2CG4GPBFMRG","created_at":"2026-07-05T11:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"W2CG4GPBFMRGXJFK","created_at":"2026-07-05T11:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"W2CG4GPB","created_at":"2026-07-05T11:45:09Z"}],"graph_snapshots":[{"event_id":"sha256:4ed74717ff136c5266705975de40903d822194b12b732b4f18694520f6baf0c8","target":"graph","created_at":"2026-07-05T11:45:09Z","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/2507.21924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), enhanced through agent tuning, have demonstrated remarkable capabilities in Chain-of-Thought (CoT) and tool utilization, significantly surpassing the performance of standalone models. However, the multimodal domain still lacks a large-scale, high-quality agent tuning dataset to unlock the full potential of multimodal large language models. To bridge this gap, we introduce MMAT-1M, the first million-scale multimodal agent tuning dataset designed to support CoT, reflection, and dynamic tool usage. Our dataset is constructed through a novel four-stage data engine: 1)","authors_text":"Gang Zhang, Haixiao Yue, Shanshan Liu, Tianhong Gao, Weiqun Wu, Yannian Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T15:39:14Z","title":"MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21924","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:b13e30b6150800056db9bb9a928ddc09d7e113c49ffa3a4cb952865af9e57861","target":"record","created_at":"2026-07-05T11:45:09Z","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":"3546d74051ec9dbf42322bd6c3becc5d135e0756150712e39288731c2f235b26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T15:39:14Z","title_canon_sha256":"6d6d134021f6e19049339f7e7ded1390fe4ec3dce2e8c7fa44b32403a25f0bc9"},"schema_version":"1.0","source":{"id":"2507.21924","kind":"arxiv","version":1}},"canonical_sha256":"b6846e19e12b226ba4aa2a37781c1f07b768c816cb94c5e36acd9fb5f3c62d02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6846e19e12b226ba4aa2a37781c1f07b768c816cb94c5e36acd9fb5f3c62d02","first_computed_at":"2026-07-05T11:45:09.903509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:09.903509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oogZrS9T7y3sgsatTvlQuqATedv3ElPf31yi4ebWMAwLv7nWGu8EIMTmUxUu/qDuX3AhenRneikBIbmEOvyPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:09.904002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b13e30b6150800056db9bb9a928ddc09d7e113c49ffa3a4cb952865af9e57861","sha256:4ed74717ff136c5266705975de40903d822194b12b732b4f18694520f6baf0c8"],"state_sha256":"7b78039ec272810747dadd07c514ff786a56d59a8160217ee4d2c9605aa7b792"}