{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:REDJBZJJS72W76W3ZZNA4UBLRF","short_pith_number":"pith:REDJBZJJ","schema_version":"1.0","canonical_sha256":"890690e52997f56ffadbce5a0e502b89674575514993b4150d8c3bd2416ae22e","source":{"kind":"arxiv","id":"2205.10760","version":4},"attestation_state":"computed","paper":{"title":"CNNs Avoid Curse of Dimensionality by Learning on Patches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jason Bunk, Shivkumar Chandrasekaran, Vamshi C. Madala","submitted_at":"2022-05-22T06:22:27Z","abstract_excerpt":"Despite the success of convolutional neural networks (CNNs) in numerous computer vision tasks and their extraordinary generalization performances, several attempts to predict the generalization errors of CNNs have only been limited to a posteriori analyses thus far. A priori theories explaining the generalization performances of deep neural networks have mostly ignored the convolutionality aspect and do not specify why CNNs are able to seemingly overcome curse of dimensionality on computer vision tasks like image classification where the image dimensions are in thousands. Our work attempts to "},"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":"2205.10760","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-22T06:22:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"57cf67300b818fa16002140d7b3b817cb7d7b727aa0d4dfde26ac52ff09420b1","abstract_canon_sha256":"23dcd30880521df10a4be919ab10987c2463e95e14ff2feb704691d45ee9e31c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:40.906367Z","signature_b64":"+X0hLa1XeBlPJXBb2jFfsK7tgssAd23E13sT6jGwJ0t9WPma76+qeoSBu/891hESHMW9g5eSmm63BZpDRl2pCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"890690e52997f56ffadbce5a0e502b89674575514993b4150d8c3bd2416ae22e","last_reissued_at":"2026-07-05T11:37:40.905157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:40.905157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CNNs Avoid Curse of Dimensionality by Learning on Patches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jason Bunk, Shivkumar Chandrasekaran, Vamshi C. Madala","submitted_at":"2022-05-22T06:22:27Z","abstract_excerpt":"Despite the success of convolutional neural networks (CNNs) in numerous computer vision tasks and their extraordinary generalization performances, several attempts to predict the generalization errors of CNNs have only been limited to a posteriori analyses thus far. A priori theories explaining the generalization performances of deep neural networks have mostly ignored the convolutionality aspect and do not specify why CNNs are able to seemingly overcome curse of dimensionality on computer vision tasks like image classification where the image dimensions are in thousands. Our work attempts to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10760","kind":"arxiv","version":4},"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/2205.10760/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":"2205.10760","created_at":"2026-07-05T11:37:40.905685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10760v4","created_at":"2026-07-05T11:37:40.905685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10760","created_at":"2026-07-05T11:37:40.905685+00:00"},{"alias_kind":"pith_short_12","alias_value":"REDJBZJJS72W","created_at":"2026-07-05T11:37:40.905685+00:00"},{"alias_kind":"pith_short_16","alias_value":"REDJBZJJS72W76W3","created_at":"2026-07-05T11:37:40.905685+00:00"},{"alias_kind":"pith_short_8","alias_value":"REDJBZJJ","created_at":"2026-07-05T11:37:40.905685+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/REDJBZJJS72W76W3ZZNA4UBLRF","json":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF.json","graph_json":"https://pith.science/api/pith-number/REDJBZJJS72W76W3ZZNA4UBLRF/graph.json","events_json":"https://pith.science/api/pith-number/REDJBZJJS72W76W3ZZNA4UBLRF/events.json","paper":"https://pith.science/paper/REDJBZJJ"},"agent_actions":{"view_html":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF","download_json":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF.json","view_paper":"https://pith.science/paper/REDJBZJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10760&json=true","fetch_graph":"https://pith.science/api/pith-number/REDJBZJJS72W76W3ZZNA4UBLRF/graph.json","fetch_events":"https://pith.science/api/pith-number/REDJBZJJS72W76W3ZZNA4UBLRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF/action/storage_attestation","attest_author":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF/action/author_attestation","sign_citation":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF/action/citation_signature","submit_replication":"https://pith.science/pith/REDJBZJJS72W76W3ZZNA4UBLRF/action/replication_record"}},"created_at":"2026-07-05T11:37:40.905685+00:00","updated_at":"2026-07-05T11:37:40.905685+00:00"}