{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YHUHYYFA3DWV4ACJIFO3WAHXIV","short_pith_number":"pith:YHUHYYFA","schema_version":"1.0","canonical_sha256":"c1e87c60a0d8ed5e0049415dbb00f7457b1583b9915ba8d2e8e84843801ef35f","source":{"kind":"arxiv","id":"2409.13980","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Advanced Visual Reasoning Ability of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyi Zhang, Dongnan Liu, Heng Wang, Tengfei Xue, Weidong Cai, Zhiyuan Li","submitted_at":"2024-09-21T02:10:19Z","abstract_excerpt":"Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks while struggling with complex reasoning scenarios. Conversely, Large Language Models (LLMs) demonstrate robust text reasoning capabilities; however, they lack visual acuity. To bridge this gap, we propose Complex Visual Reasoning Large Language Models (CVR-LLM), capitalizing on VLMs' visual perception proficiency and LLMs' extensive reasoning capability. Un"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.13980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T02:10:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"00f0af6451200baac6c6b7f82b61e93209c4a6e521740124c2de97e68a5ab0a9","abstract_canon_sha256":"6b2a259c2e65636c12d84baca927d4f54cb764c7c54e39e6fa5bf69455c2cecb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:09.728921Z","signature_b64":"pWrv+TbVWmtKVHOMoCiqEqP9KnXvO7PamzuNND9Dt2dWXxybuFAE9L9EsmqQKDzPPGApLVIsm/6FkPnDu0cfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1e87c60a0d8ed5e0049415dbb00f7457b1583b9915ba8d2e8e84843801ef35f","last_reissued_at":"2026-07-05T09:10:09.728451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:09.728451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Advanced Visual Reasoning Ability of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyi Zhang, Dongnan Liu, Heng Wang, Tengfei Xue, Weidong Cai, Zhiyuan Li","submitted_at":"2024-09-21T02:10:19Z","abstract_excerpt":"Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks while struggling with complex reasoning scenarios. Conversely, Large Language Models (LLMs) demonstrate robust text reasoning capabilities; however, they lack visual acuity. To bridge this gap, we propose Complex Visual Reasoning Large Language Models (CVR-LLM), capitalizing on VLMs' visual perception proficiency and LLMs' extensive reasoning capability. Un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13980","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.13980/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.13980","created_at":"2026-07-05T09:10:09.728509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13980v1","created_at":"2026-07-05T09:10:09.728509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13980","created_at":"2026-07-05T09:10:09.728509+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHUHYYFA3DWV","created_at":"2026-07-05T09:10:09.728509+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHUHYYFA3DWV4ACJ","created_at":"2026-07-05T09:10:09.728509+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHUHYYFA","created_at":"2026-07-05T09:10:09.728509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.10026","citing_title":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04570","citing_title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23179","citing_title":"Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV","json":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV.json","graph_json":"https://pith.science/api/pith-number/YHUHYYFA3DWV4ACJIFO3WAHXIV/graph.json","events_json":"https://pith.science/api/pith-number/YHUHYYFA3DWV4ACJIFO3WAHXIV/events.json","paper":"https://pith.science/paper/YHUHYYFA"},"agent_actions":{"view_html":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV","download_json":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV.json","view_paper":"https://pith.science/paper/YHUHYYFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13980&json=true","fetch_graph":"https://pith.science/api/pith-number/YHUHYYFA3DWV4ACJIFO3WAHXIV/graph.json","fetch_events":"https://pith.science/api/pith-number/YHUHYYFA3DWV4ACJIFO3WAHXIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV/action/storage_attestation","attest_author":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV/action/author_attestation","sign_citation":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV/action/citation_signature","submit_replication":"https://pith.science/pith/YHUHYYFA3DWV4ACJIFO3WAHXIV/action/replication_record"}},"created_at":"2026-07-05T09:10:09.728509+00:00","updated_at":"2026-07-05T09:10:09.728509+00:00"}