{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQZYFQSIKEXHA6STSGUEBK3V3A","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":"7c14a5d99f1c6bd89285bf4784efd63573378fb8c2ae622f9ffd1fad4596a550","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T15:28:48Z","title_canon_sha256":"226b2206ac4e25d34a7a9ab235c289db61fc8a87b630a16020cc081d4dff1ac7"},"schema_version":"1.0","source":{"id":"2410.04521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04521","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04521v1","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04521","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"CQZYFQSIKEXH","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"CQZYFQSIKEXHA6ST","created_at":"2026-07-05T09:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"CQZYFQSI","created_at":"2026-07-05T09:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:ed3223960c067961d6ab962acc5fc14add1fb1216b85bf5e6e9ae37f2438cdf2","target":"graph","created_at":"2026-07-05T09:16:35Z","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/2410.04521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent advancements, multimodal large language models (MLLMs) have been fine-tuned on specific medical image datasets to address medical visual question answering (Med-VQA) tasks. However, this common approach of task-specific fine-tuning is costly and necessitates separate models for each downstream task, limiting the exploration of zero-shot capabilities. In this paper, we introduce MC-CoT, a modular cross-modal collaboration Chain-of-Thought (CoT) framework designed to enhance the zero-shot performance of MLLMs in Med-VQA by leveraging large language models (LLMs). MC-CoT improves reason","authors_text":"Lai Wei, Wei Chen, Wenkai Wang, Xiaojin Zhang, Xiaoyu Shen, Yu Xie, Zhihao Fan, Zhongyu Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T15:28:48Z","title":"MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04521","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:c43101cf3ea310edbee088638fcabe5cea8f0d178219604e9558921e40e5f6bd","target":"record","created_at":"2026-07-05T09:16:35Z","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":"7c14a5d99f1c6bd89285bf4784efd63573378fb8c2ae622f9ffd1fad4596a550","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T15:28:48Z","title_canon_sha256":"226b2206ac4e25d34a7a9ab235c289db61fc8a87b630a16020cc081d4dff1ac7"},"schema_version":"1.0","source":{"id":"2410.04521","kind":"arxiv","version":1}},"canonical_sha256":"143382c248512e707a5391a840ab75d80e290dab32929f1a1a0254412c95e66b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"143382c248512e707a5391a840ab75d80e290dab32929f1a1a0254412c95e66b","first_computed_at":"2026-07-05T09:16:35.426496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:35.426496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vmiwbOvr7dQxDePuoAzQDVimuG7aWbc+3Otzv3DWlqcW6Fn++q4xjvmpVEv9P1GOb3P/ilvdhs/VCDtmBLo7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:35.426986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c43101cf3ea310edbee088638fcabe5cea8f0d178219604e9558921e40e5f6bd","sha256:ed3223960c067961d6ab962acc5fc14add1fb1216b85bf5e6e9ae37f2438cdf2"],"state_sha256":"9a232383ac5c4f5d7cb3057038b0f5663589d299597166d2421f6d72a10ae95d"}