{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G4WMOLK44NXAZ3GPGJWHMMK3AL","short_pith_number":"pith:G4WMOLK4","schema_version":"1.0","canonical_sha256":"372cc72d5ce36e0ceccf326c76315b02d2a8c1d4dd6b57c868eef2e8a1738083","source":{"kind":"arxiv","id":"1909.12673","version":2},"attestation_state":"computed","paper":{"title":"A Constructive Prediction of the Generalization Error Across Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Rosenfeld, Jonathan S. Rosenfeld, Nir Shavit, Yonatan Belinkov","submitted_at":"2019-09-27T13:27:53Z","abstract_excerpt":"The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networks. Nevertheless, the functional form of this dependency remains elusive. In this work, we present a functional form which approximates well the generalization error in practice. Capitalizing on the successful concept of model scaling (e.g., width, depth), we are able to simultaneously construct such a form and specify the exact models which can attain it across model/data scales. Our construction follows insights ob"},"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":"1909.12673","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-27T13:27:53Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"58c024d2a119d586f3a583cbb889ba906284ee8f333d0bf253ed5712c26ab643","abstract_canon_sha256":"9c8b80cbd956438fee65f849f4f99f885fd5fe42c3a3937502c8780699317994"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:32.955496Z","signature_b64":"3+y37rzDT1lO8gkM24PrXod8X0OvQo+5Kp+TpDWwAXcaeg/b+nxDtDlO412AnanCXEwkwgyOHHL4+ilqN4RJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"372cc72d5ce36e0ceccf326c76315b02d2a8c1d4dd6b57c868eef2e8a1738083","last_reissued_at":"2026-07-05T00:27:32.955027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:32.955027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Constructive Prediction of the Generalization Error Across Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Rosenfeld, Jonathan S. Rosenfeld, Nir Shavit, Yonatan Belinkov","submitted_at":"2019-09-27T13:27:53Z","abstract_excerpt":"The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networks. Nevertheless, the functional form of this dependency remains elusive. In this work, we present a functional form which approximates well the generalization error in practice. Capitalizing on the successful concept of model scaling (e.g., width, depth), we are able to simultaneously construct such a form and specify the exact models which can attain it across model/data scales. Our construction follows insights ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12673","kind":"arxiv","version":2},"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/1909.12673/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":"1909.12673","created_at":"2026-07-05T00:27:32.955082+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12673v2","created_at":"2026-07-05T00:27:32.955082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12673","created_at":"2026-07-05T00:27:32.955082+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4WMOLK44NXA","created_at":"2026-07-05T00:27:32.955082+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4WMOLK44NXAZ3GP","created_at":"2026-07-05T00:27:32.955082+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4WMOLK4","created_at":"2026-07-05T00:27:32.955082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06725","citing_title":"Compute-Optimal Network Design for Echocardiography Myocardial Segmentation and Perfusion Quantification using Neural Scaling Laws","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26248","citing_title":"Unified Neural Scaling Laws","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27989","citing_title":"Law of Neural Interaction: Depth-Width Shape, Interaction Efficiency, and Generalization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23198","citing_title":"Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15551","citing_title":"Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2405.07987","citing_title":"The Platonic Representation Hypothesis","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2010.14701","citing_title":"Scaling Laws for Autoregressive Generative Modeling","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08297","citing_title":"A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":243,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2001.08361","citing_title":"Scaling Laws for Neural Language Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL","json":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL.json","graph_json":"https://pith.science/api/pith-number/G4WMOLK44NXAZ3GPGJWHMMK3AL/graph.json","events_json":"https://pith.science/api/pith-number/G4WMOLK44NXAZ3GPGJWHMMK3AL/events.json","paper":"https://pith.science/paper/G4WMOLK4"},"agent_actions":{"view_html":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL","download_json":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL.json","view_paper":"https://pith.science/paper/G4WMOLK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12673&json=true","fetch_graph":"https://pith.science/api/pith-number/G4WMOLK44NXAZ3GPGJWHMMK3AL/graph.json","fetch_events":"https://pith.science/api/pith-number/G4WMOLK44NXAZ3GPGJWHMMK3AL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL/action/storage_attestation","attest_author":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL/action/author_attestation","sign_citation":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL/action/citation_signature","submit_replication":"https://pith.science/pith/G4WMOLK44NXAZ3GPGJWHMMK3AL/action/replication_record"}},"created_at":"2026-07-05T00:27:32.955082+00:00","updated_at":"2026-07-05T00:27:32.955082+00:00"}