{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JAA2SAKS65AM74GCMMDOAYYEML","short_pith_number":"pith:JAA2SAKS","schema_version":"1.0","canonical_sha256":"4801a90152f740cff0c26306e0630462d56a0ae132e47f1b14647a7a480ce535","source":{"kind":"arxiv","id":"2201.11679","version":1},"attestation_state":"computed","paper":{"title":"DropNAS: Grouped Operation Dropout for Differentiable Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guilin Li, Ruiming Tang, Weijun Hong, Weinan Zhang, Yong Yu, Yunhe Wang, Zhenguo Li","submitted_at":"2022-01-27T17:28:23Z","abstract_excerpt":"Neural architecture search (NAS) has shown encouraging results in automating the architecture design. Recently, DARTS relaxes the search process with a differentiable formulation that leverages weight-sharing and SGD where all candidate operations are trained simultaneously. Our empirical results show that such procedure results in the co-adaption problem and Matthew Effect: operations with fewer parameters would be trained maturely earlier. This causes two problems: firstly, the operations with more parameters may never have the chance to express the desired function since those with less hav"},"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":"2201.11679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T17:28:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e1cf7aaf31d550a1c9837a3a65ddb446568a2e62cda2749f28d35bddf4a7ea49","abstract_canon_sha256":"a385572a93d9f48d53c35d855e7c6f61c267cd626742251c7167bd53f111d59d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:04.385858Z","signature_b64":"dWdRcOMbO11QcvhyvdpZqXcq5b3/52ndku/UQ+yvGHNhcmJ4PK2fBdU5MXaB5d5vDFRJu9VX/qEBxI/0sw5VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4801a90152f740cff0c26306e0630462d56a0ae132e47f1b14647a7a480ce535","last_reissued_at":"2026-07-05T03:52:04.385480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:04.385480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropNAS: Grouped Operation Dropout for Differentiable Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guilin Li, Ruiming Tang, Weijun Hong, Weinan Zhang, Yong Yu, Yunhe Wang, Zhenguo Li","submitted_at":"2022-01-27T17:28:23Z","abstract_excerpt":"Neural architecture search (NAS) has shown encouraging results in automating the architecture design. Recently, DARTS relaxes the search process with a differentiable formulation that leverages weight-sharing and SGD where all candidate operations are trained simultaneously. Our empirical results show that such procedure results in the co-adaption problem and Matthew Effect: operations with fewer parameters would be trained maturely earlier. This causes two problems: firstly, the operations with more parameters may never have the chance to express the desired function since those with less hav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11679","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/2201.11679/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":"2201.11679","created_at":"2026-07-05T03:52:04.385542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11679v1","created_at":"2026-07-05T03:52:04.385542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11679","created_at":"2026-07-05T03:52:04.385542+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAA2SAKS65AM","created_at":"2026-07-05T03:52:04.385542+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAA2SAKS65AM74GC","created_at":"2026-07-05T03:52:04.385542+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAA2SAKS","created_at":"2026-07-05T03:52:04.385542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.03420","citing_title":"Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML","json":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML.json","graph_json":"https://pith.science/api/pith-number/JAA2SAKS65AM74GCMMDOAYYEML/graph.json","events_json":"https://pith.science/api/pith-number/JAA2SAKS65AM74GCMMDOAYYEML/events.json","paper":"https://pith.science/paper/JAA2SAKS"},"agent_actions":{"view_html":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML","download_json":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML.json","view_paper":"https://pith.science/paper/JAA2SAKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11679&json=true","fetch_graph":"https://pith.science/api/pith-number/JAA2SAKS65AM74GCMMDOAYYEML/graph.json","fetch_events":"https://pith.science/api/pith-number/JAA2SAKS65AM74GCMMDOAYYEML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML/action/storage_attestation","attest_author":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML/action/author_attestation","sign_citation":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML/action/citation_signature","submit_replication":"https://pith.science/pith/JAA2SAKS65AM74GCMMDOAYYEML/action/replication_record"}},"created_at":"2026-07-05T03:52:04.385542+00:00","updated_at":"2026-07-05T03:52:04.385542+00:00"}