{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:D2BI2G4UAOWS7XKBKZ2ZCYXMEF","short_pith_number":"pith:D2BI2G4U","schema_version":"1.0","canonical_sha256":"1e828d1b9403ad2fdd4156759162ec2160c954cb6efde848b869af34e8375f19","source":{"kind":"arxiv","id":"1904.00420","version":4},"attestation_state":"computed","paper":{"title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Mu, Jian Sun, Wen Heng, Xiangyu Zhang, Yichen Wei, Zechun Liu, Zichao Guo","submitted_at":"2019-03-31T14:34:43Z","abstract_excerpt":"We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This work propose a Single Path One-Shot model to address the challenge in the training. Our central idea is to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Training is performed by uniform path sampling. All architectures (and their weights) are trained fully and equally.\n  Comprehen"},"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":"1904.00420","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-31T14:34:43Z","cross_cats_sorted":[],"title_canon_sha256":"d5112fc96a29f2e6a594a12ed0127c60fb41ac03f2d45b6c9e4421eb85e255b4","abstract_canon_sha256":"1700976872b6bc75f11179c9dcc4bdb3b300692c849caf494af577c3ea7eeca8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:15.592836Z","signature_b64":"DBdYiHhmZqz2xM7+tH6OVwzrDPcIqU8OFYqM4bVd0d9+KzLpXnYmhxnb9sIo9CL8OlLmNemPIf+CGEOL4QLwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e828d1b9403ad2fdd4156759162ec2160c954cb6efde848b869af34e8375f19","last_reissued_at":"2026-07-05T01:17:15.592434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:15.592434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Mu, Jian Sun, Wen Heng, Xiangyu Zhang, Yichen Wei, Zechun Liu, Zichao Guo","submitted_at":"2019-03-31T14:34:43Z","abstract_excerpt":"We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This work propose a Single Path One-Shot model to address the challenge in the training. Our central idea is to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Training is performed by uniform path sampling. All architectures (and their weights) are trained fully and equally.\n  Comprehen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00420","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/1904.00420/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":"1904.00420","created_at":"2026-07-05T01:17:15.592483+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.00420v4","created_at":"2026-07-05T01:17:15.592483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00420","created_at":"2026-07-05T01:17:15.592483+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2BI2G4UAOWS","created_at":"2026-07-05T01:17:15.592483+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2BI2G4UAOWS7XKB","created_at":"2026-07-05T01:17:15.592483+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2BI2G4U","created_at":"2026-07-05T01:17:15.592483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21772","citing_title":"Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF","json":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF.json","graph_json":"https://pith.science/api/pith-number/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/graph.json","events_json":"https://pith.science/api/pith-number/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/events.json","paper":"https://pith.science/paper/D2BI2G4U"},"agent_actions":{"view_html":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF","download_json":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF.json","view_paper":"https://pith.science/paper/D2BI2G4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.00420&json=true","fetch_graph":"https://pith.science/api/pith-number/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/graph.json","fetch_events":"https://pith.science/api/pith-number/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/action/storage_attestation","attest_author":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/action/author_attestation","sign_citation":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/action/citation_signature","submit_replication":"https://pith.science/pith/D2BI2G4UAOWS7XKBKZ2ZCYXMEF/action/replication_record"}},"created_at":"2026-07-05T01:17:15.592483+00:00","updated_at":"2026-07-05T01:17:15.592483+00:00"}