{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NE3TZ5M2EWNNH4NHERQKBAJQP7","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":"267eeb5790528225dfc38b325a67ea8c0fc0a90417a48418cd29b3ba3509e41d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-12T22:12:35Z","title_canon_sha256":"641d8ea5a58affadeea6f05b0375bf230a4b22d0bd7ebd0d67fd6cd2e9aa8a5e"},"schema_version":"1.0","source":{"id":"2302.06015","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06015","created_at":"2026-07-05T07:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06015v3","created_at":"2026-07-05T07:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06015","created_at":"2026-07-05T07:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"NE3TZ5M2EWNN","created_at":"2026-07-05T07:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"NE3TZ5M2EWNNH4NH","created_at":"2026-07-05T07:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"NE3TZ5M2","created_at":"2026-07-05T07:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:07e8c0b69e879906b0981ce810efc359fb13da75bcb385fa2ba5467328a76db1","target":"graph","created_at":"2026-07-05T07:12:16Z","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/2302.06015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly elusive. Based on a data model characterizing both label-relevant and label-irrelevant tokens, this paper provides the first theoretical analysis of training a shallow ViT, i.e., one self-attention layer followed by a two-layer perceptron, for a classification task. We characterize the sample complexity to achieve a zero generalization error. Our sample comple","authors_text":"Hongkang Li, Meng Wang, Pin-Yu Chen, Sijia Liu","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-12T22:12:35Z","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06015","kind":"arxiv","version":3},"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:e41f69cf74581fd2afc73cdc6dc2b56e26cf44b7e0eef1ee134c5f9a95220df2","target":"record","created_at":"2026-07-05T07:12:16Z","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":"267eeb5790528225dfc38b325a67ea8c0fc0a90417a48418cd29b3ba3509e41d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-12T22:12:35Z","title_canon_sha256":"641d8ea5a58affadeea6f05b0375bf230a4b22d0bd7ebd0d67fd6cd2e9aa8a5e"},"schema_version":"1.0","source":{"id":"2302.06015","kind":"arxiv","version":3}},"canonical_sha256":"69373cf59a259ad3f1a72460a081307ffe946dd5e093053353875b1fb33d591b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69373cf59a259ad3f1a72460a081307ffe946dd5e093053353875b1fb33d591b","first_computed_at":"2026-07-05T07:12:16.054694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:16.054694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0i0q92eIOPah/9iSwWsF6wgQ1eeDhWfE/s5kU7lNXnGAz4+F3D6X8yMFDYeF1A63gs8qLp9z0wuFhI2aQTnJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:16.055183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06015","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e41f69cf74581fd2afc73cdc6dc2b56e26cf44b7e0eef1ee134c5f9a95220df2","sha256:07e8c0b69e879906b0981ce810efc359fb13da75bcb385fa2ba5467328a76db1"],"state_sha256":"19bbb7e83ce02beab1f5cceab5f487e22f9dd86c5170d6892ab0e66e1939f202"}