{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FSD2AS6RUYUJM2E5J3V5LCCAPP","short_pith_number":"pith:FSD2AS6R","schema_version":"1.0","canonical_sha256":"2c87a04bd1a62896689d4eebd588407bf4f8807202835178310258abe23c26ec","source":{"kind":"arxiv","id":"2408.00082","version":1},"attestation_state":"computed","paper":{"title":"TASI Lectures on Physics for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ph"],"primary_cat":"hep-th","authors_text":"Jim Halverson","submitted_at":"2024-07-31T18:00:22Z","abstract_excerpt":"These notes are based on lectures I gave at TASI 2024 on Physics for Machine Learning. The focus is on neural network theory, organized according to network expressivity, statistics, and dynamics. I present classic results such as the universal approximation theorem and neural network / Gaussian process correspondence, and also more recent results such as the neural tangent kernel, feature learning with the maximal update parameterization, and Kolmogorov-Arnold networks. The exposition on neural network theory emphasizes a field theoretic perspective familiar to theoretical physicists. I elabo"},"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":"2408.00082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-th","submitted_at":"2024-07-31T18:00:22Z","cross_cats_sorted":["cs.LG","hep-ph"],"title_canon_sha256":"02a5e7d398263e6cbf931347d982d59003ede43e56661bfbf8ced2d142a9a3e1","abstract_canon_sha256":"ac0341bbac85114476ad6026d3a74ed2dbf8aa34f5364ce4232cc3991b4b1cb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:44.925485Z","signature_b64":"v5Pd98WcoAQ7bWl7oQZmK7q+R/hDdY60lMUhLGRHZURWHt+FCnVIh8MlCB9pQZ6hHSAXCtR1FU7tclWucm3bBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c87a04bd1a62896689d4eebd588407bf4f8807202835178310258abe23c26ec","last_reissued_at":"2026-07-05T08:50:44.925070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:44.925070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TASI Lectures on Physics for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ph"],"primary_cat":"hep-th","authors_text":"Jim Halverson","submitted_at":"2024-07-31T18:00:22Z","abstract_excerpt":"These notes are based on lectures I gave at TASI 2024 on Physics for Machine Learning. The focus is on neural network theory, organized according to network expressivity, statistics, and dynamics. I present classic results such as the universal approximation theorem and neural network / Gaussian process correspondence, and also more recent results such as the neural tangent kernel, feature learning with the maximal update parameterization, and Kolmogorov-Arnold networks. The exposition on neural network theory emphasizes a field theoretic perspective familiar to theoretical physicists. I elabo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00082","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/2408.00082/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":"2408.00082","created_at":"2026-07-05T08:50:44.925125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00082v1","created_at":"2026-07-05T08:50:44.925125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00082","created_at":"2026-07-05T08:50:44.925125+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSD2AS6RUYUJ","created_at":"2026-07-05T08:50:44.925125+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSD2AS6RUYUJM2E5","created_at":"2026-07-05T08:50:44.925125+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSD2AS6R","created_at":"2026-07-05T08:50:44.925125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02313","citing_title":"Topological Effects in Neural Network Field Theory","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12488","citing_title":"Anomalies in Neural Network Field Theory","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27050","citing_title":"Optimal Architecture and Fundamental Bounds in Neural Network Field Theory","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP","json":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP.json","graph_json":"https://pith.science/api/pith-number/FSD2AS6RUYUJM2E5J3V5LCCAPP/graph.json","events_json":"https://pith.science/api/pith-number/FSD2AS6RUYUJM2E5J3V5LCCAPP/events.json","paper":"https://pith.science/paper/FSD2AS6R"},"agent_actions":{"view_html":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP","download_json":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP.json","view_paper":"https://pith.science/paper/FSD2AS6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00082&json=true","fetch_graph":"https://pith.science/api/pith-number/FSD2AS6RUYUJM2E5J3V5LCCAPP/graph.json","fetch_events":"https://pith.science/api/pith-number/FSD2AS6RUYUJM2E5J3V5LCCAPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP/action/storage_attestation","attest_author":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP/action/author_attestation","sign_citation":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP/action/citation_signature","submit_replication":"https://pith.science/pith/FSD2AS6RUYUJM2E5J3V5LCCAPP/action/replication_record"}},"created_at":"2026-07-05T08:50:44.925125+00:00","updated_at":"2026-07-05T08:50:44.925125+00:00"}