{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOV3EJSIDX2XR36YBYKYBR2LR4","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":"912b47d85eb3bd296e81b0bb5aa153058ac707ecf6d4a262bbbb481e3f0eba9f","cross_cats_sorted":["cs.NA","math.NA","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T05:41:46Z","title_canon_sha256":"66c005030f9934fd0c6e6eb499b3565dd812b2b2367703781b4b84c0cb438000"},"schema_version":"1.0","source":{"id":"2505.03205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03205","created_at":"2026-05-20T00:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03205v3","created_at":"2026-05-20T00:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03205","created_at":"2026-05-20T00:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"UOV3EJSIDX2X","created_at":"2026-05-20T00:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"UOV3EJSIDX2XR36Y","created_at":"2026-05-20T00:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"UOV3EJSI","created_at":"2026-05-20T00:02:50Z"}],"graph_snapshots":[{"event_id":"sha256:127c15e724efc147d90b2d78ce891546748cd13e63f663108192e3b7915d1c23","target":"graph","created_at":"2026-05-20T00:02:50Z","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/2505.03205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit low-dimensional structures, along with some noise or measurement error. The performance of transformers tends to depend on the intrinsic dimension of the data/tasks, though theoretical understandings remain largely unexplored for transformers. This work establishes a theoretical foundation by analyzing the performance of transformers for regression tasks involving noi","authors_text":"Alexander Cloninger, Alex Havrilla, Rongjie Lai, Wenjing Liao, Zhaiming Shen","cross_cats":["cs.NA","math.NA","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T05:41:46Z","title":"Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03205","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":"sha256:28d20b0666b97db44844deac3b380441b1d3f8deead51d1ecb7942b877f6891f","target":"record","created_at":"2026-05-20T00:02:50Z","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":"912b47d85eb3bd296e81b0bb5aa153058ac707ecf6d4a262bbbb481e3f0eba9f","cross_cats_sorted":["cs.NA","math.NA","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T05:41:46Z","title_canon_sha256":"66c005030f9934fd0c6e6eb499b3565dd812b2b2367703781b4b84c0cb438000"},"schema_version":"1.0","source":{"id":"2505.03205","kind":"arxiv","version":3}},"canonical_sha256":"a3abb226481df578efd80e1580c74b8f1eed91c40c3d8dfdbf1456d834d18fbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3abb226481df578efd80e1580c74b8f1eed91c40c3d8dfdbf1456d834d18fbf","first_computed_at":"2026-05-20T00:02:50.033039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:50.033039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vcEAlLBqo84CZh2S1veY7vUyAxoEKGz8XLldMe1PAlxrjlcZblaCEyyjQIv7tRoODtU/b9beO7gKBSaghSUuAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:50.033785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28d20b0666b97db44844deac3b380441b1d3f8deead51d1ecb7942b877f6891f","sha256:127c15e724efc147d90b2d78ce891546748cd13e63f663108192e3b7915d1c23"],"state_sha256":"fa9ff1e033523af7bb608af5e74678d6186469c525b368efbc4ed0715bf25d7c"}