{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7DITFT7RG37UUHR5JBGUYFZMUL","short_pith_number":"pith:7DITFT7R","schema_version":"1.0","canonical_sha256":"f8d132cff136ff4a1e3d484d4c172ca2dd251e27620c620b387982d03727f4e2","source":{"kind":"arxiv","id":"1906.08255","version":1},"attestation_state":"computed","paper":{"title":"Training on test data: Removing near duplicates in Fashion-MNIST","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Geier","submitted_at":"2019-06-19T22:09:47Z","abstract_excerpt":"MNIST and Fashion MNIST are extremely popular for testing in the machine learning space. Fashion MNIST improves on MNIST by introducing a harder problem, increasing the diversity of testing sets, and more accurately representing a modern computer vision task. In order to increase the data quality of FashionMNIST, this paper investigates near duplicate images between training and testing sets. Near-duplicates between testing and training sets artificially increase the testing accuracy of machine learning models. This paper identifies near-duplicate images in Fashion MNIST and proposes a dataset"},"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":"1906.08255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:09:47Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3f7035360214362670b5c32e2cacd99508a1f7247001d60e76d870e0c2849ed2","abstract_canon_sha256":"ee5d89a852b2fef20a19630bef96c18a7cb6b5989f54d330d7fd39e532c1eb88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.938107Z","signature_b64":"0TtTI7wGD6L1bqAIf8xtcRu3Dpl9MxjUw7ivqxQEJwXDwgfjLGoMgyx64PkI6A9BExUAbj5XkBP6n9DRWV2mDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8d132cff136ff4a1e3d484d4c172ca2dd251e27620c620b387982d03727f4e2","last_reissued_at":"2026-05-17T23:42:52.937421Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.937421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training on test data: Removing near duplicates in Fashion-MNIST","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Geier","submitted_at":"2019-06-19T22:09:47Z","abstract_excerpt":"MNIST and Fashion MNIST are extremely popular for testing in the machine learning space. Fashion MNIST improves on MNIST by introducing a harder problem, increasing the diversity of testing sets, and more accurately representing a modern computer vision task. In order to increase the data quality of FashionMNIST, this paper investigates near duplicate images between training and testing sets. Near-duplicates between testing and training sets artificially increase the testing accuracy of machine learning models. This paper identifies near-duplicate images in Fashion MNIST and proposes a dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08255","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":"1906.08255","created_at":"2026-05-17T23:42:52.937529+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08255v1","created_at":"2026-05-17T23:42:52.937529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08255","created_at":"2026-05-17T23:42:52.937529+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DITFT7RG37U","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DITFT7RG37UUHR5","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DITFT7R","created_at":"2026-05-18T12:33:12.712433+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/7DITFT7RG37UUHR5JBGUYFZMUL","json":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL.json","graph_json":"https://pith.science/api/pith-number/7DITFT7RG37UUHR5JBGUYFZMUL/graph.json","events_json":"https://pith.science/api/pith-number/7DITFT7RG37UUHR5JBGUYFZMUL/events.json","paper":"https://pith.science/paper/7DITFT7R"},"agent_actions":{"view_html":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL","download_json":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL.json","view_paper":"https://pith.science/paper/7DITFT7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08255&json=true","fetch_graph":"https://pith.science/api/pith-number/7DITFT7RG37UUHR5JBGUYFZMUL/graph.json","fetch_events":"https://pith.science/api/pith-number/7DITFT7RG37UUHR5JBGUYFZMUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/action/storage_attestation","attest_author":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/action/author_attestation","sign_citation":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/action/citation_signature","submit_replication":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/action/replication_record"}},"created_at":"2026-05-17T23:42:52.937529+00:00","updated_at":"2026-05-17T23:42:52.937529+00:00"}