{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TXZUWN2DTZSO22AGQKGHI6RGUP","short_pith_number":"pith:TXZUWN2D","schema_version":"1.0","canonical_sha256":"9df34b37439e64ed6806828c747a26a3d4b72e6ea6537d0623c7b3d34b39315a","source":{"kind":"arxiv","id":"2303.09730","version":2},"attestation_state":"computed","paper":{"title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Tang, Huiqiang Jiang, Jiahang Xu, Li Lyna Zhang, Mao Yang, Quanlu Zhang, Ting Cao, Yuqing Yang, Zhi Wang","submitted_at":"2023-03-17T02:19:28Z","abstract_excerpt":"Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big challenge. In this work, we propose ElasticViT, a two-stage NAS approach that trains a high-quality ViT supernet over a very large search space that supports a wide range of mobile devices, and then searches an optimal sub-network (subnet) for direct deployment. However, prior supernet training methods that rely on uniform sampling suffer from the gradient conf"},"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":"2303.09730","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T02:19:28Z","cross_cats_sorted":[],"title_canon_sha256":"deff1bc693bc99b350d6791b298ae887124cec9ff1c41a27dd4dd8aee5dbf40d","abstract_canon_sha256":"47ad9a055bae9c6f5dc749bd7c7fdb34753d6a4908ba29c31be783f1aafaf610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:16.383860Z","signature_b64":"p7dNvq13DMCEl/jDE/RmYIGDAS73w3EwGxxewlZhwy/C5ZeW3ru5MOJ9a26W1oz1hC6/cTxogiBrGiI5FREsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df34b37439e64ed6806828c747a26a3d4b72e6ea6537d0623c7b3d34b39315a","last_reissued_at":"2026-07-05T05:53:16.383305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:16.383305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Tang, Huiqiang Jiang, Jiahang Xu, Li Lyna Zhang, Mao Yang, Quanlu Zhang, Ting Cao, Yuqing Yang, Zhi Wang","submitted_at":"2023-03-17T02:19:28Z","abstract_excerpt":"Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big challenge. In this work, we propose ElasticViT, a two-stage NAS approach that trains a high-quality ViT supernet over a very large search space that supports a wide range of mobile devices, and then searches an optimal sub-network (subnet) for direct deployment. However, prior supernet training methods that rely on uniform sampling suffer from the gradient conf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09730","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/2303.09730/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":"2303.09730","created_at":"2026-07-05T05:53:16.383371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09730v2","created_at":"2026-07-05T05:53:16.383371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09730","created_at":"2026-07-05T05:53:16.383371+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXZUWN2DTZSO","created_at":"2026-07-05T05:53:16.383371+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXZUWN2DTZSO22AG","created_at":"2026-07-05T05:53:16.383371+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXZUWN2D","created_at":"2026-07-05T05:53:16.383371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP","json":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP.json","graph_json":"https://pith.science/api/pith-number/TXZUWN2DTZSO22AGQKGHI6RGUP/graph.json","events_json":"https://pith.science/api/pith-number/TXZUWN2DTZSO22AGQKGHI6RGUP/events.json","paper":"https://pith.science/paper/TXZUWN2D"},"agent_actions":{"view_html":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP","download_json":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP.json","view_paper":"https://pith.science/paper/TXZUWN2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09730&json=true","fetch_graph":"https://pith.science/api/pith-number/TXZUWN2DTZSO22AGQKGHI6RGUP/graph.json","fetch_events":"https://pith.science/api/pith-number/TXZUWN2DTZSO22AGQKGHI6RGUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP/action/storage_attestation","attest_author":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP/action/author_attestation","sign_citation":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP/action/citation_signature","submit_replication":"https://pith.science/pith/TXZUWN2DTZSO22AGQKGHI6RGUP/action/replication_record"}},"created_at":"2026-07-05T05:53:16.383371+00:00","updated_at":"2026-07-05T05:53:16.383371+00:00"}