{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UPET4LCN3O2JYKXJHUAVNYOO57","short_pith_number":"pith:UPET4LCN","schema_version":"1.0","canonical_sha256":"a3c93e2c4ddbb49c2ae93d0156e1ceefd536dc79b8d617d0424806fc0b79d33d","source":{"kind":"arxiv","id":"2406.02234","version":2},"attestation_state":"computed","paper":{"title":"On the Limitations of Fractal Dimension as a Measure of Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthea Monod, Charlie B. Tan, In\\'es Garc\\'ia-Redondo, Michael M. Bronstein, Qiquan Wang","submitted_at":"2024-06-04T11:56:19Z","abstract_excerpt":"Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. There is a recent and growing body of literature that proposes the framework of fractals to model optimization trajectories of neural networks, motivating generalization bounds and measures based on the fractal dimension of the trajectory. Notably, the persistent homology dimension has been proposed to correlate with the generalization gap. This paper performs an empirical evaluation of these persistent homology-based generalization measures, with "},"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":"2406.02234","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T11:56:19Z","cross_cats_sorted":["cs.AI","math.DS","stat.ML"],"title_canon_sha256":"8b704d2f8c1989a2ef216aa5b404d99f68d4b177b4682fe3cd971b87e2c0a03b","abstract_canon_sha256":"6fd96a23074139621bd2e46215f74ac171c83ee317f147c60d61d058cfd8cd49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:29.926540Z","signature_b64":"l0UkPzUhJWwWhRCQliQtYGl4cdmgDAf7NQ1JD9i2lI8b67jsvnde5nfooLElttZhKUY/LD2+RRwJDSCCxOfWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3c93e2c4ddbb49c2ae93d0156e1ceefd536dc79b8d617d0424806fc0b79d33d","last_reissued_at":"2026-07-05T09:29:29.926063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:29.926063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Limitations of Fractal Dimension as a Measure of Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthea Monod, Charlie B. Tan, In\\'es Garc\\'ia-Redondo, Michael M. Bronstein, Qiquan Wang","submitted_at":"2024-06-04T11:56:19Z","abstract_excerpt":"Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. There is a recent and growing body of literature that proposes the framework of fractals to model optimization trajectories of neural networks, motivating generalization bounds and measures based on the fractal dimension of the trajectory. Notably, the persistent homology dimension has been proposed to correlate with the generalization gap. This paper performs an empirical evaluation of these persistent homology-based generalization measures, with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02234","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/2406.02234/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":"2406.02234","created_at":"2026-07-05T09:29:29.926115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02234v2","created_at":"2026-07-05T09:29:29.926115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02234","created_at":"2026-07-05T09:29:29.926115+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPET4LCN3O2J","created_at":"2026-07-05T09:29:29.926115+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPET4LCN3O2JYKXJ","created_at":"2026-07-05T09:29:29.926115+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPET4LCN","created_at":"2026-07-05T09:29:29.926115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18598","citing_title":"Pointwise Generalization in Deep Neural Networks","ref_index":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57","json":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57.json","graph_json":"https://pith.science/api/pith-number/UPET4LCN3O2JYKXJHUAVNYOO57/graph.json","events_json":"https://pith.science/api/pith-number/UPET4LCN3O2JYKXJHUAVNYOO57/events.json","paper":"https://pith.science/paper/UPET4LCN"},"agent_actions":{"view_html":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57","download_json":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57.json","view_paper":"https://pith.science/paper/UPET4LCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02234&json=true","fetch_graph":"https://pith.science/api/pith-number/UPET4LCN3O2JYKXJHUAVNYOO57/graph.json","fetch_events":"https://pith.science/api/pith-number/UPET4LCN3O2JYKXJHUAVNYOO57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57/action/storage_attestation","attest_author":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57/action/author_attestation","sign_citation":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57/action/citation_signature","submit_replication":"https://pith.science/pith/UPET4LCN3O2JYKXJHUAVNYOO57/action/replication_record"}},"created_at":"2026-07-05T09:29:29.926115+00:00","updated_at":"2026-07-05T09:29:29.926115+00:00"}