{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FPJMYMUF2M4HZYN4ONFBVB7DCV","short_pith_number":"pith:FPJMYMUF","schema_version":"1.0","canonical_sha256":"2bd2cc3285d3387ce1bc734a1a87e3156bcdea2b056b7c4dcb4461cf469e2250","source":{"kind":"arxiv","id":"2504.10967","version":2},"attestation_state":"computed","paper":{"title":"An Efficient and Mixed Heterogeneous Model for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Kaihang Zheng, Liujuan Cao, Rongrong Ji, Weijian Ruan, Xiaoshuai Sun, Yuan Meng, Yubin Gu","submitted_at":"2025-04-15T08:19:12Z","abstract_excerpt":"Image restoration~(IR), as a fundamental multimedia data processing task, has a significant impact on downstream visual applications. In recent years, researchers have focused on developing general-purpose IR models capable of handling diverse degradation types, thereby reducing the cost and complexity of model development. Current mainstream approaches are based on three architectural paradigms: CNNs, Transformers, and Mambas. CNNs excel in efficient inference, whereas Transformers and Mamba excel at capturing long-range dependencies and modeling global contexts. While each architecture has d"},"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":"2504.10967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-15T08:19:12Z","cross_cats_sorted":[],"title_canon_sha256":"48ea2d665f7d5b51ddb44cf118637a223fdf79bfa5224474e4d49fd42edc1f2b","abstract_canon_sha256":"94a4de58a3ed288242c548e4f20f6913af310b32cf5409acbbf2af53613b9da9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:37.157700Z","signature_b64":"WpmKWjRZ0r8bfYMRjQWzAxKsSw679f2Q/hQfewCa87Qgm2jOb74/TpFZ+iFcglB+gKCeTLRqHOB64mQkXTCZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bd2cc3285d3387ce1bc734a1a87e3156bcdea2b056b7c4dcb4461cf469e2250","last_reissued_at":"2026-07-05T10:51:37.157195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:37.157195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient and Mixed Heterogeneous Model for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Kaihang Zheng, Liujuan Cao, Rongrong Ji, Weijian Ruan, Xiaoshuai Sun, Yuan Meng, Yubin Gu","submitted_at":"2025-04-15T08:19:12Z","abstract_excerpt":"Image restoration~(IR), as a fundamental multimedia data processing task, has a significant impact on downstream visual applications. In recent years, researchers have focused on developing general-purpose IR models capable of handling diverse degradation types, thereby reducing the cost and complexity of model development. Current mainstream approaches are based on three architectural paradigms: CNNs, Transformers, and Mambas. CNNs excel in efficient inference, whereas Transformers and Mamba excel at capturing long-range dependencies and modeling global contexts. While each architecture has d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10967","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/2504.10967/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":"2504.10967","created_at":"2026-07-05T10:51:37.157254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10967v2","created_at":"2026-07-05T10:51:37.157254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10967","created_at":"2026-07-05T10:51:37.157254+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPJMYMUF2M4H","created_at":"2026-07-05T10:51:37.157254+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPJMYMUF2M4HZYN4","created_at":"2026-07-05T10:51:37.157254+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPJMYMUF","created_at":"2026-07-05T10:51:37.157254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31048","citing_title":"Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05418","citing_title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV","json":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV.json","graph_json":"https://pith.science/api/pith-number/FPJMYMUF2M4HZYN4ONFBVB7DCV/graph.json","events_json":"https://pith.science/api/pith-number/FPJMYMUF2M4HZYN4ONFBVB7DCV/events.json","paper":"https://pith.science/paper/FPJMYMUF"},"agent_actions":{"view_html":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV","download_json":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV.json","view_paper":"https://pith.science/paper/FPJMYMUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10967&json=true","fetch_graph":"https://pith.science/api/pith-number/FPJMYMUF2M4HZYN4ONFBVB7DCV/graph.json","fetch_events":"https://pith.science/api/pith-number/FPJMYMUF2M4HZYN4ONFBVB7DCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV/action/storage_attestation","attest_author":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV/action/author_attestation","sign_citation":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV/action/citation_signature","submit_replication":"https://pith.science/pith/FPJMYMUF2M4HZYN4ONFBVB7DCV/action/replication_record"}},"created_at":"2026-07-05T10:51:37.157254+00:00","updated_at":"2026-07-05T10:51:37.157254+00:00"}