{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQCEZEBTHDCXYAX3O67OUJM56F","short_pith_number":"pith:DQCEZEBT","schema_version":"1.0","canonical_sha256":"1c044c903338c57c02fb77beea259df175b266315d40d9c05916379386478a0e","source":{"kind":"arxiv","id":"2402.01092","version":4},"attestation_state":"computed","paper":{"title":"A Dynamical Model of Neural Scaling Laws","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan","submitted_at":"2024-02-02T01:41:38Z","abstract_excerpt":"On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is the compute-optimal scaling law, which reports the performance as a function of units of compute when choosing model sizes optimally. We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. This reproduces many observations about neural scaling laws. First, our model makes a prediction about "},"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":"2402.01092","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-02T01:41:38Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"5769ff445ed3db60860afda2d0dbd2d40078476f2bcdb34d3988b736b56cc297","abstract_canon_sha256":"86683bdc1c5e3a8297f6105c1f0e8711123e3ac2cd92d8a12934973c64b08986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:41.352074Z","signature_b64":"5MklduA59qC0spZMiaErtdau42YsJF1ZpQ36GaMXERNc9vp4U6zAmd8FA0pUcrgiJuyV2emgERIT2b78aKvFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c044c903338c57c02fb77beea259df175b266315d40d9c05916379386478a0e","last_reissued_at":"2026-07-05T08:35:41.351567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:41.351567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dynamical Model of Neural Scaling Laws","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan","submitted_at":"2024-02-02T01:41:38Z","abstract_excerpt":"On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is the compute-optimal scaling law, which reports the performance as a function of units of compute when choosing model sizes optimally. We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. This reproduces many observations about neural scaling laws. First, our model makes a prediction about "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01092","kind":"arxiv","version":4},"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/2402.01092/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":"2402.01092","created_at":"2026-07-05T08:35:41.351628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01092v4","created_at":"2026-07-05T08:35:41.351628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01092","created_at":"2026-07-05T08:35:41.351628+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQCEZEBTHDCX","created_at":"2026-07-05T08:35:41.351628+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQCEZEBTHDCXYAX3","created_at":"2026-07-05T08:35:41.351628+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQCEZEBT","created_at":"2026-07-05T08:35:41.351628+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":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12360","citing_title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07247","citing_title":"Theory of learning of high-dimensional controlled non-linear dynamical systems (I): models and methods","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27989","citing_title":"Law of Neural Interaction: Depth-Width Shape, Interaction Efficiency, and Generalization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07870","citing_title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26554","citing_title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21691","citing_title":"There Will Be a Scientific Theory of Deep Learning","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07870","citing_title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F","json":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F.json","graph_json":"https://pith.science/api/pith-number/DQCEZEBTHDCXYAX3O67OUJM56F/graph.json","events_json":"https://pith.science/api/pith-number/DQCEZEBTHDCXYAX3O67OUJM56F/events.json","paper":"https://pith.science/paper/DQCEZEBT"},"agent_actions":{"view_html":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F","download_json":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F.json","view_paper":"https://pith.science/paper/DQCEZEBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01092&json=true","fetch_graph":"https://pith.science/api/pith-number/DQCEZEBTHDCXYAX3O67OUJM56F/graph.json","fetch_events":"https://pith.science/api/pith-number/DQCEZEBTHDCXYAX3O67OUJM56F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F/action/storage_attestation","attest_author":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F/action/author_attestation","sign_citation":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F/action/citation_signature","submit_replication":"https://pith.science/pith/DQCEZEBTHDCXYAX3O67OUJM56F/action/replication_record"}},"created_at":"2026-07-05T08:35:41.351628+00:00","updated_at":"2026-07-05T08:35:41.351628+00:00"}