{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TQLEAYACLJ7LOSWBB4PAJ6NPGM","short_pith_number":"pith:TQLEAYAC","schema_version":"1.0","canonical_sha256":"9c164060025a7eb74ac10f1e04f9af3338e8ec526cd381662b5a5b22e9539f6e","source":{"kind":"arxiv","id":"2401.06805","version":2},"attestation_state":"computed","paper":{"title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohan Zhai, Haiteng Zhao, Hongxia Yang, Jianbo Yuan, Quanzeng You, Wentao Chen, Xiaotian Han, Xudong Lin, Yiqi Wang, Yongfei Liu","submitted_at":"2024-01-10T15:29:21Z","abstract_excerpt":"Strong Artificial Intelligence (Strong AI) or Artificial General Intelligence (AGI) with abstract reasoning ability is the goal of next-generation AI. Recent advancements in Large Language Models (LLMs), along with the emerging field of Multimodal Large Language Models (MLLMs), have demonstrated impressive capabilities across a wide range of multimodal tasks and applications. Particularly, various MLLMs, each with distinct model architectures, training data, and training stages, have been evaluated across a broad range of MLLM benchmarks. These studies have, to varying degrees, revealed differ"},"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":"2401.06805","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-10T15:29:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec1d92ddbe6e8560e8e61f9b218f06fa18d3967caa595b2d1f92387368c7547d","abstract_canon_sha256":"c6555139be3889ae2b391bbf204fe082609454feb4cc4ff3eea447a824b50501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:54.477034Z","signature_b64":"CJ3CZPKGnXrG4MuM+rzhVr9wXSoCiB8DqREyqYAeSbeih5CMPA0zQe1sP4Ak/ziUQw/bA7KYRKBVi+PFzv7TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c164060025a7eb74ac10f1e04f9af3338e8ec526cd381662b5a5b22e9539f6e","last_reissued_at":"2026-07-05T07:34:54.476515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:54.476515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohan Zhai, Haiteng Zhao, Hongxia Yang, Jianbo Yuan, Quanzeng You, Wentao Chen, Xiaotian Han, Xudong Lin, Yiqi Wang, Yongfei Liu","submitted_at":"2024-01-10T15:29:21Z","abstract_excerpt":"Strong Artificial Intelligence (Strong AI) or Artificial General Intelligence (AGI) with abstract reasoning ability is the goal of next-generation AI. Recent advancements in Large Language Models (LLMs), along with the emerging field of Multimodal Large Language Models (MLLMs), have demonstrated impressive capabilities across a wide range of multimodal tasks and applications. Particularly, various MLLMs, each with distinct model architectures, training data, and training stages, have been evaluated across a broad range of MLLM benchmarks. These studies have, to varying degrees, revealed differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06805","kind":"arxiv","version":2},"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/2401.06805/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":"2401.06805","created_at":"2026-07-05T07:34:54.476579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06805v2","created_at":"2026-07-05T07:34:54.476579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06805","created_at":"2026-07-05T07:34:54.476579+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQLEAYACLJ7L","created_at":"2026-07-05T07:34:54.476579+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQLEAYACLJ7LOSWB","created_at":"2026-07-05T07:34:54.476579+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQLEAYAC","created_at":"2026-07-05T07:34:54.476579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03713","citing_title":"Investigating Adversarial Robustness of Multi-modal Large Language Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27960","citing_title":"Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04509","citing_title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":198,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16549","citing_title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14159","citing_title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20950","citing_title":"Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01908","citing_title":"Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21540","citing_title":"PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07536","citing_title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04415","citing_title":"Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13375","citing_title":"GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11931","citing_title":"Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12335","citing_title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07518","citing_title":"Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08645","citing_title":"3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20254","citing_title":"Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM","json":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM.json","graph_json":"https://pith.science/api/pith-number/TQLEAYACLJ7LOSWBB4PAJ6NPGM/graph.json","events_json":"https://pith.science/api/pith-number/TQLEAYACLJ7LOSWBB4PAJ6NPGM/events.json","paper":"https://pith.science/paper/TQLEAYAC"},"agent_actions":{"view_html":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM","download_json":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM.json","view_paper":"https://pith.science/paper/TQLEAYAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06805&json=true","fetch_graph":"https://pith.science/api/pith-number/TQLEAYACLJ7LOSWBB4PAJ6NPGM/graph.json","fetch_events":"https://pith.science/api/pith-number/TQLEAYACLJ7LOSWBB4PAJ6NPGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM/action/storage_attestation","attest_author":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM/action/author_attestation","sign_citation":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM/action/citation_signature","submit_replication":"https://pith.science/pith/TQLEAYACLJ7LOSWBB4PAJ6NPGM/action/replication_record"}},"created_at":"2026-07-05T07:34:54.476579+00:00","updated_at":"2026-07-05T07:34:54.476579+00:00"}