{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A3U7ESYAESXDDI5FO7UZ4WRXXU","short_pith_number":"pith:A3U7ESYA","schema_version":"1.0","canonical_sha256":"06e9f24b0024ae31a3a577e99e5a37bd076c4b3282f2325d81d09e7341cb0cde","source":{"kind":"arxiv","id":"1908.00709","version":6},"attestation_state":"computed","paper":{"title":"AutoML: A Survey of the State-of-the-Art","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiyong Zhao, Xiaowen Chu, Xin He","submitted_at":"2019-08-02T05:56:13Z","abstract_excerpt":"Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data pre"},"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":"1908.00709","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T05:56:13Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1462b12d27a7e1f03159e9f0f863fc3043947d7e68867ef99bbedcc4e9ba8c46","abstract_canon_sha256":"4bec65667bed52bafef6d1ce75e72f0d6f9454c95e6a8cda72ff0fc761875efa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:31.080965Z","signature_b64":"U9Amha013Es/+omdyYA2KUlWwFdEJQ7G5CiuYNc3Jgu7zrlbZqHXo7l1RGcykjEgfKyidqQ/+1RtClQhxwE2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06e9f24b0024ae31a3a577e99e5a37bd076c4b3282f2325d81d09e7341cb0cde","last_reissued_at":"2026-07-05T02:32:31.080483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:31.080483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoML: A Survey of the State-of-the-Art","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiyong Zhao, Xiaowen Chu, Xin He","submitted_at":"2019-08-02T05:56:13Z","abstract_excerpt":"Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.00709","kind":"arxiv","version":6},"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/1908.00709/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":"1908.00709","created_at":"2026-07-05T02:32:31.080543+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.00709v6","created_at":"2026-07-05T02:32:31.080543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.00709","created_at":"2026-07-05T02:32:31.080543+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3U7ESYAESXD","created_at":"2026-07-05T02:32:31.080543+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3U7ESYAESXDDI5F","created_at":"2026-07-05T02:32:31.080543+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3U7ESYA","created_at":"2026-07-05T02:32:31.080543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22971","citing_title":"Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20657","citing_title":"A-Evolve-Training: Autonomous Post-Training of a 30B Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20375","citing_title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU","json":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU.json","graph_json":"https://pith.science/api/pith-number/A3U7ESYAESXDDI5FO7UZ4WRXXU/graph.json","events_json":"https://pith.science/api/pith-number/A3U7ESYAESXDDI5FO7UZ4WRXXU/events.json","paper":"https://pith.science/paper/A3U7ESYA"},"agent_actions":{"view_html":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU","download_json":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU.json","view_paper":"https://pith.science/paper/A3U7ESYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.00709&json=true","fetch_graph":"https://pith.science/api/pith-number/A3U7ESYAESXDDI5FO7UZ4WRXXU/graph.json","fetch_events":"https://pith.science/api/pith-number/A3U7ESYAESXDDI5FO7UZ4WRXXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU/action/storage_attestation","attest_author":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU/action/author_attestation","sign_citation":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU/action/citation_signature","submit_replication":"https://pith.science/pith/A3U7ESYAESXDDI5FO7UZ4WRXXU/action/replication_record"}},"created_at":"2026-07-05T02:32:31.080543+00:00","updated_at":"2026-07-05T02:32:31.080543+00:00"}