{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UYZ75WN2TT34EPRLKJDIPO2NLD","short_pith_number":"pith:UYZ75WN2","schema_version":"1.0","canonical_sha256":"a633fed9ba9cf7c23e2b524687bb4d58d919ffb24e1b9335e4dd960767e92f37","source":{"kind":"arxiv","id":"2111.10007","version":3},"attestation_state":"computed","paper":{"title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Chaojian Li, Hang Zhang, Jialiang Wang, Matthew Yu, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Yingyan Celine Lin","submitted_at":"2021-11-19T02:07:34Z","abstract_excerpt":"Neural Architecture Search (NAS) has been widely adopted to design accurate and efficient image classification models. However, applying NAS to a new computer vision task still requires a huge amount of effort. This is because 1) previous NAS research has been over-prioritized on image classification while largely ignoring other tasks; 2) many NAS works focus on optimizing task-specific components that cannot be favorably transferred to other tasks; and 3) existing NAS methods are typically designed to be \"proxyless\" and require significant effort to be integrated with each new task's training"},"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":"2111.10007","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T02:07:34Z","cross_cats_sorted":[],"title_canon_sha256":"5c6ebbf25f3f9aa46f80c17316975cf6800825a6e802bb8a922f43ce07c62583","abstract_canon_sha256":"917536c73a091586191ca904e435947f52178041c8952501c7ba98f38f97f1d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:31.597964Z","signature_b64":"dXSnJqPLg+0w2WrwiYMfWVWYSUiY0OZ28boPFgKCWH48K6Em1D7b/z10ekD2jSnUIMHLBWbEBPkgYx9fkqwMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a633fed9ba9cf7c23e2b524687bb4d58d919ffb24e1b9335e4dd960767e92f37","last_reissued_at":"2026-07-05T10:40:31.597475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:31.597475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Chaojian Li, Hang Zhang, Jialiang Wang, Matthew Yu, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Yingyan Celine Lin","submitted_at":"2021-11-19T02:07:34Z","abstract_excerpt":"Neural Architecture Search (NAS) has been widely adopted to design accurate and efficient image classification models. However, applying NAS to a new computer vision task still requires a huge amount of effort. This is because 1) previous NAS research has been over-prioritized on image classification while largely ignoring other tasks; 2) many NAS works focus on optimizing task-specific components that cannot be favorably transferred to other tasks; and 3) existing NAS methods are typically designed to be \"proxyless\" and require significant effort to be integrated with each new task's training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10007","kind":"arxiv","version":3},"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/2111.10007/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":"2111.10007","created_at":"2026-07-05T10:40:31.597534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10007v3","created_at":"2026-07-05T10:40:31.597534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10007","created_at":"2026-07-05T10:40:31.597534+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYZ75WN2TT34","created_at":"2026-07-05T10:40:31.597534+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYZ75WN2TT34EPRL","created_at":"2026-07-05T10:40:31.597534+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYZ75WN2","created_at":"2026-07-05T10:40:31.597534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16463","citing_title":"AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD","json":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD.json","graph_json":"https://pith.science/api/pith-number/UYZ75WN2TT34EPRLKJDIPO2NLD/graph.json","events_json":"https://pith.science/api/pith-number/UYZ75WN2TT34EPRLKJDIPO2NLD/events.json","paper":"https://pith.science/paper/UYZ75WN2"},"agent_actions":{"view_html":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD","download_json":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD.json","view_paper":"https://pith.science/paper/UYZ75WN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10007&json=true","fetch_graph":"https://pith.science/api/pith-number/UYZ75WN2TT34EPRLKJDIPO2NLD/graph.json","fetch_events":"https://pith.science/api/pith-number/UYZ75WN2TT34EPRLKJDIPO2NLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD/action/storage_attestation","attest_author":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD/action/author_attestation","sign_citation":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD/action/citation_signature","submit_replication":"https://pith.science/pith/UYZ75WN2TT34EPRLKJDIPO2NLD/action/replication_record"}},"created_at":"2026-07-05T10:40:31.597534+00:00","updated_at":"2026-07-05T10:40:31.597534+00:00"}