{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PBADDFSBYQZT5FGHFMTHPG4KSJ","short_pith_number":"pith:PBADDFSB","schema_version":"1.0","canonical_sha256":"7840319641c4333e94c72b26779b8a9263aba4b8aed8432d203b1260b831cb9f","source":{"kind":"arxiv","id":"2301.12332","version":1},"attestation_state":"computed","paper":{"title":"Towards Vision Transformer Unrolling Fixed-Point Algorithm: a Case Study on Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ke Yang, Peng Qiao, Sidun Liu, Tao Sun, Yong Dou","submitted_at":"2023-01-29T02:59:14Z","abstract_excerpt":"The great success of Deep Neural Networks (DNNs) has inspired the algorithmic development of DNN-based Fixed-Point (DNN-FP) for computer vision tasks. DNN-FP methods, trained by Back-Propagation Through Time or computing the inaccurate inversion of the Jacobian, suffer from inferior representation ability. Motivated by the representation power of the Transformer, we propose a framework to unroll the FP and approximate each unrolled process via Transformer blocks, called FPformer. To reduce the high consumption of memory and computation, we come up with FPRformer by sharing parameters between t"},"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":"2301.12332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-29T02:59:14Z","cross_cats_sorted":[],"title_canon_sha256":"e185d502e29406c7435fec5013f0801cf3b009cb03db8cb19f830582bdc3245c","abstract_canon_sha256":"49edf7b39ffd9c4ed668110c43266e4a11c6ac94c4e24a17017e6ed90a90b4e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:38.139297Z","signature_b64":"5QpgdA1OpHETYu7pN7ffis3QBE1M/kHsaNINRI0/LafHY1jlA6w6gGH1xVP7hvOc1umIbf9n52a4IqQATcU8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7840319641c4333e94c72b26779b8a9263aba4b8aed8432d203b1260b831cb9f","last_reissued_at":"2026-07-05T05:36:38.138757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:38.138757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Vision Transformer Unrolling Fixed-Point Algorithm: a Case Study on Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ke Yang, Peng Qiao, Sidun Liu, Tao Sun, Yong Dou","submitted_at":"2023-01-29T02:59:14Z","abstract_excerpt":"The great success of Deep Neural Networks (DNNs) has inspired the algorithmic development of DNN-based Fixed-Point (DNN-FP) for computer vision tasks. DNN-FP methods, trained by Back-Propagation Through Time or computing the inaccurate inversion of the Jacobian, suffer from inferior representation ability. Motivated by the representation power of the Transformer, we propose a framework to unroll the FP and approximate each unrolled process via Transformer blocks, called FPformer. To reduce the high consumption of memory and computation, we come up with FPRformer by sharing parameters between t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12332","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/2301.12332/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":"2301.12332","created_at":"2026-07-05T05:36:38.138809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12332v1","created_at":"2026-07-05T05:36:38.138809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12332","created_at":"2026-07-05T05:36:38.138809+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBADDFSBYQZT","created_at":"2026-07-05T05:36:38.138809+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBADDFSBYQZT5FGH","created_at":"2026-07-05T05:36:38.138809+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBADDFSB","created_at":"2026-07-05T05:36:38.138809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13569","citing_title":"Change of Thought: Adaptive Test-Time Computation","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ","json":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ.json","graph_json":"https://pith.science/api/pith-number/PBADDFSBYQZT5FGHFMTHPG4KSJ/graph.json","events_json":"https://pith.science/api/pith-number/PBADDFSBYQZT5FGHFMTHPG4KSJ/events.json","paper":"https://pith.science/paper/PBADDFSB"},"agent_actions":{"view_html":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ","download_json":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ.json","view_paper":"https://pith.science/paper/PBADDFSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12332&json=true","fetch_graph":"https://pith.science/api/pith-number/PBADDFSBYQZT5FGHFMTHPG4KSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PBADDFSBYQZT5FGHFMTHPG4KSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ/action/storage_attestation","attest_author":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ/action/author_attestation","sign_citation":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ/action/citation_signature","submit_replication":"https://pith.science/pith/PBADDFSBYQZT5FGHFMTHPG4KSJ/action/replication_record"}},"created_at":"2026-07-05T05:36:38.138809+00:00","updated_at":"2026-07-05T05:36:38.138809+00:00"}