{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EBO72R5MNCN4UAT5CYYF7P5FLA","short_pith_number":"pith:EBO72R5M","schema_version":"1.0","canonical_sha256":"205dfd47ac689bca027d16305fbfa5583758d8d69ce9b01a0924b11abe374b64","source":{"kind":"arxiv","id":"2302.00932","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS \"Cold-Start\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Chen Chen, Enshu Liu, Jiajin Zhang, Junbo Zhao, Qingmin Liao, Tianchen Zhao, Xuefei Ning, Yu Wang, Zixuan Zhou","submitted_at":"2023-02-02T08:22:35Z","abstract_excerpt":"Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of architecture-performance data is required to get a working predictor. In this paper, we focus on exploiting information in cheaper-to-obtain performance estimations (i.e., low-fidelity information) to mitigate the large data requirements of predictor training. Despite the intuitiveness of this idea, we observe that using inappropriate low-fidelity information even dam"},"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":"2302.00932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T08:22:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1da54b690ae5cc40553be57e0b4fd4d273ecc777e97ddccb0256e3e5c8ffea3","abstract_canon_sha256":"8d2ad03c423c591afb413e43bab23e657ffcd0fc8cd6facb8736eff6669b4dc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:14.078757Z","signature_b64":"cM8YatgXbddDn1lxmf/qmjiktSTOxohV/dUsa5WJJzMmyG70KUZPpL7ymDjTigp4+upzCW0nDyX60UY5m2A/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"205dfd47ac689bca027d16305fbfa5583758d8d69ce9b01a0924b11abe374b64","last_reissued_at":"2026-07-05T05:38:14.078360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:14.078360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS \"Cold-Start\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Chen Chen, Enshu Liu, Jiajin Zhang, Junbo Zhao, Qingmin Liao, Tianchen Zhao, Xuefei Ning, Yu Wang, Zixuan Zhou","submitted_at":"2023-02-02T08:22:35Z","abstract_excerpt":"Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of architecture-performance data is required to get a working predictor. In this paper, we focus on exploiting information in cheaper-to-obtain performance estimations (i.e., low-fidelity information) to mitigate the large data requirements of predictor training. Despite the intuitiveness of this idea, we observe that using inappropriate low-fidelity information even dam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00932","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/2302.00932/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":"2302.00932","created_at":"2026-07-05T05:38:14.078418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00932v1","created_at":"2026-07-05T05:38:14.078418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00932","created_at":"2026-07-05T05:38:14.078418+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBO72R5MNCN4","created_at":"2026-07-05T05:38:14.078418+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBO72R5MNCN4UAT5","created_at":"2026-07-05T05:38:14.078418+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBO72R5M","created_at":"2026-07-05T05:38:14.078418+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/EBO72R5MNCN4UAT5CYYF7P5FLA","json":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA.json","graph_json":"https://pith.science/api/pith-number/EBO72R5MNCN4UAT5CYYF7P5FLA/graph.json","events_json":"https://pith.science/api/pith-number/EBO72R5MNCN4UAT5CYYF7P5FLA/events.json","paper":"https://pith.science/paper/EBO72R5M"},"agent_actions":{"view_html":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA","download_json":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA.json","view_paper":"https://pith.science/paper/EBO72R5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00932&json=true","fetch_graph":"https://pith.science/api/pith-number/EBO72R5MNCN4UAT5CYYF7P5FLA/graph.json","fetch_events":"https://pith.science/api/pith-number/EBO72R5MNCN4UAT5CYYF7P5FLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA/action/storage_attestation","attest_author":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA/action/author_attestation","sign_citation":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA/action/citation_signature","submit_replication":"https://pith.science/pith/EBO72R5MNCN4UAT5CYYF7P5FLA/action/replication_record"}},"created_at":"2026-07-05T05:38:14.078418+00:00","updated_at":"2026-07-05T05:38:14.078418+00:00"}