{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OD4FY62L6D63QBLRUQBMYZWOPZ","short_pith_number":"pith:OD4FY62L","schema_version":"1.0","canonical_sha256":"70f85c7b4bf0fdb80571a402cc66ce7e406e2bb9d0d14b28e2aea9a5e019940f","source":{"kind":"arxiv","id":"2311.06783","version":1},"attestation_state":"computed","paper":{"title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Annan Wang, Chaofeng Chen, Chunyi Li, Erli Zhang, Geng Xue, Guangtao Zhai, Haoning Wu, Jingwen Hou, Kaixin Xu, Liang Liao, Qiong Yan, Weisi Lin, Wenxiu Sun, Zicheng Zhang","submitted_at":"2023-11-12T09:10:51Z","abstract_excerpt":"Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model. While existing foundation models have shown exciting potentials on low-level visual tasks, their related abilities are still preliminary and need to be improved. In order to enhance these models, we conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision. Each feedback follows a pathway that starts with a detailed descri"},"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":"2311.06783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:10:51Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d84d8f19e92803daa1bf5984fca4d97168685e52161ad86550b23328ccf422e9","abstract_canon_sha256":"a4c01c1b87f2f2d3c69c31e3d17cdf1524044ea1b4a35d4a71a257c175462dad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:03.617288Z","signature_b64":"ftZ6+rOAtapc6LQlDVUFicU+b8V6txX3VskpfI57T44+AmPhzvJ4jd4Zw9mOdfcX75CjCeUaEqr2FkLpFa0wBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70f85c7b4bf0fdb80571a402cc66ce7e406e2bb9d0d14b28e2aea9a5e019940f","last_reissued_at":"2026-07-05T07:12:03.616795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:03.616795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Annan Wang, Chaofeng Chen, Chunyi Li, Erli Zhang, Geng Xue, Guangtao Zhai, Haoning Wu, Jingwen Hou, Kaixin Xu, Liang Liao, Qiong Yan, Weisi Lin, Wenxiu Sun, Zicheng Zhang","submitted_at":"2023-11-12T09:10:51Z","abstract_excerpt":"Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model. While existing foundation models have shown exciting potentials on low-level visual tasks, their related abilities are still preliminary and need to be improved. In order to enhance these models, we conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision. Each feedback follows a pathway that starts with a detailed descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06783","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/2311.06783/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":"2311.06783","created_at":"2026-07-05T07:12:03.616860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06783v1","created_at":"2026-07-05T07:12:03.616860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06783","created_at":"2026-07-05T07:12:03.616860+00:00"},{"alias_kind":"pith_short_12","alias_value":"OD4FY62L6D63","created_at":"2026-07-05T07:12:03.616860+00:00"},{"alias_kind":"pith_short_16","alias_value":"OD4FY62L6D63QBLR","created_at":"2026-07-05T07:12:03.616860+00:00"},{"alias_kind":"pith_short_8","alias_value":"OD4FY62L","created_at":"2026-07-05T07:12:03.616860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21244","citing_title":"SR-Ground: Image Quality Grounding for Super-Resolved Content","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":288,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ","json":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ.json","graph_json":"https://pith.science/api/pith-number/OD4FY62L6D63QBLRUQBMYZWOPZ/graph.json","events_json":"https://pith.science/api/pith-number/OD4FY62L6D63QBLRUQBMYZWOPZ/events.json","paper":"https://pith.science/paper/OD4FY62L"},"agent_actions":{"view_html":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ","download_json":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ.json","view_paper":"https://pith.science/paper/OD4FY62L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06783&json=true","fetch_graph":"https://pith.science/api/pith-number/OD4FY62L6D63QBLRUQBMYZWOPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OD4FY62L6D63QBLRUQBMYZWOPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ/action/storage_attestation","attest_author":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ/action/author_attestation","sign_citation":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ/action/citation_signature","submit_replication":"https://pith.science/pith/OD4FY62L6D63QBLRUQBMYZWOPZ/action/replication_record"}},"created_at":"2026-07-05T07:12:03.616860+00:00","updated_at":"2026-07-05T07:12:03.616860+00:00"}