{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NEJSSQX73EMZUT4GQRG76RRWLV","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":"28226107f6dd8aa4117957d7af16f70c5a19101caf5fcc788e7b3f85903c86a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:31:56Z","title_canon_sha256":"a47e565760f6a23a33e1f2474913d7fad8bc80f790bb5dc44283360a1910c630"},"schema_version":"1.0","source":{"id":"2507.07424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07424","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07424v1","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07424","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"pith_short_12","alias_value":"NEJSSQX73EMZ","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"pith_short_16","alias_value":"NEJSSQX73EMZUT4G","created_at":"2026-07-05T11:34:57Z"},{"alias_kind":"pith_short_8","alias_value":"NEJSSQX7","created_at":"2026-07-05T11:34:57Z"}],"graph_snapshots":[{"event_id":"sha256:4884b89e273cd15068cd8755a4b25a43f3d8245d69ead6c9aa272302fe508dec","target":"graph","created_at":"2026-07-05T11:34:57Z","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/2507.07424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have demonstrated exceptional performance in multimodal perception and understanding. However, leading open-source MLLMs exhibit significant limitations in complex and structured reasoning, particularly in tasks requiring deep reasoning for decision-making and problem-solving. In this work, we present Corvid, an MLLM with enhanced chain-of-thought (CoT) reasoning capabilities. Architecturally, Corvid incorporates a hybrid vision encoder for informative visual representation and a meticulously designed connector (GateMixer) to faci","authors_text":"Chao Ma, Hanwang Zhang, Jingjing Jiang, Jun Luo, Xurui Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:31:56Z","title":"Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07424","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:c331b0bb5b42bfe429751adfe6f64e9ed542570e3f7efb573f9e0701b3727fca","target":"record","created_at":"2026-07-05T11:34:57Z","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":"28226107f6dd8aa4117957d7af16f70c5a19101caf5fcc788e7b3f85903c86a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T04:31:56Z","title_canon_sha256":"a47e565760f6a23a33e1f2474913d7fad8bc80f790bb5dc44283360a1910c630"},"schema_version":"1.0","source":{"id":"2507.07424","kind":"arxiv","version":1}},"canonical_sha256":"69132942ffd9199a4f86844dff46365d76fc71d2708d2db49152a1991144322f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69132942ffd9199a4f86844dff46365d76fc71d2708d2db49152a1991144322f","first_computed_at":"2026-07-05T11:34:57.711683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:57.711683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N4Yprd5OYVMdVFSXeeiVZUEpy32BVbjBfm4LTnKXciitVRBTvkue8rqJQrK3QBdC0qNMrrzKDKGCUQCtSNrzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:57.712163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c331b0bb5b42bfe429751adfe6f64e9ed542570e3f7efb573f9e0701b3727fca","sha256:4884b89e273cd15068cd8755a4b25a43f3d8245d69ead6c9aa272302fe508dec"],"state_sha256":"db2d60099021fa2579cc86113b3e116fae18583db9004b9fe99fe01ab03c619b"}