{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7DITFT7RG37UUHR5JBGUYFZMUL","short_pith_number":"pith:7DITFT7R","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"},"canonical_sha256":"f8d132cff136ff4a1e3d484d4c172ca2dd251e27620c620b387982d03727f4e2","source":{"kind":"arxiv","id":"1906.08255","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08255","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08255v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08255","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"7DITFT7RG37U","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7DITFT7RG37UUHR5","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7DITFT7R","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7DITFT7RG37UUHR5JBGUYFZMUL","target":"record","payload":{"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"},"canonical_sha256":"f8d132cff136ff4a1e3d484d4c172ca2dd251e27620c620b387982d03727f4e2","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"},"source_kind":"arxiv","source_id":"1906.08255","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/9mDFRXW1y4fj8XelpCBTsioAc1CrwsjMwDjozbuRn6/7bMrCjvTf8jIxzk604+yUYMQBzoqgITVKYgdSiMVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:19:56.564185Z"},"content_sha256":"9ff15c1d556d27ef13e84a47585973ecdecc64c823a396521aabb750b7c5081e","schema_version":"1.0","event_id":"sha256:9ff15c1d556d27ef13e84a47585973ecdecc64c823a396521aabb750b7c5081e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7DITFT7RG37UUHR5JBGUYFZMUL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJKPOKGdbKN/PQU3DMtUK9jUSgEVh0wSvSBClfHA12uE2AXVgtjtjD50DLPy6U0n3Ig1IHkhQMLgApbAZY4UCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:19:56.564773Z"},"content_sha256":"6939dc6eec41450dc59c3d9c4fca084a0d7d18049127340adbf3211ab086095a","schema_version":"1.0","event_id":"sha256:6939dc6eec41450dc59c3d9c4fca084a0d7d18049127340adbf3211ab086095a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/bundle.json","state_url":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DITFT7RG37UUHR5JBGUYFZMUL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T02:19:56Z","links":{"resolver":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL","bundle":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/bundle.json","state":"https://pith.science/pith/7DITFT7RG37UUHR5JBGUYFZMUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DITFT7RG37UUHR5JBGUYFZMUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7DITFT7RG37UUHR5JBGUYFZMUL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee5d89a852b2fef20a19630bef96c18a7cb6b5989f54d330d7fd39e532c1eb88","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:09:47Z","title_canon_sha256":"3f7035360214362670b5c32e2cacd99508a1f7247001d60e76d870e0c2849ed2"},"schema_version":"1.0","source":{"id":"1906.08255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08255","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08255v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08255","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"7DITFT7RG37U","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7DITFT7RG37UUHR5","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7DITFT7R","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:6939dc6eec41450dc59c3d9c4fca084a0d7d18049127340adbf3211ab086095a","target":"graph","created_at":"2026-05-17T23:42:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Christopher Geier","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:09:47Z","title":"Training on test data: Removing near duplicates in Fashion-MNIST"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08255","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9ff15c1d556d27ef13e84a47585973ecdecc64c823a396521aabb750b7c5081e","target":"record","created_at":"2026-05-17T23:42:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee5d89a852b2fef20a19630bef96c18a7cb6b5989f54d330d7fd39e532c1eb88","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:09:47Z","title_canon_sha256":"3f7035360214362670b5c32e2cacd99508a1f7247001d60e76d870e0c2849ed2"},"schema_version":"1.0","source":{"id":"1906.08255","kind":"arxiv","version":1}},"canonical_sha256":"f8d132cff136ff4a1e3d484d4c172ca2dd251e27620c620b387982d03727f4e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8d132cff136ff4a1e3d484d4c172ca2dd251e27620c620b387982d03727f4e2","first_computed_at":"2026-05-17T23:42:52.937421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:52.937421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0TtTI7wGD6L1bqAIf8xtcRu3Dpl9MxjUw7ivqxQEJwXDwgfjLGoMgyx64PkI6A9BExUAbj5XkBP6n9DRWV2mDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:52.938107Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ff15c1d556d27ef13e84a47585973ecdecc64c823a396521aabb750b7c5081e","sha256:6939dc6eec41450dc59c3d9c4fca084a0d7d18049127340adbf3211ab086095a"],"state_sha256":"eb5e16af092549793cd72aebc8084134e6daa99152b4b74f3d70a28596774e90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yz1cpaZvVtYG1aZthyA2YGzfmVnuj1gXc02A2lCYEuW+Bcct4RJL5fZKNnkcNrGCmwEpMCx3aKPdJ0ks6BrfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:19:56.568290Z","bundle_sha256":"56584675cf6e6330ffa8a005d5ed4f58dfea8807eb408a6b45fc41b91584d726"}}