{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:62JOGUXFNUU75Z57WAG4KOJ5VZ","short_pith_number":"pith:62JOGUXF","schema_version":"1.0","canonical_sha256":"f692e352e56d29fee7bfb00dc5393dae4472e9a6a2caedac89799ff28acc5e76","source":{"kind":"arxiv","id":"2408.08601","version":1},"attestation_state":"computed","paper":{"title":"Learning A Low-Level Vision Generalist via Visual Task Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jiantao Zhou, Wenlong Zhang, Xiangyu Chen, Yihao Liu, Yuandong Pu, Yu Qiao","submitted_at":"2024-08-16T08:37:56Z","abstract_excerpt":"Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoration approaches can address multiple degradation-to-clean restoration tasks, while their applicability to tasks with different target domains (e.g., image stylization) is limited. Methods like PromptGIP can handle multiple input-target domains but rely on the Masked Autoencoder (MAE) paradigm. Consequently, they are tied to the ViT architecture, resulting in suboptimal image reconstruction quality. In addition, these me"},"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":"2408.08601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-16T08:37:56Z","cross_cats_sorted":[],"title_canon_sha256":"900c408bf1b4783450e14f6cc73cffc781021e806afb7842ecbd2f63d662264b","abstract_canon_sha256":"b9eff9207c798c96e89a14d686f8301e5a5bfa2407a6d8e125d744103cf1c9e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:06.381837Z","signature_b64":"qUqTwQu/k7WwAkKT9TzLoHpc2XM62cLpUBLPXy7nRmRGqFmgngcbJRs/xuv46SoxKHTL8qGop6dE/q4T+JyyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f692e352e56d29fee7bfb00dc5393dae4472e9a6a2caedac89799ff28acc5e76","last_reissued_at":"2026-07-05T08:56:06.381424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:06.381424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning A Low-Level Vision Generalist via Visual Task Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jiantao Zhou, Wenlong Zhang, Xiangyu Chen, Yihao Liu, Yuandong Pu, Yu Qiao","submitted_at":"2024-08-16T08:37:56Z","abstract_excerpt":"Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoration approaches can address multiple degradation-to-clean restoration tasks, while their applicability to tasks with different target domains (e.g., image stylization) is limited. Methods like PromptGIP can handle multiple input-target domains but rely on the Masked Autoencoder (MAE) paradigm. Consequently, they are tied to the ViT architecture, resulting in suboptimal image reconstruction quality. In addition, these me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08601","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/2408.08601/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":"2408.08601","created_at":"2026-07-05T08:56:06.381481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08601v1","created_at":"2026-07-05T08:56:06.381481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08601","created_at":"2026-07-05T08:56:06.381481+00:00"},{"alias_kind":"pith_short_12","alias_value":"62JOGUXFNUU7","created_at":"2026-07-05T08:56:06.381481+00:00"},{"alias_kind":"pith_short_16","alias_value":"62JOGUXFNUU75Z57","created_at":"2026-07-05T08:56:06.381481+00:00"},{"alias_kind":"pith_short_8","alias_value":"62JOGUXF","created_at":"2026-07-05T08:56:06.381481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16007","citing_title":"Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image Processing","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ","json":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ.json","graph_json":"https://pith.science/api/pith-number/62JOGUXFNUU75Z57WAG4KOJ5VZ/graph.json","events_json":"https://pith.science/api/pith-number/62JOGUXFNUU75Z57WAG4KOJ5VZ/events.json","paper":"https://pith.science/paper/62JOGUXF"},"agent_actions":{"view_html":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ","download_json":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ.json","view_paper":"https://pith.science/paper/62JOGUXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08601&json=true","fetch_graph":"https://pith.science/api/pith-number/62JOGUXFNUU75Z57WAG4KOJ5VZ/graph.json","fetch_events":"https://pith.science/api/pith-number/62JOGUXFNUU75Z57WAG4KOJ5VZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ/action/storage_attestation","attest_author":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ/action/author_attestation","sign_citation":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ/action/citation_signature","submit_replication":"https://pith.science/pith/62JOGUXFNUU75Z57WAG4KOJ5VZ/action/replication_record"}},"created_at":"2026-07-05T08:56:06.381481+00:00","updated_at":"2026-07-05T08:56:06.381481+00:00"}