{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YUYTKXEBKDNYNO4HDUYCQHCHMW","short_pith_number":"pith:YUYTKXEB","schema_version":"1.0","canonical_sha256":"c531355c8150db86bb871d30281c4765b2cd7aa3835f590212bcc9c2e73a8f4e","source":{"kind":"arxiv","id":"2505.09344","version":1},"attestation_state":"computed","paper":{"title":"GreenFactory: Ensembling Zero-Cost Proxies to Estimate Performance of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Gabriel Cort\\^es, Nuno Louren\\c{c}o, Paolo Romano, Penousal Machado","submitted_at":"2025-05-14T12:40:34Z","abstract_excerpt":"Determining the performance of a Deep Neural Network during Neural Architecture Search processes is essential for identifying optimal architectures and hyperparameters. Traditionally, this process requires training and evaluation of each network, which is time-consuming and resource-intensive. Zero-cost proxies estimate performance without training, serving as an alternative to traditional training. However, recent proxies often lack generalization across diverse scenarios and provide only relative rankings rather than predicted accuracies. To address these limitations, we propose GreenFactory"},"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":"2505.09344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-14T12:40:34Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"d45efdd91cf250c3e00d6d16c9f64a30381be4f923eca7518ff3784596778a4c","abstract_canon_sha256":"b3850219b5d3dec9866b589b2e52f77e5188f720af23c63767a4b1cfbef66e04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:06.700521Z","signature_b64":"JFqh7Y2r/FOmIhgOCB0thK7kBD4NTCDPa14SGq/xUCj2jTCArC5uiFv8j0KeHccouNdIHzTjtyOy+YbRVScDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c531355c8150db86bb871d30281c4765b2cd7aa3835f590212bcc9c2e73a8f4e","last_reissued_at":"2026-07-05T11:03:06.700032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:06.700032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GreenFactory: Ensembling Zero-Cost Proxies to Estimate Performance of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Gabriel Cort\\^es, Nuno Louren\\c{c}o, Paolo Romano, Penousal Machado","submitted_at":"2025-05-14T12:40:34Z","abstract_excerpt":"Determining the performance of a Deep Neural Network during Neural Architecture Search processes is essential for identifying optimal architectures and hyperparameters. Traditionally, this process requires training and evaluation of each network, which is time-consuming and resource-intensive. Zero-cost proxies estimate performance without training, serving as an alternative to traditional training. However, recent proxies often lack generalization across diverse scenarios and provide only relative rankings rather than predicted accuracies. To address these limitations, we propose GreenFactory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09344","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/2505.09344/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":"2505.09344","created_at":"2026-07-05T11:03:06.700088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09344v1","created_at":"2026-07-05T11:03:06.700088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09344","created_at":"2026-07-05T11:03:06.700088+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUYTKXEBKDNY","created_at":"2026-07-05T11:03:06.700088+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUYTKXEBKDNYNO4H","created_at":"2026-07-05T11:03:06.700088+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUYTKXEB","created_at":"2026-07-05T11:03:06.700088+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/YUYTKXEBKDNYNO4HDUYCQHCHMW","json":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW.json","graph_json":"https://pith.science/api/pith-number/YUYTKXEBKDNYNO4HDUYCQHCHMW/graph.json","events_json":"https://pith.science/api/pith-number/YUYTKXEBKDNYNO4HDUYCQHCHMW/events.json","paper":"https://pith.science/paper/YUYTKXEB"},"agent_actions":{"view_html":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW","download_json":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW.json","view_paper":"https://pith.science/paper/YUYTKXEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09344&json=true","fetch_graph":"https://pith.science/api/pith-number/YUYTKXEBKDNYNO4HDUYCQHCHMW/graph.json","fetch_events":"https://pith.science/api/pith-number/YUYTKXEBKDNYNO4HDUYCQHCHMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW/action/storage_attestation","attest_author":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW/action/author_attestation","sign_citation":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW/action/citation_signature","submit_replication":"https://pith.science/pith/YUYTKXEBKDNYNO4HDUYCQHCHMW/action/replication_record"}},"created_at":"2026-07-05T11:03:06.700088+00:00","updated_at":"2026-07-05T11:03:06.700088+00:00"}