{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ND6K7ZECQAOLEJ73KUJHMS46XP","short_pith_number":"pith:ND6K7ZEC","schema_version":"1.0","canonical_sha256":"68fcafe482801cb227fb5512764b9ebbc3a939ed6561bfbf515a24110592bf4e","source":{"kind":"arxiv","id":"2301.11300","version":3},"attestation_state":"computed","paper":{"title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guihong Li, Kartikeya Bhardwaj, Radu Marculescu, Yuedong Yang","submitted_at":"2023-01-26T18:38:56Z","abstract_excerpt":"Neural Architecture Search (NAS) is widely used to automatically obtain the neural network with the best performance among a large number of candidate architectures. To reduce the search time, zero-shot NAS aims at designing training-free proxies that can predict the test performance of a given architecture. However, as shown recently, none of the zero-shot proxies proposed to date can actually work consistently better than a naive proxy, namely, the number of network parameters (#Params). To improve this state of affairs, as the main theoretical contribution, we first reveal how some specific"},"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":"2301.11300","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-26T18:38:56Z","cross_cats_sorted":[],"title_canon_sha256":"a7931f67e77b2e957427d8c6637a7dd123a7ec6c0b82153f2f44022127aedb65","abstract_canon_sha256":"b18267b96655184eb12cf46dcffe546abc536bf5885ce188eaa1714901fd1ff1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:36.105392Z","signature_b64":"ySmLJueuctBfDzoMg/qmISJhcAeBlVIz8h10Qvh+aN0hv3XNsPeHimxloFSiDALfECyrQu6KUnCW67DV/d3aBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68fcafe482801cb227fb5512764b9ebbc3a939ed6561bfbf515a24110592bf4e","last_reissued_at":"2026-07-05T06:00:36.104964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:36.104964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guihong Li, Kartikeya Bhardwaj, Radu Marculescu, Yuedong Yang","submitted_at":"2023-01-26T18:38:56Z","abstract_excerpt":"Neural Architecture Search (NAS) is widely used to automatically obtain the neural network with the best performance among a large number of candidate architectures. To reduce the search time, zero-shot NAS aims at designing training-free proxies that can predict the test performance of a given architecture. However, as shown recently, none of the zero-shot proxies proposed to date can actually work consistently better than a naive proxy, namely, the number of network parameters (#Params). To improve this state of affairs, as the main theoretical contribution, we first reveal how some specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11300","kind":"arxiv","version":3},"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/2301.11300/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":"2301.11300","created_at":"2026-07-05T06:00:36.105020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11300v3","created_at":"2026-07-05T06:00:36.105020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11300","created_at":"2026-07-05T06:00:36.105020+00:00"},{"alias_kind":"pith_short_12","alias_value":"ND6K7ZECQAOL","created_at":"2026-07-05T06:00:36.105020+00:00"},{"alias_kind":"pith_short_16","alias_value":"ND6K7ZECQAOLEJ73","created_at":"2026-07-05T06:00:36.105020+00:00"},{"alias_kind":"pith_short_8","alias_value":"ND6K7ZEC","created_at":"2026-07-05T06:00:36.105020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23437","citing_title":"Coflex: Enhancing HW-NAS with Sparse Gaussian Processes for Efficient and Scalable DNN Accelerator Design","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP","json":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP.json","graph_json":"https://pith.science/api/pith-number/ND6K7ZECQAOLEJ73KUJHMS46XP/graph.json","events_json":"https://pith.science/api/pith-number/ND6K7ZECQAOLEJ73KUJHMS46XP/events.json","paper":"https://pith.science/paper/ND6K7ZEC"},"agent_actions":{"view_html":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP","download_json":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP.json","view_paper":"https://pith.science/paper/ND6K7ZEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11300&json=true","fetch_graph":"https://pith.science/api/pith-number/ND6K7ZECQAOLEJ73KUJHMS46XP/graph.json","fetch_events":"https://pith.science/api/pith-number/ND6K7ZECQAOLEJ73KUJHMS46XP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP/action/storage_attestation","attest_author":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP/action/author_attestation","sign_citation":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP/action/citation_signature","submit_replication":"https://pith.science/pith/ND6K7ZECQAOLEJ73KUJHMS46XP/action/replication_record"}},"created_at":"2026-07-05T06:00:36.105020+00:00","updated_at":"2026-07-05T06:00:36.105020+00:00"}