{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UBAYL5WXNF4LS2FRVQDNV2PLA2","short_pith_number":"pith:UBAYL5WX","schema_version":"1.0","canonical_sha256":"a04185f6d76978b968b1ac06dae9eb06b2be9b1e6d4c8a11d942707f68f9f2af","source":{"kind":"arxiv","id":"2006.10355","version":4},"attestation_state":"computed","paper":{"title":"DrNAS: Dirichlet Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Minhao Cheng, Ruochen Wang, Xiangning Chen, Xiaocheng Tang","submitted_at":"2020-06-18T08:23:02Z","abstract_excerpt":"This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet distribution. With recently developed pathwise derivatives, the Dirichlet parameters can be easily optimized with gradient-based optimizer in an end-to-end manner. This formulation improves the generalization ability and induces stochasticity that naturally encourages exploration in the search space. Furthermore, to alleviate the large memory consumption of differentia"},"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":"2006.10355","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T08:23:02Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3f8b998f4e6df2d3352b8712163a61b5afa2d569adc746d783d139d232fd690c","abstract_canon_sha256":"535a0befa184a5ac1784b95d631082f111d400fe3985c6530cd16629bb161273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:08.545533Z","signature_b64":"0D8idGxNoHSXrw3rqkyJ3k0VzdIEvO/Duoy0moTpqpwOWwzz4z0vfzOLqONH8u7MjkjBKfoIKG67I3guGBAPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04185f6d76978b968b1ac06dae9eb06b2be9b1e6d4c8a11d942707f68f9f2af","last_reissued_at":"2026-07-05T02:23:08.545044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:08.545044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrNAS: Dirichlet Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Minhao Cheng, Ruochen Wang, Xiangning Chen, Xiaocheng Tang","submitted_at":"2020-06-18T08:23:02Z","abstract_excerpt":"This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet distribution. With recently developed pathwise derivatives, the Dirichlet parameters can be easily optimized with gradient-based optimizer in an end-to-end manner. This formulation improves the generalization ability and induces stochasticity that naturally encourages exploration in the search space. Furthermore, to alleviate the large memory consumption of differentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10355","kind":"arxiv","version":4},"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/2006.10355/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":"2006.10355","created_at":"2026-07-05T02:23:08.545102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10355v4","created_at":"2026-07-05T02:23:08.545102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10355","created_at":"2026-07-05T02:23:08.545102+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBAYL5WXNF4L","created_at":"2026-07-05T02:23:08.545102+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBAYL5WXNF4LS2FR","created_at":"2026-07-05T02:23:08.545102+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBAYL5WX","created_at":"2026-07-05T02:23:08.545102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19206","citing_title":"NADER: Neural Architecture Design via Multi-Agent Collaboration","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2","json":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2.json","graph_json":"https://pith.science/api/pith-number/UBAYL5WXNF4LS2FRVQDNV2PLA2/graph.json","events_json":"https://pith.science/api/pith-number/UBAYL5WXNF4LS2FRVQDNV2PLA2/events.json","paper":"https://pith.science/paper/UBAYL5WX"},"agent_actions":{"view_html":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2","download_json":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2.json","view_paper":"https://pith.science/paper/UBAYL5WX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10355&json=true","fetch_graph":"https://pith.science/api/pith-number/UBAYL5WXNF4LS2FRVQDNV2PLA2/graph.json","fetch_events":"https://pith.science/api/pith-number/UBAYL5WXNF4LS2FRVQDNV2PLA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2/action/storage_attestation","attest_author":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2/action/author_attestation","sign_citation":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2/action/citation_signature","submit_replication":"https://pith.science/pith/UBAYL5WXNF4LS2FRVQDNV2PLA2/action/replication_record"}},"created_at":"2026-07-05T02:23:08.545102+00:00","updated_at":"2026-07-05T02:23:08.545102+00:00"}