{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LPKFDEF2KUDOM5LKICLATM7EFQ","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":"806bf0ea619aad41f547e2fe585fd6d46076305293a1b81de068801f057faa85","cross_cats_sorted":["cs.LG","cs.NA","cs.NE","math.NA","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-05T16:22:46Z","title_canon_sha256":"5f5b904a0e9edd13ba48fbae4804b33fcbafc8a2a2e762404ddcfb6342e1b09f"},"schema_version":"1.0","source":{"id":"2502.03327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03327","created_at":"2026-07-05T10:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03327v1","created_at":"2026-07-05T10:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03327","created_at":"2026-07-05T10:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"LPKFDEF2KUDO","created_at":"2026-07-05T10:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"LPKFDEF2KUDOM5LK","created_at":"2026-07-05T10:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"LPKFDEF2","created_at":"2026-07-05T10:10:03Z"}],"graph_snapshots":[{"event_id":"sha256:b3324ca1e16cddbac8b01c97f5828de466d7b9e1ea2fb2d632b444d8e959fab0","target":"graph","created_at":"2026-07-05T10:10:03Z","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/2502.03327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of transformers is often linked to their ability to perform in-context learning. Recent work shows that transformers are universal in context, capable of approximating any real-valued continuous function of a context (a probability measure over $\\mathcal{X}\\subseteq \\mathbb{R}^d$) and a query $x\\in \\mathcal{X}$. This raises the question: Does in-context universality explain their advantage over classical models? We answer this in the negative by proving that MLPs with trainable activation functions are also universal in-context. This suggests the transformer's success is likely due","authors_text":"Anastasis Kratsios, Takashi Furuya","cross_cats":["cs.LG","cs.NA","cs.NE","math.NA","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-05T16:22:46Z","title":"Is In-Context Universality Enough? MLPs are Also Universal In-Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03327","kind":"arxiv","version":1},"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:e4711fc13c45336898ee1b016a0f8b295594c421b1d8958a435ff73b466a3c7e","target":"record","created_at":"2026-07-05T10:10:03Z","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":"806bf0ea619aad41f547e2fe585fd6d46076305293a1b81de068801f057faa85","cross_cats_sorted":["cs.LG","cs.NA","cs.NE","math.NA","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-05T16:22:46Z","title_canon_sha256":"5f5b904a0e9edd13ba48fbae4804b33fcbafc8a2a2e762404ddcfb6342e1b09f"},"schema_version":"1.0","source":{"id":"2502.03327","kind":"arxiv","version":1}},"canonical_sha256":"5bd45190ba5506e6756a409609b3e42c29828d6507c2972dd86c7ed167ca72c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bd45190ba5506e6756a409609b3e42c29828d6507c2972dd86c7ed167ca72c5","first_computed_at":"2026-07-05T10:10:03.258057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:03.258057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RtFYeGHPQ+6nbAjsYurZYS/hGyhdouICXfl/iFaJJwEkbV3xeb2HeIw2yyyCEFwO+PI2MbvATk3vyYsRoLNiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:03.258535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4711fc13c45336898ee1b016a0f8b295594c421b1d8958a435ff73b466a3c7e","sha256:b3324ca1e16cddbac8b01c97f5828de466d7b9e1ea2fb2d632b444d8e959fab0"],"state_sha256":"dc4ba43497658cc4873adf1f099ff5aba42a877e2bdde8fd68029ce6c834b8cc"}