{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6N6XUTSQOTNWNLVCLBBJ7YO7AR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ada15c765386a9c262d86bffd0cc4ac0e0de837dbae6adc7c2a0acd829cc9182","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T15:39:08Z","title_canon_sha256":"17430bf55a71fa597df47b90dee6eaf3a1d90f609ea98384245d0169c2086805"},"schema_version":"1.0","source":{"id":"2106.13700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13700","created_at":"2026-07-05T03:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13700v2","created_at":"2026-07-05T03:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13700","created_at":"2026-07-05T03:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"6N6XUTSQOTNW","created_at":"2026-07-05T03:36:07Z"},{"alias_kind":"pith_short_16","alias_value":"6N6XUTSQOTNWNLVC","created_at":"2026-07-05T03:36:07Z"},{"alias_kind":"pith_short_8","alias_value":"6N6XUTSQ","created_at":"2026-07-05T03:36:07Z"}],"graph_snapshots":[{"event_id":"sha256:943e4b9c5f8f96ef46bf0e9f7315047d2b4bc03d19c5c99164cb555b3e2cfac1","target":"graph","created_at":"2026-07-05T03:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.13700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used neural architecture search (NAS) in CNNs. However, we empirically find this straightforward adaptation would encounter catastrophic failures and be frustratingly unstable for the training of superformer. In this paper, we argue that since ViTs mainly operate on token embeddings with little inductive bias, imbalance of channels for different architectures would ","authors_text":"Changshui Zhang, Chang Xu, Chen Qian, Fei Wang, Jiyang Xie, Mingkai Zheng, Shan You, Xiaogang Wang, Xiu Su","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T15:39:08Z","title":"ViTAS: Vision Transformer Architecture Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13700","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6470b5ce4277021b980676d8084ad9239c23bc540ca1d972523326939fae117a","target":"record","created_at":"2026-07-05T03:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ada15c765386a9c262d86bffd0cc4ac0e0de837dbae6adc7c2a0acd829cc9182","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T15:39:08Z","title_canon_sha256":"17430bf55a71fa597df47b90dee6eaf3a1d90f609ea98384245d0169c2086805"},"schema_version":"1.0","source":{"id":"2106.13700","kind":"arxiv","version":2}},"canonical_sha256":"f37d7a4e5074db66aea258429fe1df046a63572198b763b022360e1b48bd3c2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f37d7a4e5074db66aea258429fe1df046a63572198b763b022360e1b48bd3c2e","first_computed_at":"2026-07-05T03:36:07.556440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:07.556440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U3nVDaI/DkVT8up5iBZSciABcHxmDjehJ1knPSOKpRdp2PD6B5I6TzmRmEokVhDHgltRdsgd2D1QV9cXHBMsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:07.556949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6470b5ce4277021b980676d8084ad9239c23bc540ca1d972523326939fae117a","sha256:943e4b9c5f8f96ef46bf0e9f7315047d2b4bc03d19c5c99164cb555b3e2cfac1"],"state_sha256":"7b65dccb064ed538198dfd2b813398070b24c20ffb16c8939338d9324e4d85b2"}