{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QCLFROAXIUHKC5LAW2ID6HFS5D","short_pith_number":"pith:QCLFROAX","schema_version":"1.0","canonical_sha256":"809658b817450ea17560b6903f1cb2e8ec9157dec361f125ee99a86549fdf9a4","source":{"kind":"arxiv","id":"1811.12569","version":1},"attestation_state":"computed","paper":{"title":"Are All Training Examples Created Equal? An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jitendra Malik, Kailas Vodrahalli, Ke Li","submitted_at":"2018-11-30T01:16:42Z","abstract_excerpt":"Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for training. In this paper, we propose a gradient-based importance measure that we use to empirically analyze relative importance of training images in four datasets of varying complexity. We find that in some cases, a small subsample is indeed sufficient for training. For other datasets, however, the relative differences in importance are negligible. These results have important implications for active learning on deep netwo"},"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":"1811.12569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T01:16:42Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"869105d136e227be229cd7e22468e5912c264de321edbdf9a0abfb543fe9ab60","abstract_canon_sha256":"aa3e4e06c02ccf3323f1c39a1923e748b13689214ea7f4dc8a7db7efea2d95b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:29.246751Z","signature_b64":"XnV9xpUXXa9PDzS1tWuP+IHWYwMVoyL+mU83RVuxhUg7/F6ojVuXAVhSsvUVHKYXb6KdT+0zUJeTQ2kiwFQoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"809658b817450ea17560b6903f1cb2e8ec9157dec361f125ee99a86549fdf9a4","last_reissued_at":"2026-05-17T23:59:29.246123Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:29.246123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are All Training Examples Created Equal? An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jitendra Malik, Kailas Vodrahalli, Ke Li","submitted_at":"2018-11-30T01:16:42Z","abstract_excerpt":"Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for training. In this paper, we propose a gradient-based importance measure that we use to empirically analyze relative importance of training images in four datasets of varying complexity. We find that in some cases, a small subsample is indeed sufficient for training. For other datasets, however, the relative differences in importance are negligible. These results have important implications for active learning on deep netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12569","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":"1811.12569","created_at":"2026-05-17T23:59:29.246227+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12569v1","created_at":"2026-05-17T23:59:29.246227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12569","created_at":"2026-05-17T23:59:29.246227+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCLFROAXIUHK","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCLFROAXIUHKC5LA","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCLFROAX","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07023","citing_title":"Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D","json":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D.json","graph_json":"https://pith.science/api/pith-number/QCLFROAXIUHKC5LAW2ID6HFS5D/graph.json","events_json":"https://pith.science/api/pith-number/QCLFROAXIUHKC5LAW2ID6HFS5D/events.json","paper":"https://pith.science/paper/QCLFROAX"},"agent_actions":{"view_html":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D","download_json":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D.json","view_paper":"https://pith.science/paper/QCLFROAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12569&json=true","fetch_graph":"https://pith.science/api/pith-number/QCLFROAXIUHKC5LAW2ID6HFS5D/graph.json","fetch_events":"https://pith.science/api/pith-number/QCLFROAXIUHKC5LAW2ID6HFS5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D/action/storage_attestation","attest_author":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D/action/author_attestation","sign_citation":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D/action/citation_signature","submit_replication":"https://pith.science/pith/QCLFROAXIUHKC5LAW2ID6HFS5D/action/replication_record"}},"created_at":"2026-05-17T23:59:29.246227+00:00","updated_at":"2026-05-17T23:59:29.246227+00:00"}