{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YONTOAG2ZLAAKMBZRBPN4QBQSL","short_pith_number":"pith:YONTOAG2","schema_version":"1.0","canonical_sha256":"c39b3700dacac0053039885ede403092de92178a55cd29f29fe5474d8c8a560e","source":{"kind":"arxiv","id":"2306.14975","version":3},"attestation_state":"computed","paper":{"title":"The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","hep-th","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Noam Levi, Yaron Oz","submitted_at":"2023-06-26T18:01:47Z","abstract_excerpt":"We study universal traits which emerge both in real-world complex datasets, as well as in artificially generated ones. Our approach is to analogize data to a physical system and employ tools from statistical physics and Random Matrix Theory (RMT) to reveal their underlying structure. We focus on the feature-feature covariance matrix, analyzing both its local and global eigenvalue statistics. Our main observations are: (i) The power-law scalings that the bulk of its eigenvalues exhibit are vastly different for uncorrelated normally distributed data compared to real-world data, (ii) this scaling"},"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":"2306.14975","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-26T18:01:47Z","cross_cats_sorted":["cond-mat.dis-nn","hep-th","math.PR","stat.ML"],"title_canon_sha256":"616ee4291c5d0151a14413cd65a2b9f6de6a19f33e8892a4c631aae79ff8c037","abstract_canon_sha256":"639bffa7ffa8e657d726eda5af807f8e4a1ecbe7e25097570d0f56259346789b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:32.721381Z","signature_b64":"OUI4bVkGf2uNZF58VXQuOTU2m8uwrtlOcivO9PpA1/SHW3FWWGx/9fjACmuUK64YnuJWVDRh9A1sA1sZlk9pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c39b3700dacac0053039885ede403092de92178a55cd29f29fe5474d8c8a560e","last_reissued_at":"2026-07-05T08:04:32.720959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:32.720959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","hep-th","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Noam Levi, Yaron Oz","submitted_at":"2023-06-26T18:01:47Z","abstract_excerpt":"We study universal traits which emerge both in real-world complex datasets, as well as in artificially generated ones. Our approach is to analogize data to a physical system and employ tools from statistical physics and Random Matrix Theory (RMT) to reveal their underlying structure. We focus on the feature-feature covariance matrix, analyzing both its local and global eigenvalue statistics. Our main observations are: (i) The power-law scalings that the bulk of its eigenvalues exhibit are vastly different for uncorrelated normally distributed data compared to real-world data, (ii) this scaling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14975","kind":"arxiv","version":3},"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/2306.14975/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":"2306.14975","created_at":"2026-07-05T08:04:32.721013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14975v3","created_at":"2026-07-05T08:04:32.721013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14975","created_at":"2026-07-05T08:04:32.721013+00:00"},{"alias_kind":"pith_short_12","alias_value":"YONTOAG2ZLAA","created_at":"2026-07-05T08:04:32.721013+00:00"},{"alias_kind":"pith_short_16","alias_value":"YONTOAG2ZLAAKMBZ","created_at":"2026-07-05T08:04:32.721013+00:00"},{"alias_kind":"pith_short_8","alias_value":"YONTOAG2","created_at":"2026-07-05T08:04:32.721013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28486","citing_title":"Spectral phase transitions and trainability in neural network learning dynamics","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2405.00592","citing_title":"Scaling and renormalization in high-dimensional regression","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21715","citing_title":"DNNs, Dataset Statistics, and Correlation Functions","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02415","citing_title":"Generative models on phase space","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL","json":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL.json","graph_json":"https://pith.science/api/pith-number/YONTOAG2ZLAAKMBZRBPN4QBQSL/graph.json","events_json":"https://pith.science/api/pith-number/YONTOAG2ZLAAKMBZRBPN4QBQSL/events.json","paper":"https://pith.science/paper/YONTOAG2"},"agent_actions":{"view_html":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL","download_json":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL.json","view_paper":"https://pith.science/paper/YONTOAG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14975&json=true","fetch_graph":"https://pith.science/api/pith-number/YONTOAG2ZLAAKMBZRBPN4QBQSL/graph.json","fetch_events":"https://pith.science/api/pith-number/YONTOAG2ZLAAKMBZRBPN4QBQSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL/action/storage_attestation","attest_author":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL/action/author_attestation","sign_citation":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL/action/citation_signature","submit_replication":"https://pith.science/pith/YONTOAG2ZLAAKMBZRBPN4QBQSL/action/replication_record"}},"created_at":"2026-07-05T08:04:32.721013+00:00","updated_at":"2026-07-05T08:04:32.721013+00:00"}