{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZTBPJH5GTAMT335TVL3NODON54","short_pith_number":"pith:ZTBPJH5G","schema_version":"1.0","canonical_sha256":"ccc2f49fa698193defb3aaf6d70dcdef0ff4cb135199ae49e1c409a8fa230a5a","source":{"kind":"arxiv","id":"2309.14181","version":3},"attestation_state":"computed","paper":{"title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Annan Wang, Chaofeng Chen, Chunyi Li, Erli Zhang, Guangtao Zhai, Haoning Wu, Liang Liao, Qiong Yan, Weisi Lin, Wenxiu Sun, Zicheng Zhang","submitted_at":"2023-09-25T14:43:43Z","abstract_excerpt":"The rapid evolution of Multi-modality Large Language Models (MLLMs) has catalyzed a shift in computer vision from specialized models to general-purpose foundation models. Nevertheless, there is still an inadequacy in assessing the abilities of MLLMs on low-level visual perception and understanding. To address this gap, we present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment. a) To evaluate the low-level perception ability, we constru"},"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":"2309.14181","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T14:43:43Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"176a02cb4a0660280f833af1947d69c9961ba19d4574d6c0d0251c03eaa1278e","abstract_canon_sha256":"6817654141cda4f4956d1e21f51465447e220f90dfad349cd70678daedde4f04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:12.640135Z","signature_b64":"Qu6gq5NqV+sFpNecTeDnCFMVHE/fPa5am8rDit0sutntcyywqVG50f21KN4dxpAzqJ0by7DCnOtOVolHeoC5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccc2f49fa698193defb3aaf6d70dcdef0ff4cb135199ae49e1c409a8fa230a5a","last_reissued_at":"2026-07-05T07:29:12.639649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:12.639649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Annan Wang, Chaofeng Chen, Chunyi Li, Erli Zhang, Guangtao Zhai, Haoning Wu, Liang Liao, Qiong Yan, Weisi Lin, Wenxiu Sun, Zicheng Zhang","submitted_at":"2023-09-25T14:43:43Z","abstract_excerpt":"The rapid evolution of Multi-modality Large Language Models (MLLMs) has catalyzed a shift in computer vision from specialized models to general-purpose foundation models. Nevertheless, there is still an inadequacy in assessing the abilities of MLLMs on low-level visual perception and understanding. To address this gap, we present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment. a) To evaluate the low-level perception ability, we constru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14181","kind":"arxiv","version":3},"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/2309.14181/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":"2309.14181","created_at":"2026-07-05T07:29:12.639715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14181v3","created_at":"2026-07-05T07:29:12.639715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14181","created_at":"2026-07-05T07:29:12.639715+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTBPJH5GTAMT","created_at":"2026-07-05T07:29:12.639715+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTBPJH5GTAMT335T","created_at":"2026-07-05T07:29:12.639715+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTBPJH5G","created_at":"2026-07-05T07:29:12.639715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24553","citing_title":"IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28241","citing_title":"PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07148","citing_title":"Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19522","citing_title":"iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04257","citing_title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2309.15112","citing_title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16420","citing_title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12793","citing_title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2403.20330","citing_title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10576","citing_title":"SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12175","citing_title":"Redefining Quality Criteria and Distance-Aware Score Modeling for Image Editing Assessment","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07895","citing_title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2408.03326","citing_title":"LLaVA-OneVision: Easy Visual Task Transfer","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21343","citing_title":"Latent Denoising Improves Visual Alignment in Large Multimodal Models","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54","json":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54.json","graph_json":"https://pith.science/api/pith-number/ZTBPJH5GTAMT335TVL3NODON54/graph.json","events_json":"https://pith.science/api/pith-number/ZTBPJH5GTAMT335TVL3NODON54/events.json","paper":"https://pith.science/paper/ZTBPJH5G"},"agent_actions":{"view_html":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54","download_json":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54.json","view_paper":"https://pith.science/paper/ZTBPJH5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14181&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTBPJH5GTAMT335TVL3NODON54/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTBPJH5GTAMT335TVL3NODON54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54/action/storage_attestation","attest_author":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54/action/author_attestation","sign_citation":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54/action/citation_signature","submit_replication":"https://pith.science/pith/ZTBPJH5GTAMT335TVL3NODON54/action/replication_record"}},"created_at":"2026-07-05T07:29:12.639715+00:00","updated_at":"2026-07-05T07:29:12.639715+00:00"}