{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCYIA55ZARUYAIPLIKEXND4N43","short_pith_number":"pith:WCYIA55Z","schema_version":"1.0","canonical_sha256":"b0b08077b904698021eb4289768f8de6e1dec6ebf20277a7d71179d6f557fb90","source":{"kind":"arxiv","id":"2412.03017","version":2},"attestation_state":"computed","paper":{"title":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Lingchen Sun, Qiaosi Yi, Rongyuan Wu, Shuaizheng Liu, Zhiyuan Ma","submitted_at":"2024-12-04T04:07:49Z","abstract_excerpt":"Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance pixel-wise fidelity and perceptual quality. Meanwhile, users have varying preferences on SR results, thus it is demanded to develop an adjustable SR model that can be tailored to different fidelity-perception preferences during inference without re-training. We present Pixel-level and Semantic-level Adjustable SR (PiSA-SR), which learns two LoRA modules upon the "},"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":"2412.03017","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T04:07:49Z","cross_cats_sorted":[],"title_canon_sha256":"68fbb4f35777d4de966aa1e977f93bbce9ca2090d8fede29b221314031611ca9","abstract_canon_sha256":"28df4994f77a22ae0299acd0dceba66386a366fc6d6add82d0af989f580b25a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:41.561097Z","signature_b64":"xaS/PeVENSoj2i1oDfal+hgYQ2AwcW2flFaap46SquJnKfJAxEAZdG4feA1Q5+xwtM8MiRrurO2EyzKzF/5kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0b08077b904698021eb4289768f8de6e1dec6ebf20277a7d71179d6f557fb90","last_reissued_at":"2026-07-05T10:43:41.560643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:41.560643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Lingchen Sun, Qiaosi Yi, Rongyuan Wu, Shuaizheng Liu, Zhiyuan Ma","submitted_at":"2024-12-04T04:07:49Z","abstract_excerpt":"Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance pixel-wise fidelity and perceptual quality. Meanwhile, users have varying preferences on SR results, thus it is demanded to develop an adjustable SR model that can be tailored to different fidelity-perception preferences during inference without re-training. We present Pixel-level and Semantic-level Adjustable SR (PiSA-SR), which learns two LoRA modules upon the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03017","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/2412.03017/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":"2412.03017","created_at":"2026-07-05T10:43:41.560701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03017v2","created_at":"2026-07-05T10:43:41.560701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03017","created_at":"2026-07-05T10:43:41.560701+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCYIA55ZARUY","created_at":"2026-07-05T10:43:41.560701+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCYIA55ZARUYAIPL","created_at":"2026-07-05T10:43:41.560701+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCYIA55Z","created_at":"2026-07-05T10:43:41.560701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.16796","citing_title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03225","citing_title":"VOSR: A Vision-Only Generative Model for Image Super-Resolution","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43","json":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43.json","graph_json":"https://pith.science/api/pith-number/WCYIA55ZARUYAIPLIKEXND4N43/graph.json","events_json":"https://pith.science/api/pith-number/WCYIA55ZARUYAIPLIKEXND4N43/events.json","paper":"https://pith.science/paper/WCYIA55Z"},"agent_actions":{"view_html":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43","download_json":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43.json","view_paper":"https://pith.science/paper/WCYIA55Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03017&json=true","fetch_graph":"https://pith.science/api/pith-number/WCYIA55ZARUYAIPLIKEXND4N43/graph.json","fetch_events":"https://pith.science/api/pith-number/WCYIA55ZARUYAIPLIKEXND4N43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43/action/storage_attestation","attest_author":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43/action/author_attestation","sign_citation":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43/action/citation_signature","submit_replication":"https://pith.science/pith/WCYIA55ZARUYAIPLIKEXND4N43/action/replication_record"}},"created_at":"2026-07-05T10:43:41.560701+00:00","updated_at":"2026-07-05T10:43:41.560701+00:00"}