{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EHF3GRQNCELJAYSS2EQBDGFHA3","short_pith_number":"pith:EHF3GRQN","schema_version":"1.0","canonical_sha256":"21cbb3460d1116906252d1201198a706c65c98bb8fe40f095bd26a6048c61a03","source":{"kind":"arxiv","id":"2503.06092","version":1},"attestation_state":"computed","paper":{"title":"ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Danilo Ardagna, Eugenio Lomurno, Lunchen Xie, Manual Roveri, Matteo Gambella, Matteo Matteucci, Qingjiang Shi","submitted_at":"2025-03-08T06:43:33Z","abstract_excerpt":"Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS methods often face constraints in efficiency, operation selection, and adaptability under varying resource limitations. We introduce ZO-DARTS++, a novel NAS method that effectively balances performance and resource constraints. By integrating a zeroth-order approximation for efficient gradient handling, employing a sparsemax function with temperature annealing for clearer and more interpretable architecture distributions"},"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":"2503.06092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T06:43:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"863d2124a4e93ce24b9b4429828f143c185addc9ad13fe2c7ea16794ecd1d7ff","abstract_canon_sha256":"414f5d401b92dfb0e961c0cf6a48e2ec25aa97e6e3b8b531fece26133eae3624"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:53.770165Z","signature_b64":"Bhor618i7QAwnsA9WJsML2McPeaCG/zaxxO+JsUJe+5EOS98f3dATEVacrWwvvaz5Ycv98qJXx0T9xxTGBriCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21cbb3460d1116906252d1201198a706c65c98bb8fe40f095bd26a6048c61a03","last_reissued_at":"2026-07-05T10:26:53.769273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:53.769273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Danilo Ardagna, Eugenio Lomurno, Lunchen Xie, Manual Roveri, Matteo Gambella, Matteo Matteucci, Qingjiang Shi","submitted_at":"2025-03-08T06:43:33Z","abstract_excerpt":"Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS methods often face constraints in efficiency, operation selection, and adaptability under varying resource limitations. We introduce ZO-DARTS++, a novel NAS method that effectively balances performance and resource constraints. By integrating a zeroth-order approximation for efficient gradient handling, employing a sparsemax function with temperature annealing for clearer and more interpretable architecture distributions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06092","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/2503.06092/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":"2503.06092","created_at":"2026-07-05T10:26:53.769442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06092v1","created_at":"2026-07-05T10:26:53.769442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06092","created_at":"2026-07-05T10:26:53.769442+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHF3GRQNCELJ","created_at":"2026-07-05T10:26:53.769442+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHF3GRQNCELJAYSS","created_at":"2026-07-05T10:26:53.769442+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHF3GRQN","created_at":"2026-07-05T10:26:53.769442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10457","citing_title":"SEAL: Searching Expandable Architectures for Incremental Learning","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3","json":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3.json","graph_json":"https://pith.science/api/pith-number/EHF3GRQNCELJAYSS2EQBDGFHA3/graph.json","events_json":"https://pith.science/api/pith-number/EHF3GRQNCELJAYSS2EQBDGFHA3/events.json","paper":"https://pith.science/paper/EHF3GRQN"},"agent_actions":{"view_html":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3","download_json":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3.json","view_paper":"https://pith.science/paper/EHF3GRQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06092&json=true","fetch_graph":"https://pith.science/api/pith-number/EHF3GRQNCELJAYSS2EQBDGFHA3/graph.json","fetch_events":"https://pith.science/api/pith-number/EHF3GRQNCELJAYSS2EQBDGFHA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3/action/storage_attestation","attest_author":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3/action/author_attestation","sign_citation":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3/action/citation_signature","submit_replication":"https://pith.science/pith/EHF3GRQNCELJAYSS2EQBDGFHA3/action/replication_record"}},"created_at":"2026-07-05T10:26:53.769442+00:00","updated_at":"2026-07-05T10:26:53.769442+00:00"}