{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LXKPD2BW4CRZZ23BS6QD2VVDBJ","short_pith_number":"pith:LXKPD2BW","schema_version":"1.0","canonical_sha256":"5dd4f1e836e0a39ceb6197a03d56a30a7054e0c789f39139e6acc1f6017b3c3c","source":{"kind":"arxiv","id":"2402.07116","version":2},"attestation_state":"computed","paper":{"title":"Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erli Zhang, Guangtao Zhai, Haoning Wu, Weisi Lin, Zicheng Zhang","submitted_at":"2024-02-11T06:44:11Z","abstract_excerpt":"The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and understanding remains a yet-to-explore domain. To this end, we design benchmark settings to emulate human language responses related to low-level vision: the low-level visual perception (A1) via visual question answering related to low-level attributes (e.g. clarity, lighting); and the low-level visual description (A2), on evaluating MLLMs for low-level text description"},"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":"2402.07116","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T06:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"b57ff06f6136150a5bba4464f529878e4436a893662a252f45fc4a04f1a2ded5","abstract_canon_sha256":"e77d61b745e53dee0588c2b87bbc56e48ed5bd689ea295ee62259e67a480f735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:07.084322Z","signature_b64":"89d8t6eh+C9cVP62p1UOdCMQMH7eObE0KppW8zlBHQeJdgvfurYvd0CNMlH1JLnEMgKRr37qghfFvZDMlZdVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dd4f1e836e0a39ceb6197a03d56a30a7054e0c789f39139e6acc1f6017b3c3c","last_reissued_at":"2026-07-05T08:54:07.083925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:07.083925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erli Zhang, Guangtao Zhai, Haoning Wu, Weisi Lin, Zicheng Zhang","submitted_at":"2024-02-11T06:44:11Z","abstract_excerpt":"The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and understanding remains a yet-to-explore domain. To this end, we design benchmark settings to emulate human language responses related to low-level vision: the low-level visual perception (A1) via visual question answering related to low-level attributes (e.g. clarity, lighting); and the low-level visual description (A2), on evaluating MLLMs for low-level text description"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07116","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/2402.07116/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":"2402.07116","created_at":"2026-07-05T08:54:07.083980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07116v2","created_at":"2026-07-05T08:54:07.083980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07116","created_at":"2026-07-05T08:54:07.083980+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXKPD2BW4CRZ","created_at":"2026-07-05T08:54:07.083980+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXKPD2BW4CRZZ23B","created_at":"2026-07-05T08:54:07.083980+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXKPD2BW","created_at":"2026-07-05T08:54:07.083980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19966","citing_title":"DistortBench: Benchmarking Vision Language Models on Image Distortion Identification","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ","json":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ.json","graph_json":"https://pith.science/api/pith-number/LXKPD2BW4CRZZ23BS6QD2VVDBJ/graph.json","events_json":"https://pith.science/api/pith-number/LXKPD2BW4CRZZ23BS6QD2VVDBJ/events.json","paper":"https://pith.science/paper/LXKPD2BW"},"agent_actions":{"view_html":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ","download_json":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ.json","view_paper":"https://pith.science/paper/LXKPD2BW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07116&json=true","fetch_graph":"https://pith.science/api/pith-number/LXKPD2BW4CRZZ23BS6QD2VVDBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LXKPD2BW4CRZZ23BS6QD2VVDBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ/action/storage_attestation","attest_author":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ/action/author_attestation","sign_citation":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ/action/citation_signature","submit_replication":"https://pith.science/pith/LXKPD2BW4CRZZ23BS6QD2VVDBJ/action/replication_record"}},"created_at":"2026-07-05T08:54:07.083980+00:00","updated_at":"2026-07-05T08:54:07.083980+00:00"}