{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:URINQU2EAACZ6XH6OG7I5XCGSC","short_pith_number":"pith:URINQU2E","schema_version":"1.0","canonical_sha256":"a450d8534400059f5cfe71be8edc4690ada595b3cc8011126a650158897cdebf","source":{"kind":"arxiv","id":"2012.03531","version":1},"attestation_state":"computed","paper":{"title":"Why Unsupervised Deep Networks Generalize","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anita de Mello Koch, Ellen de Mello Koch, Robert de Mello Koch","submitted_at":"2020-12-07T08:45:20Z","abstract_excerpt":"Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very few parameters, despite the fact that naive estimates suggest otherwise. Our central hypothesis is that the mechanisms behind the renormalization group are also at work in deep learning, and that this leads to a resolution of the generalization puzzle. We show detailed quantitative evidence that proves the hypothesis for an RBM, by showing that the trained RBM"},"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":"2012.03531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-07T08:45:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"dc995be79feedf364b1daede4ccc0a24e6806a1160e8c7eff77008043d93d121","abstract_canon_sha256":"05735935108c876ea090928c403373aac7cd1fbe271609f837a0ecbc81da6784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:30.662874Z","signature_b64":"p27jHhdll9y0mQzr5LRlQI8Twv2+8qdi5Ar4rHBiku+K1ZFqz0H0Zj5Di4p1KIBFzGJWCjOzNM1rAvGDLQLQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a450d8534400059f5cfe71be8edc4690ada595b3cc8011126a650158897cdebf","last_reissued_at":"2026-07-05T01:57:30.662426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:30.662426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Unsupervised Deep Networks Generalize","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anita de Mello Koch, Ellen de Mello Koch, Robert de Mello Koch","submitted_at":"2020-12-07T08:45:20Z","abstract_excerpt":"Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very few parameters, despite the fact that naive estimates suggest otherwise. Our central hypothesis is that the mechanisms behind the renormalization group are also at work in deep learning, and that this leads to a resolution of the generalization puzzle. We show detailed quantitative evidence that proves the hypothesis for an RBM, by showing that the trained RBM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03531","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/2012.03531/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":"2012.03531","created_at":"2026-07-05T01:57:30.662481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.03531v1","created_at":"2026-07-05T01:57:30.662481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03531","created_at":"2026-07-05T01:57:30.662481+00:00"},{"alias_kind":"pith_short_12","alias_value":"URINQU2EAACZ","created_at":"2026-07-05T01:57:30.662481+00:00"},{"alias_kind":"pith_short_16","alias_value":"URINQU2EAACZ6XH6","created_at":"2026-07-05T01:57:30.662481+00:00"},{"alias_kind":"pith_short_8","alias_value":"URINQU2E","created_at":"2026-07-05T01:57:30.662481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12700","citing_title":"A Two-Phase Perspective on Deep Learning Dynamics","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC","json":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC.json","graph_json":"https://pith.science/api/pith-number/URINQU2EAACZ6XH6OG7I5XCGSC/graph.json","events_json":"https://pith.science/api/pith-number/URINQU2EAACZ6XH6OG7I5XCGSC/events.json","paper":"https://pith.science/paper/URINQU2E"},"agent_actions":{"view_html":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC","download_json":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC.json","view_paper":"https://pith.science/paper/URINQU2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.03531&json=true","fetch_graph":"https://pith.science/api/pith-number/URINQU2EAACZ6XH6OG7I5XCGSC/graph.json","fetch_events":"https://pith.science/api/pith-number/URINQU2EAACZ6XH6OG7I5XCGSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC/action/storage_attestation","attest_author":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC/action/author_attestation","sign_citation":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC/action/citation_signature","submit_replication":"https://pith.science/pith/URINQU2EAACZ6XH6OG7I5XCGSC/action/replication_record"}},"created_at":"2026-07-05T01:57:30.662481+00:00","updated_at":"2026-07-05T01:57:30.662481+00:00"}