{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ORG2DZ5OLIJ5KGWEJEOSQ6SFX4","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":"c4e5a1838346ad3f0ba00cacfb5065786814ca395d78fdeb64b5e077c57160f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T16:56:56Z","title_canon_sha256":"5c8f6335628d93922b09fc08ebe5b9b2a12386efe4e629fb7b889a4aaf54d6d6"},"schema_version":"1.0","source":{"id":"2605.20105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20105","created_at":"2026-05-20T02:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20105v1","created_at":"2026-05-20T02:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20105","created_at":"2026-05-20T02:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"ORG2DZ5OLIJ5","created_at":"2026-05-20T02:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"ORG2DZ5OLIJ5KGWE","created_at":"2026-05-20T02:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"ORG2DZ5O","created_at":"2026-05-20T02:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:7a45f854d49270987a97bbf05f47bf92ec766a6dcf43ffa1d12b3bfaf4dd4fba","target":"graph","created_at":"2026-05-20T02:06:02Z","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/2605.20105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to generalise from limited data is a fundamental challenge for both artificial and biological systems. A common strategy is to extract reusable structure from abundant unlabelled data, enabling efficient adaptation to new tasks from limited labelled data. This two-stage paradigm is now standard in modern training pipelines, where pretraining is followed by fine-tuning or linear probing. We provide an analytical model of this process: structure extraction is formalized as principal component analysis on unlabelled data, and downstream learning as linear regression on a separate labelle","authors_text":"Andrew Saxe, Cl\\'ementine Domin\\'e, Marco Mondelli, Rachel Swanson, Valentina Njaradi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T16:56:56Z","title":"Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20105","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":"sha256:289b668bcf4ec4cb763f82961c98bbe212aab912d7d149f3d095d091a08a8850","target":"record","created_at":"2026-05-20T02:06:02Z","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":"c4e5a1838346ad3f0ba00cacfb5065786814ca395d78fdeb64b5e077c57160f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T16:56:56Z","title_canon_sha256":"5c8f6335628d93922b09fc08ebe5b9b2a12386efe4e629fb7b889a4aaf54d6d6"},"schema_version":"1.0","source":{"id":"2605.20105","kind":"arxiv","version":1}},"canonical_sha256":"744da1e7ae5a13d51ac4491d287a45bf0950dadfca8e1d130c00345f2ec3d4c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"744da1e7ae5a13d51ac4491d287a45bf0950dadfca8e1d130c00345f2ec3d4c7","first_computed_at":"2026-05-20T02:06:02.263416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:06:02.263416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FmG7SpvI+1VVXVC6eBjlar29S9ZL6Zx+UeWBrB1HzjLhTK84KxOZUNjqJVLRUOAe4LlrbVhQH5uukHyu36Q1CA==","signature_status":"signed_v1","signed_at":"2026-05-20T02:06:02.264043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:289b668bcf4ec4cb763f82961c98bbe212aab912d7d149f3d095d091a08a8850","sha256:7a45f854d49270987a97bbf05f47bf92ec766a6dcf43ffa1d12b3bfaf4dd4fba"],"state_sha256":"2e4c4b03a422cc8bd6fd2d1434244fbda2cb5a9db8d399d0ea7c1f56a4b69f85"}