{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4HLCE4A57BIMD73CF6IZGMVTHL","short_pith_number":"pith:4HLCE4A5","schema_version":"1.0","canonical_sha256":"e1d622701df850c1ff622f919332b33ac93b23bf6eb2c519dc2009902b3a4de3","source":{"kind":"arxiv","id":"2606.02008","version":1},"attestation_state":"computed","paper":{"title":"Provable Data Scaling Law for Meta Learning via Complexity Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kazuto Fukuchi, Kota Matsui, Ryuichiro Hataya","submitted_at":"2026-06-01T10:02:29Z","abstract_excerpt":"Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon. In this paper, we introduce complexity minimization, a novel meta-representation learning framework designed to enable theoretical analysis of this scaling behavior, which learns representations by evaluating the downstream model complexity best suited to each domain and minimizing the worst-case such"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-01T10:02:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3966c6dbb4804284246954a200e01c8962bdaf99d812175a580b278ce08c1e2","abstract_canon_sha256":"e1b48b60960abea38b302c6087dffa17c3919203f9f660d188d7ecee3f358532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:03.425382Z","signature_b64":"deUpyD+7v1c3qALJMbd7JjYCZs2Cjbe9E1f+ebIrP5ZBpJea/ZlKBrYdyAbc5j6cLngqaTzA7/AfzSOuc2PsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d622701df850c1ff622f919332b33ac93b23bf6eb2c519dc2009902b3a4de3","last_reissued_at":"2026-06-02T02:05:03.425014Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:03.425014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Data Scaling Law for Meta Learning via Complexity Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kazuto Fukuchi, Kota Matsui, Ryuichiro Hataya","submitted_at":"2026-06-01T10:02:29Z","abstract_excerpt":"Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon. In this paper, we introduce complexity minimization, a novel meta-representation learning framework designed to enable theoretical analysis of this scaling behavior, which learns representations by evaluating the downstream model complexity best suited to each domain and minimizing the worst-case such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02008","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.02008/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02008","created_at":"2026-06-02T02:05:03.425072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02008v1","created_at":"2026-06-02T02:05:03.425072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02008","created_at":"2026-06-02T02:05:03.425072+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HLCE4A57BIM","created_at":"2026-06-02T02:05:03.425072+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HLCE4A57BIMD73C","created_at":"2026-06-02T02:05:03.425072+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HLCE4A5","created_at":"2026-06-02T02:05:03.425072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL","json":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL.json","graph_json":"https://pith.science/api/pith-number/4HLCE4A57BIMD73CF6IZGMVTHL/graph.json","events_json":"https://pith.science/api/pith-number/4HLCE4A57BIMD73CF6IZGMVTHL/events.json","paper":"https://pith.science/paper/4HLCE4A5"},"agent_actions":{"view_html":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL","download_json":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL.json","view_paper":"https://pith.science/paper/4HLCE4A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02008&json=true","fetch_graph":"https://pith.science/api/pith-number/4HLCE4A57BIMD73CF6IZGMVTHL/graph.json","fetch_events":"https://pith.science/api/pith-number/4HLCE4A57BIMD73CF6IZGMVTHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL/action/storage_attestation","attest_author":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL/action/author_attestation","sign_citation":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL/action/citation_signature","submit_replication":"https://pith.science/pith/4HLCE4A57BIMD73CF6IZGMVTHL/action/replication_record"}},"created_at":"2026-06-02T02:05:03.425072+00:00","updated_at":"2026-06-02T02:05:03.425072+00:00"}