{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QYGCS55DMFYJCO5EFSVGX5O3LJ","short_pith_number":"pith:QYGCS55D","canonical_record":{"source":{"id":"1902.00423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-01T16:00:34Z","cross_cats_sorted":[],"title_canon_sha256":"d40f393f34e28396968b84c0044da30d5c72cb8a6c53b4b6772b9b08bb78fca0","abstract_canon_sha256":"c8b9a8815bc47cda1af1c1bc6e43cfa56e7339cd4262f6d525803e35cdd12903"},"schema_version":"1.0"},"canonical_sha256":"860c2977a36170913ba42caa6bf5db5a59f41b6ef26a8a8cedb49a879587455a","source":{"kind":"arxiv","id":"1902.00423","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00423","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00423v2","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00423","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"QYGCS55DMFYJ","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"QYGCS55DMFYJCO5E","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"QYGCS55D","created_at":"2026-07-05T01:07:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QYGCS55DMFYJCO5EFSVGX5O3LJ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-01T16:00:34Z","cross_cats_sorted":[],"title_canon_sha256":"d40f393f34e28396968b84c0044da30d5c72cb8a6c53b4b6772b9b08bb78fca0","abstract_canon_sha256":"c8b9a8815bc47cda1af1c1bc6e43cfa56e7339cd4262f6d525803e35cdd12903"},"schema_version":"1.0"},"canonical_sha256":"860c2977a36170913ba42caa6bf5db5a59f41b6ef26a8a8cedb49a879587455a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:24.675791Z","signature_b64":"xZ1vUodOo+oQYyc2ZA22fsLzsLayEuCLwK7/+cyGK9G6rFrx9Od3lR96jm8TD58ubvMAGdViH8UFvuTBV8qiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"860c2977a36170913ba42caa6bf5db5a59f41b6ef26a8a8cedb49a879587455a","last_reissued_at":"2026-07-05T01:07:24.675342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:24.675342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00423","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYCIME25NBc67ud8mtrUdSajemRyAoRtZ21DBvJ7E2xNVW537yCWj1yJxAvq9cr+83hJhL2rcvobdBhE29AXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:48.498134Z"},"content_sha256":"49bc48ed2c58795b82133a313298e91ce8a68eeac497b556cfc9cea4ddc3cedb","schema_version":"1.0","event_id":"sha256:49bc48ed2c58795b82133a313298e91ce8a68eeac497b556cfc9cea4ddc3cedb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QYGCS55DMFYJCO5EFSVGX5O3LJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do We Train on Test Data? Purging CIFAR of Near-Duplicates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Barz, Joachim Denzler","submitted_at":"2019-02-01T16:00:34Z","abstract_excerpt":"The CIFAR-10 and CIFAR-100 datasets are two of the most heavily benchmarked datasets in computer vision and are often used to evaluate novel methods and model architectures in the field of deep learning. However, we find that 3.3% and 10% of the images from the test sets of these datasets have duplicates in the training set. These duplicates are easily recognizable by memorization and may, hence, bias the comparison of image recognition techniques regarding their generalization capability. To eliminate this bias, we provide the \"fair CIFAR\" (ciFAIR) dataset, where we replaced all duplicates in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00423","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/1902.00423/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEx54JwvQRNDYwaUOE0VxfOzFouSBUKZMbrobniBg1WqIYl/H31oZBdgzNKtdUVKp8B8JhVdqWtn18GA0aPvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:48.498527Z"},"content_sha256":"1e82ec89234e688d39525803ad0fba691d0b1a511f349edda41094d2156c5e67","schema_version":"1.0","event_id":"sha256:1e82ec89234e688d39525803ad0fba691d0b1a511f349edda41094d2156c5e67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ/bundle.json","state_url":"https://pith.science/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ/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":"2026-07-06T19:05:48Z","links":{"resolver":"https://pith.science/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ","bundle":"https://pith.science/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ/bundle.json","state":"https://pith.science/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYGCS55DMFYJCO5EFSVGX5O3LJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QYGCS55DMFYJCO5EFSVGX5O3LJ","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":"c8b9a8815bc47cda1af1c1bc6e43cfa56e7339cd4262f6d525803e35cdd12903","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-01T16:00:34Z","title_canon_sha256":"d40f393f34e28396968b84c0044da30d5c72cb8a6c53b4b6772b9b08bb78fca0"},"schema_version":"1.0","source":{"id":"1902.00423","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00423","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00423v2","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00423","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"QYGCS55DMFYJ","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"QYGCS55DMFYJCO5E","created_at":"2026-07-05T01:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"QYGCS55D","created_at":"2026-07-05T01:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:1e82ec89234e688d39525803ad0fba691d0b1a511f349edda41094d2156c5e67","target":"graph","created_at":"2026-07-05T01:07:24Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1902.00423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The CIFAR-10 and CIFAR-100 datasets are two of the most heavily benchmarked datasets in computer vision and are often used to evaluate novel methods and model architectures in the field of deep learning. However, we find that 3.3% and 10% of the images from the test sets of these datasets have duplicates in the training set. These duplicates are easily recognizable by memorization and may, hence, bias the comparison of image recognition techniques regarding their generalization capability. To eliminate this bias, we provide the \"fair CIFAR\" (ciFAIR) dataset, where we replaced all duplicates in","authors_text":"Bj\\\"orn Barz, Joachim Denzler","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-01T16:00:34Z","title":"Do We Train on Test Data? Purging CIFAR of Near-Duplicates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00423","kind":"arxiv","version":2},"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":"sha256:49bc48ed2c58795b82133a313298e91ce8a68eeac497b556cfc9cea4ddc3cedb","target":"record","created_at":"2026-07-05T01:07:24Z","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":"c8b9a8815bc47cda1af1c1bc6e43cfa56e7339cd4262f6d525803e35cdd12903","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-01T16:00:34Z","title_canon_sha256":"d40f393f34e28396968b84c0044da30d5c72cb8a6c53b4b6772b9b08bb78fca0"},"schema_version":"1.0","source":{"id":"1902.00423","kind":"arxiv","version":2}},"canonical_sha256":"860c2977a36170913ba42caa6bf5db5a59f41b6ef26a8a8cedb49a879587455a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"860c2977a36170913ba42caa6bf5db5a59f41b6ef26a8a8cedb49a879587455a","first_computed_at":"2026-07-05T01:07:24.675342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:24.675342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xZ1vUodOo+oQYyc2ZA22fsLzsLayEuCLwK7/+cyGK9G6rFrx9Od3lR96jm8TD58ubvMAGdViH8UFvuTBV8qiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:24.675791Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00423","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49bc48ed2c58795b82133a313298e91ce8a68eeac497b556cfc9cea4ddc3cedb","sha256:1e82ec89234e688d39525803ad0fba691d0b1a511f349edda41094d2156c5e67"],"state_sha256":"598b03445cf14777cbda7aaf21a31f312f723648f5bcad3eb9fe177e9aec9d33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y48v67S5bwjX7P9SkTk8PSE7YN9xf2+ydPn9D9sYZDNfGWbEY5qq4g2FHDkdpq8mw82BHM+TCrDIH4fWvU7PBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:05:48.500615Z","bundle_sha256":"0f0cb706291e88ecb14fba1b59e0f600c218e5052fee452667b595c457e6b02d"}}