{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSTQDZBUMOBXQS3JL44BFMBH75","short_pith_number":"pith:ZSTQDZBU","schema_version":"1.0","canonical_sha256":"cca701e4346383784b695f3812b027ff7704adf24d23ec948cce76f9e8898a6d","source":{"kind":"arxiv","id":"2504.15159","version":1},"attestation_state":"computed","paper":{"title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congchao Zhu, Junyuan Deng, Song Wang, Xinyi Wu, Yongxing Yang, Zhenyao Wu","submitted_at":"2025-04-21T15:05:22Z","abstract_excerpt":"Recently, pre-trained text-to-image (T2I) models have been extensively adopted for real-world image restoration because of their powerful generative prior. However, controlling these large models for image restoration usually requires a large number of high-quality images and immense computational resources for training, which is costly and not privacy-friendly. In this paper, we find that the well-trained large T2I model (i.e., Flux) is able to produce a variety of high-quality images aligned with real-world distributions, offering an unlimited supply of training samples to mitigate the above"},"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":"2504.15159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T15:05:22Z","cross_cats_sorted":[],"title_canon_sha256":"d13a163b03042ec58b7e3183096a8db06d2e9c5e0f5247304414b5ace592bad1","abstract_canon_sha256":"4251d0983c68613df9b08d523ff3de47222e3a061f8cf4e6b5c2f08365a9abf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:57.084791Z","signature_b64":"0cfyX9KfbVpHT2JiG+AvxLorwY8Gh9tTT6GyZDI/5kKO+nD5sTKn0bxKdHCpKBo2ruyYJeA836aC8p9KiHSpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cca701e4346383784b695f3812b027ff7704adf24d23ec948cce76f9e8898a6d","last_reissued_at":"2026-07-05T10:51:57.084253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:57.084253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congchao Zhu, Junyuan Deng, Song Wang, Xinyi Wu, Yongxing Yang, Zhenyao Wu","submitted_at":"2025-04-21T15:05:22Z","abstract_excerpt":"Recently, pre-trained text-to-image (T2I) models have been extensively adopted for real-world image restoration because of their powerful generative prior. However, controlling these large models for image restoration usually requires a large number of high-quality images and immense computational resources for training, which is costly and not privacy-friendly. In this paper, we find that the well-trained large T2I model (i.e., Flux) is able to produce a variety of high-quality images aligned with real-world distributions, offering an unlimited supply of training samples to mitigate the above"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15159","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/2504.15159/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":"2504.15159","created_at":"2026-07-05T10:51:57.084312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15159v1","created_at":"2026-07-05T10:51:57.084312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15159","created_at":"2026-07-05T10:51:57.084312+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSTQDZBUMOBX","created_at":"2026-07-05T10:51:57.084312+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSTQDZBUMOBXQS3J","created_at":"2026-07-05T10:51:57.084312+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSTQDZBU","created_at":"2026-07-05T10:51:57.084312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01964","citing_title":"2D Gaussian Splatting with Semantic Alignment for Image Inpainting","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75","json":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75.json","graph_json":"https://pith.science/api/pith-number/ZSTQDZBUMOBXQS3JL44BFMBH75/graph.json","events_json":"https://pith.science/api/pith-number/ZSTQDZBUMOBXQS3JL44BFMBH75/events.json","paper":"https://pith.science/paper/ZSTQDZBU"},"agent_actions":{"view_html":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75","download_json":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75.json","view_paper":"https://pith.science/paper/ZSTQDZBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15159&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSTQDZBUMOBXQS3JL44BFMBH75/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSTQDZBUMOBXQS3JL44BFMBH75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75/action/storage_attestation","attest_author":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75/action/author_attestation","sign_citation":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75/action/citation_signature","submit_replication":"https://pith.science/pith/ZSTQDZBUMOBXQS3JL44BFMBH75/action/replication_record"}},"created_at":"2026-07-05T10:51:57.084312+00:00","updated_at":"2026-07-05T10:51:57.084312+00:00"}