{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TH3BWRWMEMOAP4BBMBBQTKAM7P","short_pith_number":"pith:TH3BWRWM","schema_version":"1.0","canonical_sha256":"99f61b46cc231c07f021604309a80cfbde1f32f29a80486d78c4bb912579bf8d","source":{"kind":"arxiv","id":"2204.04676","version":4},"attestation_state":"computed","paper":{"title":"Simple Baselines for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Liangyu Chen, Xiangyu Zhang, Xiaojie Chu","submitted_at":"2022-04-10T12:48:38Z","abstract_excerpt":"Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods. In this paper, we propose a simple baseline that exceeds the SOTA methods and is computationally efficient. To further simplify the baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed. Thus, we derive a Nonlinear Activation Free Network, "},"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":"2204.04676","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-10T12:48:38Z","cross_cats_sorted":[],"title_canon_sha256":"4ab197d5959f8a2ef41ab1aa7a7417f5fcc21e83514e4bbec28fbf5257647a5b","abstract_canon_sha256":"5b6f2e4b680bd964d8a155e1425ec055d0ac617c118eb1d34935c6a4b55a75f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:19.222476Z","signature_b64":"F3TannATcCAaWUeUpCDm1IYL0irza8TsN7JJJjCCdbT3fOA5lutVBKMgZY8rgiNeAOZBOMhqEfkjJG5C5isZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99f61b46cc231c07f021604309a80cfbde1f32f29a80486d78c4bb912579bf8d","last_reissued_at":"2026-07-05T04:45:19.221981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:19.221981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Baselines for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Liangyu Chen, Xiangyu Zhang, Xiaojie Chu","submitted_at":"2022-04-10T12:48:38Z","abstract_excerpt":"Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods. In this paper, we propose a simple baseline that exceeds the SOTA methods and is computationally efficient. To further simplify the baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed. Thus, we derive a Nonlinear Activation Free Network, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04676","kind":"arxiv","version":4},"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/2204.04676/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":"2204.04676","created_at":"2026-07-05T04:45:19.222037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04676v4","created_at":"2026-07-05T04:45:19.222037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04676","created_at":"2026-07-05T04:45:19.222037+00:00"},{"alias_kind":"pith_short_12","alias_value":"TH3BWRWMEMOA","created_at":"2026-07-05T04:45:19.222037+00:00"},{"alias_kind":"pith_short_16","alias_value":"TH3BWRWMEMOAP4BB","created_at":"2026-07-05T04:45:19.222037+00:00"},{"alias_kind":"pith_short_8","alias_value":"TH3BWRWM","created_at":"2026-07-05T04:45:19.222037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02785","citing_title":"CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10081","citing_title":"MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06945","citing_title":"NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P","json":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P.json","graph_json":"https://pith.science/api/pith-number/TH3BWRWMEMOAP4BBMBBQTKAM7P/graph.json","events_json":"https://pith.science/api/pith-number/TH3BWRWMEMOAP4BBMBBQTKAM7P/events.json","paper":"https://pith.science/paper/TH3BWRWM"},"agent_actions":{"view_html":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P","download_json":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P.json","view_paper":"https://pith.science/paper/TH3BWRWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04676&json=true","fetch_graph":"https://pith.science/api/pith-number/TH3BWRWMEMOAP4BBMBBQTKAM7P/graph.json","fetch_events":"https://pith.science/api/pith-number/TH3BWRWMEMOAP4BBMBBQTKAM7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P/action/storage_attestation","attest_author":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P/action/author_attestation","sign_citation":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P/action/citation_signature","submit_replication":"https://pith.science/pith/TH3BWRWMEMOAP4BBMBBQTKAM7P/action/replication_record"}},"created_at":"2026-07-05T04:45:19.222037+00:00","updated_at":"2026-07-05T04:45:19.222037+00:00"}