{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G5DF3FF376TIZN2FXVX3P5UBUJ","short_pith_number":"pith:G5DF3FF3","schema_version":"1.0","canonical_sha256":"37465d94bbffa68cb745bd6fb7f681a27eab71a903662c9fbfb8c0e2c523d93c","source":{"kind":"arxiv","id":"2108.05866","version":1},"attestation_state":"computed","paper":{"title":"Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Wang, Ruyi Zhang, Xubo Yang, Zheyang Li, Zhi Yang, Ziwei Yang","submitted_at":"2021-08-12T17:27:10Z","abstract_excerpt":"One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing. However, the weight-sharing technique worsens the ranking consistency of performance due to the interferences between different candidate networks. To address this issue, we propose a candidates enhancement method and progressive training pipeline to improve the ranking correlation of supernet. Specifically, we carefully redesign the sub-networks in the supernet and map the original supernet to a new one of high capacity. In addition, we"},"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":"2108.05866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-12T17:27:10Z","cross_cats_sorted":[],"title_canon_sha256":"2c5747516e236ef98be316f4e9b34db419a28be28a2e1cf332836ad5e591dfe8","abstract_canon_sha256":"976d49be9f2c014e1209003a0317dd9484e4cf854f537e94e4a95fb16997c1da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:23.218819Z","signature_b64":"mtsQGNjKEM/HhsVYLnqO2s/qkA9hry+Zk3LUC5TgXIqBVcncCFCOXTfqnppNS+S7zjxxj4iP2TUqMxwYk491Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37465d94bbffa68cb745bd6fb7f681a27eab71a903662c9fbfb8c0e2c523d93c","last_reissued_at":"2026-07-05T03:05:23.218406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:23.218406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Wang, Ruyi Zhang, Xubo Yang, Zheyang Li, Zhi Yang, Ziwei Yang","submitted_at":"2021-08-12T17:27:10Z","abstract_excerpt":"One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing. However, the weight-sharing technique worsens the ranking consistency of performance due to the interferences between different candidate networks. To address this issue, we propose a candidates enhancement method and progressive training pipeline to improve the ranking correlation of supernet. Specifically, we carefully redesign the sub-networks in the supernet and map the original supernet to a new one of high capacity. In addition, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05866","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/2108.05866/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":"2108.05866","created_at":"2026-07-05T03:05:23.218464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.05866v1","created_at":"2026-07-05T03:05:23.218464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05866","created_at":"2026-07-05T03:05:23.218464+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5DF3FF376TI","created_at":"2026-07-05T03:05:23.218464+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5DF3FF376TIZN2F","created_at":"2026-07-05T03:05:23.218464+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5DF3FF3","created_at":"2026-07-05T03:05:23.218464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ","json":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ.json","graph_json":"https://pith.science/api/pith-number/G5DF3FF376TIZN2FXVX3P5UBUJ/graph.json","events_json":"https://pith.science/api/pith-number/G5DF3FF376TIZN2FXVX3P5UBUJ/events.json","paper":"https://pith.science/paper/G5DF3FF3"},"agent_actions":{"view_html":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ","download_json":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ.json","view_paper":"https://pith.science/paper/G5DF3FF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.05866&json=true","fetch_graph":"https://pith.science/api/pith-number/G5DF3FF376TIZN2FXVX3P5UBUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/G5DF3FF376TIZN2FXVX3P5UBUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ/action/storage_attestation","attest_author":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ/action/author_attestation","sign_citation":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ/action/citation_signature","submit_replication":"https://pith.science/pith/G5DF3FF376TIZN2FXVX3P5UBUJ/action/replication_record"}},"created_at":"2026-07-05T03:05:23.218464+00:00","updated_at":"2026-07-05T03:05:23.218464+00:00"}