{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZC5GWO3LBWLOJ5QMQRRGUSPLGE","short_pith_number":"pith:ZC5GWO3L","schema_version":"1.0","canonical_sha256":"c8ba6b3b6b0d96e4f60c84626a49eb3108c1dbd6801e6f81729d1c18eb346b66","source":{"kind":"arxiv","id":"2110.05842","version":1},"attestation_state":"computed","paper":{"title":"Across-Task Neural Architecture Search via Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingtao Rong, Linlin Ou, Mingyang Zhang, Xinyi Yu","submitted_at":"2021-10-12T09:07:33Z","abstract_excerpt":"Adequate labeled data and expensive compute resources are the prerequisites for the success of neural architecture search(NAS). It is challenging to apply NAS in meta-learning scenarios with limited compute resources and data. In this paper, an across-task neural architecture search (AT-NAS) is proposed to address the problem through combining gradient-based meta-learning with EA-based NAS to learn over the distribution of tasks. The supernet is learned over an entire set of tasks by meta-learning its weights. Architecture encodes of subnets sampled from the supernet are iteratively adapted by"},"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":"2110.05842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T09:07:33Z","cross_cats_sorted":[],"title_canon_sha256":"2714ea6a10aeba351dc898d0210f115e1e019a1d958852b67014765139370e9b","abstract_canon_sha256":"fc33ea7aba6821787ff35e0f38a941f7e2f3f1234e14bb60fedaa83ee43442eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:07.138380Z","signature_b64":"3mRLxr3qg6AXR5gc6bHqPuEyuhiCy2ZBJ/yQ4jFzksvgbJFUKguTIVzu7wRRaA/sVRGPA1lJB9oOYIcdqdruBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8ba6b3b6b0d96e4f60c84626a49eb3108c1dbd6801e6f81729d1c18eb346b66","last_reissued_at":"2026-07-05T03:22:07.137840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:07.137840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Across-Task Neural Architecture Search via Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingtao Rong, Linlin Ou, Mingyang Zhang, Xinyi Yu","submitted_at":"2021-10-12T09:07:33Z","abstract_excerpt":"Adequate labeled data and expensive compute resources are the prerequisites for the success of neural architecture search(NAS). It is challenging to apply NAS in meta-learning scenarios with limited compute resources and data. In this paper, an across-task neural architecture search (AT-NAS) is proposed to address the problem through combining gradient-based meta-learning with EA-based NAS to learn over the distribution of tasks. The supernet is learned over an entire set of tasks by meta-learning its weights. Architecture encodes of subnets sampled from the supernet are iteratively adapted by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05842","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/2110.05842/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":"2110.05842","created_at":"2026-07-05T03:22:07.137900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05842v1","created_at":"2026-07-05T03:22:07.137900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05842","created_at":"2026-07-05T03:22:07.137900+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZC5GWO3LBWLO","created_at":"2026-07-05T03:22:07.137900+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZC5GWO3LBWLOJ5QM","created_at":"2026-07-05T03:22:07.137900+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZC5GWO3L","created_at":"2026-07-05T03:22:07.137900+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/ZC5GWO3LBWLOJ5QMQRRGUSPLGE","json":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE.json","graph_json":"https://pith.science/api/pith-number/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/graph.json","events_json":"https://pith.science/api/pith-number/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/events.json","paper":"https://pith.science/paper/ZC5GWO3L"},"agent_actions":{"view_html":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE","download_json":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE.json","view_paper":"https://pith.science/paper/ZC5GWO3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05842&json=true","fetch_graph":"https://pith.science/api/pith-number/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/action/storage_attestation","attest_author":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/action/author_attestation","sign_citation":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/action/citation_signature","submit_replication":"https://pith.science/pith/ZC5GWO3LBWLOJ5QMQRRGUSPLGE/action/replication_record"}},"created_at":"2026-07-05T03:22:07.137900+00:00","updated_at":"2026-07-05T03:22:07.137900+00:00"}