{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:QOMYPIRWKKTWOJFNHSH7JB75LK","short_pith_number":"pith:QOMYPIRW","schema_version":"1.0","canonical_sha256":"839987a23652a76724ad3c8ff487fd5aac1f306f3527e7526f1fa2c50fe86fdb","source":{"kind":"arxiv","id":"1102.0183","version":1},"attestation_state":"computed","paper":{"title":"High-Performance Neural Networks for Visual Object Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Dan C. Cire\\c{s}an, Jonathan Masci, J\\\"urgen Schmidhuber, Luca M. Gambardella, Ueli Meier","submitted_at":"2011-02-01T15:34:43Z","abstract_excerpt":"We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better than more shallow ones. Learning is surprisingly rapid. NORB is completely trained within five epochs. "},"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":"1102.0183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-01T15:34:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"3c5b288f8ad181c304c77b2f7ddfcd227e73dc041e63ad2ebdb821e13d86e864","abstract_canon_sha256":"38b635b77fc95eee46000f8537e5b7441722d91188176d3ea2642859cfdf777a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:30:13.021347Z","signature_b64":"pqLT1ur0i/hxJvcssaKNbCGnyQ3uzTLN3BxdVpvFmExG45O2C6Fl3vzcuqFZGuhKy5c+/pt2F4tfwNXo74yADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"839987a23652a76724ad3c8ff487fd5aac1f306f3527e7526f1fa2c50fe86fdb","last_reissued_at":"2026-05-18T04:30:13.020708Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:30:13.020708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Performance Neural Networks for Visual Object Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Dan C. Cire\\c{s}an, Jonathan Masci, J\\\"urgen Schmidhuber, Luca M. Gambardella, Ueli Meier","submitted_at":"2011-02-01T15:34:43Z","abstract_excerpt":"We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better than more shallow ones. Learning is surprisingly rapid. NORB is completely trained within five epochs. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.0183","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":""},"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":"1102.0183","created_at":"2026-05-18T04:30:13.020780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1102.0183v1","created_at":"2026-05-18T04:30:13.020780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.0183","created_at":"2026-05-18T04:30:13.020780+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOMYPIRWKKTW","created_at":"2026-05-18T12:26:39.201973+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOMYPIRWKKTWOJFN","created_at":"2026-05-18T12:26:39.201973+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOMYPIRW","created_at":"2026-05-18T12:26:39.201973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12792","citing_title":"SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK","json":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK.json","graph_json":"https://pith.science/api/pith-number/QOMYPIRWKKTWOJFNHSH7JB75LK/graph.json","events_json":"https://pith.science/api/pith-number/QOMYPIRWKKTWOJFNHSH7JB75LK/events.json","paper":"https://pith.science/paper/QOMYPIRW"},"agent_actions":{"view_html":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK","download_json":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK.json","view_paper":"https://pith.science/paper/QOMYPIRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1102.0183&json=true","fetch_graph":"https://pith.science/api/pith-number/QOMYPIRWKKTWOJFNHSH7JB75LK/graph.json","fetch_events":"https://pith.science/api/pith-number/QOMYPIRWKKTWOJFNHSH7JB75LK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK/action/storage_attestation","attest_author":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK/action/author_attestation","sign_citation":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK/action/citation_signature","submit_replication":"https://pith.science/pith/QOMYPIRWKKTWOJFNHSH7JB75LK/action/replication_record"}},"created_at":"2026-05-18T04:30:13.020780+00:00","updated_at":"2026-05-18T04:30:13.020780+00:00"}