{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VPNCBKURVBPMPZGTADNBOCUSNG","short_pith_number":"pith:VPNCBKUR","schema_version":"1.0","canonical_sha256":"abda20aa91a85ec7e4d300da170a92698e40513600d304d4dc510767c0cec5bf","source":{"kind":"arxiv","id":"2003.03384","version":2},"attestation_state":"computed","paper":{"title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Liang, David R. So, Esteban Real, Quoc V. Le","submitted_at":"2020-03-06T19:00:04Z","abstract_excerpt":"Machine learning research has advanced in multiple aspects, including model structures and learning methods. The effort to automate such research, known as AutoML, has also made significant progress. However, this progress has largely focused on the architecture of neural networks, where it has relied on sophisticated expert-designed layers as building blocks---or similarly restrictive search spaces. Our goal is to show that AutoML can go further: it is possible today to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. We "},"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":"2003.03384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-06T19:00:04Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"0de4389caa4a81232dd268a543c08c6691a638e378e9206965a7dd469d65df37","abstract_canon_sha256":"2ec6c2761537c18d841ef457fa31106e3b542400f6225cdaa744f35b99c1dfec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:41.428207Z","signature_b64":"eSgR23ze+abCvohIJ9Sn7KuUsravwL2eF6sw0OChB6aUvNRpqZxi1Qzw+yT0QDZIspG/F02ttVrGNkLhHRxADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abda20aa91a85ec7e4d300da170a92698e40513600d304d4dc510767c0cec5bf","last_reissued_at":"2026-07-05T01:14:41.427728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:41.427728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Liang, David R. So, Esteban Real, Quoc V. Le","submitted_at":"2020-03-06T19:00:04Z","abstract_excerpt":"Machine learning research has advanced in multiple aspects, including model structures and learning methods. The effort to automate such research, known as AutoML, has also made significant progress. However, this progress has largely focused on the architecture of neural networks, where it has relied on sophisticated expert-designed layers as building blocks---or similarly restrictive search spaces. Our goal is to show that AutoML can go further: it is possible today to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03384","kind":"arxiv","version":2},"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/2003.03384/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":"2003.03384","created_at":"2026-07-05T01:14:41.427789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.03384v2","created_at":"2026-07-05T01:14:41.427789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03384","created_at":"2026-07-05T01:14:41.427789+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPNCBKURVBPM","created_at":"2026-07-05T01:14:41.427789+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPNCBKURVBPMPZGT","created_at":"2026-07-05T01:14:41.427789+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPNCBKUR","created_at":"2026-07-05T01:14:41.427789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05704","citing_title":"LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11359","citing_title":"CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05587","citing_title":"ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG","json":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG.json","graph_json":"https://pith.science/api/pith-number/VPNCBKURVBPMPZGTADNBOCUSNG/graph.json","events_json":"https://pith.science/api/pith-number/VPNCBKURVBPMPZGTADNBOCUSNG/events.json","paper":"https://pith.science/paper/VPNCBKUR"},"agent_actions":{"view_html":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG","download_json":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG.json","view_paper":"https://pith.science/paper/VPNCBKUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.03384&json=true","fetch_graph":"https://pith.science/api/pith-number/VPNCBKURVBPMPZGTADNBOCUSNG/graph.json","fetch_events":"https://pith.science/api/pith-number/VPNCBKURVBPMPZGTADNBOCUSNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG/action/storage_attestation","attest_author":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG/action/author_attestation","sign_citation":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG/action/citation_signature","submit_replication":"https://pith.science/pith/VPNCBKURVBPMPZGTADNBOCUSNG/action/replication_record"}},"created_at":"2026-07-05T01:14:41.427789+00:00","updated_at":"2026-07-05T01:14:41.427789+00:00"}