{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C5JEH547MLU6RUDSNMOJXR4P6J","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":"a52dd15252321ce96f96d0ea89e589cb228bdec90af84c7089e42e08f496e254","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T18:14:24Z","title_canon_sha256":"775f88a39a0ba7add683b823586b925fc2cc2cdd23b47ba6a62b242a44943d18"},"schema_version":"1.0","source":{"id":"2412.05237","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05237","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05237v2","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05237","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"C5JEH547MLU6","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"C5JEH547MLU6RUDS","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"C5JEH547","created_at":"2026-07-05T11:15:41Z"}],"graph_snapshots":[{"event_id":"sha256:7e3823319360b6e717cd229106e9fb0776e53df6a65265d221a52722ee40ff08","target":"graph","created_at":"2026-07-05T11:15:41Z","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/2412.05237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were predominately repurposed from academic datasets such as VQA, AI2D, and ChartQA. These datasets target simplistic tasks, and only provide phrase-level answers without any intermediate rationales. To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate ratio","authors_text":"Bo Li, Graham Neubig, Jarvis Guo, King Zhu, Tuney Zheng, Wenhu Chen, Xiang Yue, Yizhi Li, Yubo Wang, Yuelin Bai","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T18:14:24Z","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05237","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":"sha256:62dd87ee8de8cfcec3037c2b2e2f2c2a3f55d36d3f6b3e2dd0bc198c2ac15fc0","target":"record","created_at":"2026-07-05T11:15:41Z","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":"a52dd15252321ce96f96d0ea89e589cb228bdec90af84c7089e42e08f496e254","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T18:14:24Z","title_canon_sha256":"775f88a39a0ba7add683b823586b925fc2cc2cdd23b47ba6a62b242a44943d18"},"schema_version":"1.0","source":{"id":"2412.05237","kind":"arxiv","version":2}},"canonical_sha256":"175243f79f62e9e8d0726b1c9bc78ff253c85b2241d0250c5f2fbf69c9af71ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"175243f79f62e9e8d0726b1c9bc78ff253c85b2241d0250c5f2fbf69c9af71ed","first_computed_at":"2026-07-05T11:15:41.028896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:41.028896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gOFrxAdBK1PDleP+towAFSH9vdX3VHAYC+dSkvEHvdcXnq9A57jglkknIyjnwUDQwxgljMOD9GtK6AvNK7u0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:41.029461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05237","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62dd87ee8de8cfcec3037c2b2e2f2c2a3f55d36d3f6b3e2dd0bc198c2ac15fc0","sha256:7e3823319360b6e717cd229106e9fb0776e53df6a65265d221a52722ee40ff08"],"state_sha256":"5bed7d9992a2ce958222e26c5f4d8d12a4d3d31805f51b7f9cfd742a877bcd04"}