{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FFQNMUIQG4JK3IPT72OKM7EVJX","short_pith_number":"pith:FFQNMUIQ","schema_version":"1.0","canonical_sha256":"2960d651103712ada1f3fe9ca67c954dd026e677916bb6092684e1d4445d1696","source":{"kind":"arxiv","id":"2105.03939","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chaoyang He, Han Huang, Li Shen, Wei Liu, Weisheng Dong","submitted_at":"2021-05-09T13:30:16Z","abstract_excerpt":"Single Image Super-Resolution (SISR) tasks have achieved significant performance with deep neural networks. However, the large number of parameters in CNN-based met-hods for SISR tasks require heavy computations. Although several efficient SISR models have been recently proposed, most are handcrafted and thus lack flexibility. In this work, we propose a novel differentiable Neural Architecture Search (NAS) approach on both the cell-level and network-level to search for lightweight SISR models. Specifically, the cell-level search space is designed based on an information distillation mechanism,"},"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":"2105.03939","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-05-09T13:30:16Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"52fc593a38ff81c8d6f4e2e9e00a28e8da3fe9bfb4d82036ca38cba2e3209a64","abstract_canon_sha256":"6924d9172903ed95e325557c31c4da0013fa3e0f6cd1ef530195ecd16590d2b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:01.519885Z","signature_b64":"m4Js6GMzM9v22ZSQYJyk4wlCL13+MZLjIhX70Eayay2LvymxDk5Bg77s23iXwvFI7+yYzB5lBmi/uMuN/s47AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2960d651103712ada1f3fe9ca67c954dd026e677916bb6092684e1d4445d1696","last_reissued_at":"2026-07-05T05:26:01.519395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:01.519395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chaoyang He, Han Huang, Li Shen, Wei Liu, Weisheng Dong","submitted_at":"2021-05-09T13:30:16Z","abstract_excerpt":"Single Image Super-Resolution (SISR) tasks have achieved significant performance with deep neural networks. However, the large number of parameters in CNN-based met-hods for SISR tasks require heavy computations. Although several efficient SISR models have been recently proposed, most are handcrafted and thus lack flexibility. In this work, we propose a novel differentiable Neural Architecture Search (NAS) approach on both the cell-level and network-level to search for lightweight SISR models. Specifically, the cell-level search space is designed based on an information distillation mechanism,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03939","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/2105.03939/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":"2105.03939","created_at":"2026-07-05T05:26:01.519455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03939v2","created_at":"2026-07-05T05:26:01.519455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03939","created_at":"2026-07-05T05:26:01.519455+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFQNMUIQG4JK","created_at":"2026-07-05T05:26:01.519455+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFQNMUIQG4JK3IPT","created_at":"2026-07-05T05:26:01.519455+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFQNMUIQ","created_at":"2026-07-05T05:26:01.519455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16306","citing_title":"Regularizing Differentiable Architecture Search with Smooth Activation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX","json":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX.json","graph_json":"https://pith.science/api/pith-number/FFQNMUIQG4JK3IPT72OKM7EVJX/graph.json","events_json":"https://pith.science/api/pith-number/FFQNMUIQG4JK3IPT72OKM7EVJX/events.json","paper":"https://pith.science/paper/FFQNMUIQ"},"agent_actions":{"view_html":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX","download_json":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX.json","view_paper":"https://pith.science/paper/FFQNMUIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03939&json=true","fetch_graph":"https://pith.science/api/pith-number/FFQNMUIQG4JK3IPT72OKM7EVJX/graph.json","fetch_events":"https://pith.science/api/pith-number/FFQNMUIQG4JK3IPT72OKM7EVJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX/action/storage_attestation","attest_author":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX/action/author_attestation","sign_citation":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX/action/citation_signature","submit_replication":"https://pith.science/pith/FFQNMUIQG4JK3IPT72OKM7EVJX/action/replication_record"}},"created_at":"2026-07-05T05:26:01.519455+00:00","updated_at":"2026-07-05T05:26:01.519455+00:00"}