{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CKPFJ2R37UVT2QCZTDTKKG3DVA","short_pith_number":"pith:CKPFJ2R3","schema_version":"1.0","canonical_sha256":"129e54ea3bfd2b3d405998e6a51b63a80cd7057a6426e2f097874b958ea9c40d","source":{"kind":"arxiv","id":"2405.19298","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Baoliang Chen, Guangtao Zhai, Hanwei Zhu, Haoning Wu, Lingyu Zhu, Shiqi Wang, Weisi Lin, Yixuan Li, Yuming Fang, Zicheng Zhang","submitted_at":"2024-05-29T17:26:09Z","abstract_excerpt":"While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored. To address this gap, we introduce Compare2Score-an all-around LMM-based no-reference IQA (NR-IQA) model, which is capable of producing qualitatively comparative responses and effectively translating these discrete comparative levels into a continuous quality score. Specifically, during training, "},"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":"2405.19298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:26:09Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"abff1eec0e2f1f6b48e68c2e66e1ae4de10345d6e2b7bf0d038c5bf419fd6f3a","abstract_canon_sha256":"b6edc8a1fce9d2d0a046116173dbf08b67fb386989b7a2598c44d46e0ef045b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:50.657209Z","signature_b64":"xLw9BuH8yc33W7LvilwkW4QwI5InSeNIdiEzLSuIRL2PRK5Ny4apOZGv98GmVQF/f63ClQRRtdV8eoP2YuKLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"129e54ea3bfd2b3d405998e6a51b63a80cd7057a6426e2f097874b958ea9c40d","last_reissued_at":"2026-07-05T08:24:50.656702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:50.656702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Baoliang Chen, Guangtao Zhai, Hanwei Zhu, Haoning Wu, Lingyu Zhu, Shiqi Wang, Weisi Lin, Yixuan Li, Yuming Fang, Zicheng Zhang","submitted_at":"2024-05-29T17:26:09Z","abstract_excerpt":"While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored. To address this gap, we introduce Compare2Score-an all-around LMM-based no-reference IQA (NR-IQA) model, which is capable of producing qualitatively comparative responses and effectively translating these discrete comparative levels into a continuous quality score. Specifically, during training, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19298","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/2405.19298/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":"2405.19298","created_at":"2026-07-05T08:24:50.656764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19298v1","created_at":"2026-07-05T08:24:50.656764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19298","created_at":"2026-07-05T08:24:50.656764+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKPFJ2R37UVT","created_at":"2026-07-05T08:24:50.656764+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKPFJ2R37UVT2QCZ","created_at":"2026-07-05T08:24:50.656764+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKPFJ2R3","created_at":"2026-07-05T08:24:50.656764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.03631","citing_title":"Generalizable Video Quality Assessment via Weak-to-Strong Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19776","citing_title":"Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19776","citing_title":"Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08664","citing_title":"IPAD-CLIP: Teaching CLIP to Detect Image Local Perceptual Artifacts","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA","json":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA.json","graph_json":"https://pith.science/api/pith-number/CKPFJ2R37UVT2QCZTDTKKG3DVA/graph.json","events_json":"https://pith.science/api/pith-number/CKPFJ2R37UVT2QCZTDTKKG3DVA/events.json","paper":"https://pith.science/paper/CKPFJ2R3"},"agent_actions":{"view_html":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA","download_json":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA.json","view_paper":"https://pith.science/paper/CKPFJ2R3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19298&json=true","fetch_graph":"https://pith.science/api/pith-number/CKPFJ2R37UVT2QCZTDTKKG3DVA/graph.json","fetch_events":"https://pith.science/api/pith-number/CKPFJ2R37UVT2QCZTDTKKG3DVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA/action/storage_attestation","attest_author":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA/action/author_attestation","sign_citation":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA/action/citation_signature","submit_replication":"https://pith.science/pith/CKPFJ2R37UVT2QCZTDTKKG3DVA/action/replication_record"}},"created_at":"2026-07-05T08:24:50.656764+00:00","updated_at":"2026-07-05T08:24:50.656764+00:00"}