{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2KTZEOTTQ2VFBVYTOJNWVAXD3Z","short_pith_number":"pith:2KTZEOTT","schema_version":"1.0","canonical_sha256":"d2a7923a7386aa50d713725b6a82e3de7c3a6e8390c83a63f137db41a134cc01","source":{"kind":"arxiv","id":"2111.13171","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.GN","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Lou, Leonidas Guibas, Tolga Birdal, Umut \\c{S}im\\c{s}ekli","submitted_at":"2021-11-25T17:06:15Z","abstract_excerpt":"Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters. Recently, it has been shown that the trajectories of iterative optimization algorithms can possess fractal structures, and their generalization error can be formally linked to the complexity of such fractals. This complexity is measured by the fractal's intrinsic dimension, a quantity usually much smaller than the number of parameters in the network. Even though this perspective provides an explanation for why overparametrized ne"},"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":"2111.13171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T17:06:15Z","cross_cats_sorted":["cs.AI","cs.CV","math.GN","stat.ML"],"title_canon_sha256":"d225fe619ebf2dad362e6d7c03992c6b098dbf635d0ed399fd05835924fce399","abstract_canon_sha256":"397a2fa2b3d8260b06aa63f9300a745ca2b89aa09f179bdebeb028dc4582288f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:18.151588Z","signature_b64":"u29s+pALQt5AJ7tjqYDjqrJRuZDrdU10WAwGgpXsHT8JklBNEADmq6Kp6Wd8iLE/fX89tmXaYARkgVNc9yrcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a7923a7386aa50d713725b6a82e3de7c3a6e8390c83a63f137db41a134cc01","last_reissued_at":"2026-07-05T03:35:18.151202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:18.151202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.GN","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Lou, Leonidas Guibas, Tolga Birdal, Umut \\c{S}im\\c{s}ekli","submitted_at":"2021-11-25T17:06:15Z","abstract_excerpt":"Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters. Recently, it has been shown that the trajectories of iterative optimization algorithms can possess fractal structures, and their generalization error can be formally linked to the complexity of such fractals. This complexity is measured by the fractal's intrinsic dimension, a quantity usually much smaller than the number of parameters in the network. Even though this perspective provides an explanation for why overparametrized ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13171","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/2111.13171/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":"2111.13171","created_at":"2026-07-05T03:35:18.151258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13171v1","created_at":"2026-07-05T03:35:18.151258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13171","created_at":"2026-07-05T03:35:18.151258+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KTZEOTTQ2VF","created_at":"2026-07-05T03:35:18.151258+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KTZEOTTQ2VFBVYT","created_at":"2026-07-05T03:35:18.151258+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KTZEOTT","created_at":"2026-07-05T03:35:18.151258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z","json":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z.json","graph_json":"https://pith.science/api/pith-number/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/graph.json","events_json":"https://pith.science/api/pith-number/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/events.json","paper":"https://pith.science/paper/2KTZEOTT"},"agent_actions":{"view_html":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z","download_json":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z.json","view_paper":"https://pith.science/paper/2KTZEOTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13171&json=true","fetch_graph":"https://pith.science/api/pith-number/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/action/storage_attestation","attest_author":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/action/author_attestation","sign_citation":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/action/citation_signature","submit_replication":"https://pith.science/pith/2KTZEOTTQ2VFBVYTOJNWVAXD3Z/action/replication_record"}},"created_at":"2026-07-05T03:35:18.151258+00:00","updated_at":"2026-07-05T03:35:18.151258+00:00"}