{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CNWATLJHBEC4KEBL47KUXJ7D5P","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":"0cc47295822008f96e5d17a8e4533e1a33cfbd63488df08c03c590b38a5cb872","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T17:59:29Z","title_canon_sha256":"540d4bc3cdddaa612773a909af33c7e886d71b9433de1349712faae246b74373"},"schema_version":"1.0","source":{"id":"2507.02859","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02859","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02859v1","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02859","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"CNWATLJHBEC4","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"pith_short_16","alias_value":"CNWATLJHBEC4KEBL","created_at":"2026-07-05T11:31:35Z"},{"alias_kind":"pith_short_8","alias_value":"CNWATLJH","created_at":"2026-07-05T11:31:35Z"}],"graph_snapshots":[{"event_id":"sha256:4f8a93361e2f54100c1aa4c2cb857fb6c6e470b81a9f58931d1ef79cb0bd200a","target":"graph","created_at":"2026-07-05T11:31:35Z","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/2507.02859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in interpreting images using natural language. However, without using large-scale datasets for retraining, these models are difficult to adapt to specialized vision tasks, e.g., chart understanding. This problem is caused by a mismatch between pre-training and downstream datasets: pre-training datasets primarily concentrate on scenes and objects but contain limited information about specialized, non-object images, such as charts and tables. In this paper, we share an interesting finding that training an MLLM wit","authors_text":"Bingkui Tong, Jiaer Xia, Kaiyang Zhou, Rui Shao, Yuhang Zang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T17:59:29Z","title":"Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02859","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":"sha256:05436bfdff284cd9d07476d89cc61fc22a1c9125eb3ce4af00f4dc6b9eb0a56c","target":"record","created_at":"2026-07-05T11:31:35Z","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":"0cc47295822008f96e5d17a8e4533e1a33cfbd63488df08c03c590b38a5cb872","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T17:59:29Z","title_canon_sha256":"540d4bc3cdddaa612773a909af33c7e886d71b9433de1349712faae246b74373"},"schema_version":"1.0","source":{"id":"2507.02859","kind":"arxiv","version":1}},"canonical_sha256":"136c09ad270905c5102be7d54ba7e3ebc9b5f3a3b4fc1fd2375b64d151d61e00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"136c09ad270905c5102be7d54ba7e3ebc9b5f3a3b4fc1fd2375b64d151d61e00","first_computed_at":"2026-07-05T11:31:35.491258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:35.491258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eAyQ1EYuiDSbWGlrDK0ncoFhebXuaxd0A5iDs8j68wxLVV6pKPbEqvnnvNg8e4tvRhi8fKlZ0bL2SUszncKGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:35.491736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02859","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05436bfdff284cd9d07476d89cc61fc22a1c9125eb3ce4af00f4dc6b9eb0a56c","sha256:4f8a93361e2f54100c1aa4c2cb857fb6c6e470b81a9f58931d1ef79cb0bd200a"],"state_sha256":"982e0b1aff435cab593f5f2705d38d83aade891a05fb1cde5825f7c9753c8134"}