{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XT2RI2A7G5ZOKHS4H3CWGPBMBD","short_pith_number":"pith:XT2RI2A7","schema_version":"1.0","canonical_sha256":"bcf514681f3772e51e5c3ec5633c2c08d99b65c00a69213026c4f473268dd4fb","source":{"kind":"arxiv","id":"2402.02105","version":1},"attestation_state":"computed","paper":{"title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lujun Li, Peijie Dong, Qiang Wang, Xiang Liu, Xiaowen Chu, Xinglin Pan, Zimian Wei","submitted_at":"2024-02-03T10:00:11Z","abstract_excerpt":"Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the efficacy of zero-cost proxies in various NAS benchmarks. Several studies propose the automated design of zero-cost proxies to achieve SOTA performance but require tedious searching progress. Furthermore, we identify a critical issue with current zero-cost proxies: they aggregate node-wise zero-cost statistics without considering the fact that not all nodes in a neural network equally impact performance estimation. Our observations reveal that node-wise zero-cost statistics significantly vary in their contributions "},"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":"2402.02105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-03T10:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"a1dde5a6514b18d1974460187035489cc14d1f403501b8bd1103cb33afeb65e5","abstract_canon_sha256":"6eadb080bda8412aebd06ccd4bd6a3b747d0ec1e6b8467cdc16096a748de728b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:11.108464Z","signature_b64":"qHxFW91XY2mZ571bWATB7qIZZLowmF49/Uc9Pu5uL2Vv+tkWiNR+nF4XlYztn/OE5oeNkTfaOvQSrlLqZTYlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf514681f3772e51e5c3ec5633c2c08d99b65c00a69213026c4f473268dd4fb","last_reissued_at":"2026-07-05T07:41:11.108032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:11.108032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lujun Li, Peijie Dong, Qiang Wang, Xiang Liu, Xiaowen Chu, Xinglin Pan, Zimian Wei","submitted_at":"2024-02-03T10:00:11Z","abstract_excerpt":"Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the efficacy of zero-cost proxies in various NAS benchmarks. Several studies propose the automated design of zero-cost proxies to achieve SOTA performance but require tedious searching progress. Furthermore, we identify a critical issue with current zero-cost proxies: they aggregate node-wise zero-cost statistics without considering the fact that not all nodes in a neural network equally impact performance estimation. Our observations reveal that node-wise zero-cost statistics significantly vary in their contributions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02105","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/2402.02105/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":"2402.02105","created_at":"2026-07-05T07:41:11.108083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02105v1","created_at":"2026-07-05T07:41:11.108083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02105","created_at":"2026-07-05T07:41:11.108083+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT2RI2A7G5ZO","created_at":"2026-07-05T07:41:11.108083+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT2RI2A7G5ZOKHS4","created_at":"2026-07-05T07:41:11.108083+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT2RI2A7","created_at":"2026-07-05T07:41:11.108083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00880","citing_title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD","json":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD.json","graph_json":"https://pith.science/api/pith-number/XT2RI2A7G5ZOKHS4H3CWGPBMBD/graph.json","events_json":"https://pith.science/api/pith-number/XT2RI2A7G5ZOKHS4H3CWGPBMBD/events.json","paper":"https://pith.science/paper/XT2RI2A7"},"agent_actions":{"view_html":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD","download_json":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD.json","view_paper":"https://pith.science/paper/XT2RI2A7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02105&json=true","fetch_graph":"https://pith.science/api/pith-number/XT2RI2A7G5ZOKHS4H3CWGPBMBD/graph.json","fetch_events":"https://pith.science/api/pith-number/XT2RI2A7G5ZOKHS4H3CWGPBMBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD/action/storage_attestation","attest_author":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD/action/author_attestation","sign_citation":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD/action/citation_signature","submit_replication":"https://pith.science/pith/XT2RI2A7G5ZOKHS4H3CWGPBMBD/action/replication_record"}},"created_at":"2026-07-05T07:41:11.108083+00:00","updated_at":"2026-07-05T07:41:11.108083+00:00"}