{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:35RY7WO4A4KEWZUZMB5ODGIPBL","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":"670d61915af1c6a37676ffd42912ed758525f7f4a36707efaa5d6b6552ea218e","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-02T15:53:25Z","title_canon_sha256":"d742706719db643bc70ca297abee950b5a9a74cccfe158364854f61b677a5d3b"},"schema_version":"1.0","source":{"id":"2501.01312","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01312","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01312v3","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01312","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"pith_short_12","alias_value":"35RY7WO4A4KE","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"pith_short_16","alias_value":"35RY7WO4A4KEWZUZ","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"pith_short_8","alias_value":"35RY7WO4","created_at":"2026-07-05T09:59:58Z"}],"graph_snapshots":[{"event_id":"sha256:880f9739acf741d30f1eb66134831ad8d285f9429a98cb950e66758e5c2b0f0f","target":"graph","created_at":"2026-07-05T09:59:58Z","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/2501.01312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, given a sufficiently large set of pre-training instances, are able to learn the algorithms themselves and perform statistical estimation tasks given new instances. This learning paradigm is distinct from the in-context learning setup and is similar to the learning procedure of human brains where skills are learned through past experience. Theoretically, we prove that pre-trained ","authors_text":"Dennis Wu, Han Liu, Hong-Yu Chen, Jianqing Fan, Yihan He, Yuan Cao","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-02T15:53:25Z","title":"Learning Spectral Methods by Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01312","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":"sha256:9fffcb5d43acf29b65cc22287526a08c3c36e093e598ce056a97872879fbae98","target":"record","created_at":"2026-07-05T09:59:58Z","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":"670d61915af1c6a37676ffd42912ed758525f7f4a36707efaa5d6b6552ea218e","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-02T15:53:25Z","title_canon_sha256":"d742706719db643bc70ca297abee950b5a9a74cccfe158364854f61b677a5d3b"},"schema_version":"1.0","source":{"id":"2501.01312","kind":"arxiv","version":3}},"canonical_sha256":"df638fd9dc07144b6699607ae1990f0adc96314f63f616841ef808d3fcc1998e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df638fd9dc07144b6699607ae1990f0adc96314f63f616841ef808d3fcc1998e","first_computed_at":"2026-07-05T09:59:58.389205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:58.389205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m06oCVXd4ow8/IVKUEFFpHl3C24cn9GiX712L17N3dlW1KLePBoU/AswBycU2p1vITtHY3BtGckYuU8stO/rAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:58.389651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01312","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fffcb5d43acf29b65cc22287526a08c3c36e093e598ce056a97872879fbae98","sha256:880f9739acf741d30f1eb66134831ad8d285f9429a98cb950e66758e5c2b0f0f"],"state_sha256":"8a0ca9e47ca5059087a0e2a66bc08aaf390768301b3c7ec1ab3613e77152bda5"}