{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B3LAEL5WHAWHC54RWGNEYHCMCQ","short_pith_number":"pith:B3LAEL5W","schema_version":"1.0","canonical_sha256":"0ed6022fb6382c717791b19a4c1c4c141cace07b2439d2271b94772b53177ddc","source":{"kind":"arxiv","id":"2508.07818","version":1},"attestation_state":"computed","paper":{"title":"Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Hui, Chenyue Song, Feng Jiang, Haiqi Zhu, Shaohui Liu, Wei Zhang, Yachun Mi","submitted_at":"2025-08-11T10:03:00Z","abstract_excerpt":"No-reference image quality assessment (NR-IQA) aims to simulate the process of perceiving image quality aligned with subjective human perception. However, existing NR-IQA methods either focus on global representations that leads to limited insights into the semantically salient regions or employ a uniform weighting for region features that weakens the sensitivity to local quality variations. In this paper, we propose a fine-grained image quality assessment model, named RSFIQA, which integrates region-level distortion information to perceive multi-dimensional quality discrepancies. To enhance r"},"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":"2508.07818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T10:03:00Z","cross_cats_sorted":[],"title_canon_sha256":"d95dbc2ee4b2237b43d8235b379a759c7094da34affcc26feca5bc97274f2937","abstract_canon_sha256":"e9beb52f828e324893033551557a265b412126064cc908fd1af9d57060f59d9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:52.835883Z","signature_b64":"Fn9QNwkVwYnIak9fmw9QqyLABSul6ozcKsUZpCQe/+UU7tT248yd6kV+tF8laqUR/WL1f92/02blLsAv0IYCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed6022fb6382c717791b19a4c1c4c141cace07b2439d2271b94772b53177ddc","last_reissued_at":"2026-07-05T11:51:52.835455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:52.835455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Hui, Chenyue Song, Feng Jiang, Haiqi Zhu, Shaohui Liu, Wei Zhang, Yachun Mi","submitted_at":"2025-08-11T10:03:00Z","abstract_excerpt":"No-reference image quality assessment (NR-IQA) aims to simulate the process of perceiving image quality aligned with subjective human perception. However, existing NR-IQA methods either focus on global representations that leads to limited insights into the semantically salient regions or employ a uniform weighting for region features that weakens the sensitivity to local quality variations. In this paper, we propose a fine-grained image quality assessment model, named RSFIQA, which integrates region-level distortion information to perceive multi-dimensional quality discrepancies. To enhance r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07818","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/2508.07818/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":"2508.07818","created_at":"2026-07-05T11:51:52.835510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07818v1","created_at":"2026-07-05T11:51:52.835510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07818","created_at":"2026-07-05T11:51:52.835510+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3LAEL5WHAWH","created_at":"2026-07-05T11:51:52.835510+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3LAEL5WHAWHC54R","created_at":"2026-07-05T11:51:52.835510+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3LAEL5W","created_at":"2026-07-05T11:51:52.835510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.22647","citing_title":"FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ","json":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ.json","graph_json":"https://pith.science/api/pith-number/B3LAEL5WHAWHC54RWGNEYHCMCQ/graph.json","events_json":"https://pith.science/api/pith-number/B3LAEL5WHAWHC54RWGNEYHCMCQ/events.json","paper":"https://pith.science/paper/B3LAEL5W"},"agent_actions":{"view_html":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ","download_json":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ.json","view_paper":"https://pith.science/paper/B3LAEL5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07818&json=true","fetch_graph":"https://pith.science/api/pith-number/B3LAEL5WHAWHC54RWGNEYHCMCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/B3LAEL5WHAWHC54RWGNEYHCMCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ/action/storage_attestation","attest_author":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ/action/author_attestation","sign_citation":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ/action/citation_signature","submit_replication":"https://pith.science/pith/B3LAEL5WHAWHC54RWGNEYHCMCQ/action/replication_record"}},"created_at":"2026-07-05T11:51:52.835510+00:00","updated_at":"2026-07-05T11:51:52.835510+00:00"}