{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NZLRBBGZI6BQPDUACOSVXXXHPX","short_pith_number":"pith:NZLRBBGZ","schema_version":"1.0","canonical_sha256":"6e571084d94783078e8013a55bdee77dd2ee9f9cfccccf8599b427e18a3a7f01","source":{"kind":"arxiv","id":"2102.04074","version":1},"attestation_state":"computed","paper":{"title":"Learning Curve Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marcus Hutter","submitted_at":"2021-02-08T09:25:31Z","abstract_excerpt":"Recently a number of empirical \"universal\" scaling law papers have been published, most notably by OpenAI. `Scaling laws' refers to power-law decreases of training or test error w.r.t. more data, larger neural networks, and/or more compute. In this work we focus on scaling w.r.t. data size $n$. Theoretical understanding of this phenomenon is largely lacking, except in finite-dimensional models for which error typically decreases with $n^{-1/2}$ or $n^{-1}$, where $n$ is the sample size. We develop and theoretically analyse the simplest possible (toy) model that can exhibit $n^{-\\beta}$ learnin"},"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":"2102.04074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T09:25:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0c3bf7d713e54876bea23fb43d4c0c6b6de8aa1c306e2ad96af0cb819967b316","abstract_canon_sha256":"3f7fb4bd29bf6be3967d3d9df4a23eb256e98e69833549eeba19b0e329750c6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:45.669139Z","signature_b64":"PH8K18usM4SPFB8iQeFS7aOfUwgvyP7y0f3TuwYgFYscGrnBz7VISMoW6e9O0lCbw9ctOoWkFv1n5JXZgM30CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e571084d94783078e8013a55bdee77dd2ee9f9cfccccf8599b427e18a3a7f01","last_reissued_at":"2026-07-05T02:14:45.668707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:45.668707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Curve Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marcus Hutter","submitted_at":"2021-02-08T09:25:31Z","abstract_excerpt":"Recently a number of empirical \"universal\" scaling law papers have been published, most notably by OpenAI. `Scaling laws' refers to power-law decreases of training or test error w.r.t. more data, larger neural networks, and/or more compute. In this work we focus on scaling w.r.t. data size $n$. Theoretical understanding of this phenomenon is largely lacking, except in finite-dimensional models for which error typically decreases with $n^{-1/2}$ or $n^{-1}$, where $n$ is the sample size. We develop and theoretically analyse the simplest possible (toy) model that can exhibit $n^{-\\beta}$ learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04074","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/2102.04074/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":"2102.04074","created_at":"2026-07-05T02:14:45.668777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04074v1","created_at":"2026-07-05T02:14:45.668777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04074","created_at":"2026-07-05T02:14:45.668777+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZLRBBGZI6BQ","created_at":"2026-07-05T02:14:45.668777+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZLRBBGZI6BQPDUA","created_at":"2026-07-05T02:14:45.668777+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZLRBBGZ","created_at":"2026-07-05T02:14:45.668777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25008","citing_title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26617","citing_title":"Sketched Linear Contrastive Learning: Approximation, Optimization, and Statistical Scaling","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20347","citing_title":"Critical Percolation as a Synthetic Data Model for Interpretability","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01302","citing_title":"Structure and Scale in Simplicial Sequence Modelling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26146","citing_title":"Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24316","citing_title":"From One-Pass SGD to Data Reuse: Mini-Batch Scaling Laws in Sketched Linear Regression","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29858","citing_title":"Smooth Scaling Laws Hide Stepwise Token Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27989","citing_title":"Law of Neural Interaction: Depth-Width Shape, Interaction Efficiency, and Generalization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10395","citing_title":"Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.10465","citing_title":"Superposition Yields Robust Neural Scaling","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX","json":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX.json","graph_json":"https://pith.science/api/pith-number/NZLRBBGZI6BQPDUACOSVXXXHPX/graph.json","events_json":"https://pith.science/api/pith-number/NZLRBBGZI6BQPDUACOSVXXXHPX/events.json","paper":"https://pith.science/paper/NZLRBBGZ"},"agent_actions":{"view_html":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX","download_json":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX.json","view_paper":"https://pith.science/paper/NZLRBBGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04074&json=true","fetch_graph":"https://pith.science/api/pith-number/NZLRBBGZI6BQPDUACOSVXXXHPX/graph.json","fetch_events":"https://pith.science/api/pith-number/NZLRBBGZI6BQPDUACOSVXXXHPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX/action/storage_attestation","attest_author":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX/action/author_attestation","sign_citation":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX/action/citation_signature","submit_replication":"https://pith.science/pith/NZLRBBGZI6BQPDUACOSVXXXHPX/action/replication_record"}},"created_at":"2026-07-05T02:14:45.668777+00:00","updated_at":"2026-07-05T02:14:45.668777+00:00"}