{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IW3S67AXQSCE5VQVBWANTISSST","short_pith_number":"pith:IW3S67AX","schema_version":"1.0","canonical_sha256":"45b72f7c1784844ed6150d80d9a25294ecd0b3621bdcf21ed153413512ff9e8b","source":{"kind":"arxiv","id":"2008.10400","version":2},"attestation_state":"computed","paper":{"title":"An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Heerin Yang, Jungmin So, MinJun Lee, Sanghyeon An, Sanglee Park","submitted_at":"2020-08-12T09:27:05Z","abstract_excerpt":"We report that a very high accuracy on the MNIST test set can be achieved by using simple convolutional neural network (CNN) models. We use three different models with 3x3, 5x5, and 7x7 kernel size in the convolution layers. Each model consists of a set of convolution layers followed by a single fully connected layer. Every convolution layer uses batch normalization and ReLU activation, and pooling is not used. Rotation and translation is used to augment training data, which is frequently used in most image classification tasks. A majority voting using the three models independently trained on"},"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":"2008.10400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-12T09:27:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8045866d6f5162ac2843899a293cc90c4c9f09ae0634cd0fa64a2ac7d2f9ed47","abstract_canon_sha256":"8889cd1bac84add97323e67a88a043969e6cd41c9d1e64683a306c1402cb9b74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:00.533949Z","signature_b64":"6v/moer1B8iQSq7FN/F+tJFE5ylWBhiIzclBWw1nO8S/SVxVYLd/AhkGN6EgkTIKwHyfwkXBR2T2Z8J2qnczDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b72f7c1784844ed6150d80d9a25294ecd0b3621bdcf21ed153413512ff9e8b","last_reissued_at":"2026-07-05T01:40:00.533442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:00.533442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Heerin Yang, Jungmin So, MinJun Lee, Sanghyeon An, Sanglee Park","submitted_at":"2020-08-12T09:27:05Z","abstract_excerpt":"We report that a very high accuracy on the MNIST test set can be achieved by using simple convolutional neural network (CNN) models. We use three different models with 3x3, 5x5, and 7x7 kernel size in the convolution layers. Each model consists of a set of convolution layers followed by a single fully connected layer. Every convolution layer uses batch normalization and ReLU activation, and pooling is not used. Rotation and translation is used to augment training data, which is frequently used in most image classification tasks. A majority voting using the three models independently trained on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10400","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/2008.10400/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":"2008.10400","created_at":"2026-07-05T01:40:00.533514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.10400v2","created_at":"2026-07-05T01:40:00.533514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10400","created_at":"2026-07-05T01:40:00.533514+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW3S67AXQSCE","created_at":"2026-07-05T01:40:00.533514+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW3S67AXQSCE5VQV","created_at":"2026-07-05T01:40:00.533514+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW3S67AX","created_at":"2026-07-05T01:40:00.533514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06364","citing_title":"Flow Matching with Arbitrary Auxiliary Paths","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST","json":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST.json","graph_json":"https://pith.science/api/pith-number/IW3S67AXQSCE5VQVBWANTISSST/graph.json","events_json":"https://pith.science/api/pith-number/IW3S67AXQSCE5VQVBWANTISSST/events.json","paper":"https://pith.science/paper/IW3S67AX"},"agent_actions":{"view_html":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST","download_json":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST.json","view_paper":"https://pith.science/paper/IW3S67AX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.10400&json=true","fetch_graph":"https://pith.science/api/pith-number/IW3S67AXQSCE5VQVBWANTISSST/graph.json","fetch_events":"https://pith.science/api/pith-number/IW3S67AXQSCE5VQVBWANTISSST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST/action/storage_attestation","attest_author":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST/action/author_attestation","sign_citation":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST/action/citation_signature","submit_replication":"https://pith.science/pith/IW3S67AXQSCE5VQVBWANTISSST/action/replication_record"}},"created_at":"2026-07-05T01:40:00.533514+00:00","updated_at":"2026-07-05T01:40:00.533514+00:00"}