{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6GSA2ACEKLECBFNCJ2PNX2NMWW","short_pith_number":"pith:6GSA2ACE","schema_version":"1.0","canonical_sha256":"f1a40d004452c82095a24e9edbe9acb581e5b24a34bb16196be0506b986fd48b","source":{"kind":"arxiv","id":"2404.14949","version":2},"attestation_state":"computed","paper":{"title":"Multi-Modal Prompt Learning on Blind Image Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enwei Zhang, Ke Li, Liujuan Cao, Rongrong Ji, Runze Hu, Shengchuan Zhang, Timin Gao, Wensheng Pan, Xiawu Zheng, Yan Zhang, Yunhang Shen, Yutao Liu, Yuting Gao","submitted_at":"2024-04-23T11:45:32Z","abstract_excerpt":"Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Currently, leveraging semantic information to enhance IQA is a crucial research direction. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. However, the generalist nature of these pre-trained Vision-Language (VL) models often renders them suboptimal for IQA-specific tasks. Recent approaches have attempted to address this mis"},"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":"2404.14949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T11:45:32Z","cross_cats_sorted":[],"title_canon_sha256":"04665b584a016463928ef478fe6b709f141133649526b494e1f6d1557c57a6dc","abstract_canon_sha256":"e39130ba4d611d896ca381b61b92044cdeeb68b5ea515e7d7a149bb9ca85b4c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:29.392616Z","signature_b64":"0Bx6s2hxiEaSmF5FETq+L42W51L3FEHn8w93i6tk24pSeXOyTyk7RJ9epc2FtDwPi/pKKWHXbt3ebdObEaI1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1a40d004452c82095a24e9edbe9acb581e5b24a34bb16196be0506b986fd48b","last_reissued_at":"2026-07-05T08:20:29.392104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:29.392104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Prompt Learning on Blind Image Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enwei Zhang, Ke Li, Liujuan Cao, Rongrong Ji, Runze Hu, Shengchuan Zhang, Timin Gao, Wensheng Pan, Xiawu Zheng, Yan Zhang, Yunhang Shen, Yutao Liu, Yuting Gao","submitted_at":"2024-04-23T11:45:32Z","abstract_excerpt":"Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Currently, leveraging semantic information to enhance IQA is a crucial research direction. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. However, the generalist nature of these pre-trained Vision-Language (VL) models often renders them suboptimal for IQA-specific tasks. Recent approaches have attempted to address this mis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14949","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/2404.14949/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":"2404.14949","created_at":"2026-07-05T08:20:29.392162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14949v2","created_at":"2026-07-05T08:20:29.392162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14949","created_at":"2026-07-05T08:20:29.392162+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GSA2ACEKLEC","created_at":"2026-07-05T08:20:29.392162+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GSA2ACEKLECBFNC","created_at":"2026-07-05T08:20:29.392162+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GSA2ACE","created_at":"2026-07-05T08:20:29.392162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03494","citing_title":"Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW","json":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW.json","graph_json":"https://pith.science/api/pith-number/6GSA2ACEKLECBFNCJ2PNX2NMWW/graph.json","events_json":"https://pith.science/api/pith-number/6GSA2ACEKLECBFNCJ2PNX2NMWW/events.json","paper":"https://pith.science/paper/6GSA2ACE"},"agent_actions":{"view_html":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW","download_json":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW.json","view_paper":"https://pith.science/paper/6GSA2ACE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14949&json=true","fetch_graph":"https://pith.science/api/pith-number/6GSA2ACEKLECBFNCJ2PNX2NMWW/graph.json","fetch_events":"https://pith.science/api/pith-number/6GSA2ACEKLECBFNCJ2PNX2NMWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW/action/storage_attestation","attest_author":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW/action/author_attestation","sign_citation":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW/action/citation_signature","submit_replication":"https://pith.science/pith/6GSA2ACEKLECBFNCJ2PNX2NMWW/action/replication_record"}},"created_at":"2026-07-05T08:20:29.392162+00:00","updated_at":"2026-07-05T08:20:29.392162+00:00"}