{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PR5TFDAATZJ24MHWY3UBPMYAGY","short_pith_number":"pith:PR5TFDAA","schema_version":"1.0","canonical_sha256":"7c7b328c009e53ae30f6c6e817b3003604f3cdaef57176b77de64c9fd2300348","source":{"kind":"arxiv","id":"1806.00451","version":1},"attestation_state":"computed","paper":{"title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Recht, Ludwig Schmidt, Rebecca Roelofs, Vaishaal Shankar","submitted_at":"2018-06-01T17:16:56Z","abstract_excerpt":"Machine learning is currently dominated by largely experimental work focused on improvements in a few key tasks. However, the impressive accuracy numbers of the best performing models are questionable because the same test sets have been used to select these models for multiple years now. To understand the danger of overfitting, we measure the accuracy of CIFAR-10 classifiers by creating a new test set of truly unseen images. Although we ensure that the new test set is as close to the original data distribution as possible, we find a large drop in accuracy (4% to 10%) for a broad range of deep"},"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":"1806.00451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T17:16:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"10745e729ed290c36e689ed8de33f8605de754957a7efd1a844814069ccb6371","abstract_canon_sha256":"25c56812f99b16d99a5053f0c72e3380b8926f59651af2d7f531b955291cb221"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:23.594521Z","signature_b64":"3YJIFy/rgc2qXTHCERVEf7KS4IwKsfAFh5S1KPLVaTMUvQejkIYvZqITHkkMa6E9It/OSxheuSX0LtL2T8KbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c7b328c009e53ae30f6c6e817b3003604f3cdaef57176b77de64c9fd2300348","last_reissued_at":"2026-05-18T00:14:23.589831Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:23.589831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Recht, Ludwig Schmidt, Rebecca Roelofs, Vaishaal Shankar","submitted_at":"2018-06-01T17:16:56Z","abstract_excerpt":"Machine learning is currently dominated by largely experimental work focused on improvements in a few key tasks. However, the impressive accuracy numbers of the best performing models are questionable because the same test sets have been used to select these models for multiple years now. To understand the danger of overfitting, we measure the accuracy of CIFAR-10 classifiers by creating a new test set of truly unseen images. Although we ensure that the new test set is as close to the original data distribution as possible, we find a large drop in accuracy (4% to 10%) for a broad range of deep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00451","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":"1806.00451","created_at":"2026-05-18T00:14:23.589962+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00451v1","created_at":"2026-05-18T00:14:23.589962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00451","created_at":"2026-05-18T00:14:23.589962+00:00"},{"alias_kind":"pith_short_12","alias_value":"PR5TFDAATZJ2","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PR5TFDAATZJ24MHW","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PR5TFDAA","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1907.01463","citing_title":"Reproducibility in Machine Learning for Health","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24810","citing_title":"A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23096","citing_title":"Encrypted Neural Networks without Overflows","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23244","citing_title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04686","citing_title":"How does the optimizer implicitly bias the model merging loss landscape?","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1910.04867","citing_title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2006.10726","citing_title":"Tent: Fully Test-time Adaptation by Entropy Minimization","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08870","citing_title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24810","citing_title":"A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05342","citing_title":"Generative Channel Knowledge Base With Environmental Information for Joint Source-Channel Coding in Semantic Communications","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY","json":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY.json","graph_json":"https://pith.science/api/pith-number/PR5TFDAATZJ24MHWY3UBPMYAGY/graph.json","events_json":"https://pith.science/api/pith-number/PR5TFDAATZJ24MHWY3UBPMYAGY/events.json","paper":"https://pith.science/paper/PR5TFDAA"},"agent_actions":{"view_html":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY","download_json":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY.json","view_paper":"https://pith.science/paper/PR5TFDAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00451&json=true","fetch_graph":"https://pith.science/api/pith-number/PR5TFDAATZJ24MHWY3UBPMYAGY/graph.json","fetch_events":"https://pith.science/api/pith-number/PR5TFDAATZJ24MHWY3UBPMYAGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY/action/storage_attestation","attest_author":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY/action/author_attestation","sign_citation":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY/action/citation_signature","submit_replication":"https://pith.science/pith/PR5TFDAATZJ24MHWY3UBPMYAGY/action/replication_record"}},"created_at":"2026-05-18T00:14:23.589962+00:00","updated_at":"2026-05-18T00:14:23.589962+00:00"}