{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6HV34LJVPKWZ7MSUPIAB5SFF55","short_pith_number":"pith:6HV34LJV","schema_version":"1.0","canonical_sha256":"f1ebbe2d357aad9fb2547a001ec8a5ef52c463613bd46253141cbe53ef1c6029","source":{"kind":"arxiv","id":"2411.19819","version":1},"attestation_state":"computed","paper":{"title":"GradAlign for Training-free Model Performance Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yunhui Guo, Yuxuan Li","submitted_at":"2024-11-29T16:27:55Z","abstract_excerpt":"Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search space, making it a time-intensive process. Recently, a novel approach known as training-free neural architecture search (NAS) has emerged, aiming to discover the ideal architecture without necessitating extensive training. Training-free NAS leverages various indicators for architecture selection, including metrics such as the count of linear regions, the density of per-sample losses, and the stability of the finite-width"},"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":"2411.19819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T16:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"5d58a4b7f601930db2452641f0856ac92af429ad994db9397b2bfd084228a61a","abstract_canon_sha256":"8ec786447ccfd00fcafa566308cd7f95761272581d5ddcc3c44693a323a03130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:08.860143Z","signature_b64":"lYqWL28qrMxOIB34d8VExW1GqoEu1tXuqAsw5RSJzxbq0d04RaUCAOVM0PzMLFD/RvK79vdFKoRVRqWPbgzKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1ebbe2d357aad9fb2547a001ec8a5ef52c463613bd46253141cbe53ef1c6029","last_reissued_at":"2026-07-05T09:42:08.859674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:08.859674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GradAlign for Training-free Model Performance Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yunhui Guo, Yuxuan Li","submitted_at":"2024-11-29T16:27:55Z","abstract_excerpt":"Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search space, making it a time-intensive process. Recently, a novel approach known as training-free neural architecture search (NAS) has emerged, aiming to discover the ideal architecture without necessitating extensive training. Training-free NAS leverages various indicators for architecture selection, including metrics such as the count of linear regions, the density of per-sample losses, and the stability of the finite-width"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19819","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/2411.19819/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":"2411.19819","created_at":"2026-07-05T09:42:08.859739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19819v1","created_at":"2026-07-05T09:42:08.859739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19819","created_at":"2026-07-05T09:42:08.859739+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HV34LJVPKWZ","created_at":"2026-07-05T09:42:08.859739+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HV34LJVPKWZ7MSU","created_at":"2026-07-05T09:42:08.859739+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HV34LJV","created_at":"2026-07-05T09:42:08.859739+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/6HV34LJVPKWZ7MSUPIAB5SFF55","json":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55.json","graph_json":"https://pith.science/api/pith-number/6HV34LJVPKWZ7MSUPIAB5SFF55/graph.json","events_json":"https://pith.science/api/pith-number/6HV34LJVPKWZ7MSUPIAB5SFF55/events.json","paper":"https://pith.science/paper/6HV34LJV"},"agent_actions":{"view_html":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55","download_json":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55.json","view_paper":"https://pith.science/paper/6HV34LJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19819&json=true","fetch_graph":"https://pith.science/api/pith-number/6HV34LJVPKWZ7MSUPIAB5SFF55/graph.json","fetch_events":"https://pith.science/api/pith-number/6HV34LJVPKWZ7MSUPIAB5SFF55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55/action/storage_attestation","attest_author":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55/action/author_attestation","sign_citation":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55/action/citation_signature","submit_replication":"https://pith.science/pith/6HV34LJVPKWZ7MSUPIAB5SFF55/action/replication_record"}},"created_at":"2026-07-05T09:42:08.859739+00:00","updated_at":"2026-07-05T09:42:08.859739+00:00"}