{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5PWU4OAFFL6QH5ZBTTBUPIAHPB","short_pith_number":"pith:5PWU4OAF","schema_version":"1.0","canonical_sha256":"ebed4e38052afd03f7219cc347a0077856ae30c99d5548209232efc899bbb222","source":{"kind":"arxiv","id":"1805.08974","version":3},"attestation_state":"computed","paper":{"title":"Do Better ImageNet Models Transfer Better?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jonathon Shlens, Quoc V. Le, Simon Kornblith","submitted_at":"2018-05-23T06:12:35Z","abstract_excerpt":"Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform better on ImageNet necessarily perform better on other vision tasks. However, this hypothesis has never been systematically tested. Here, we compare the performance of 16 classification networks on 12 image classification datasets. We find that, when networks are used as fixed feature extractors or fine-tuned, there is a strong correlation between ImageNet accura"},"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":"1805.08974","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T06:12:35Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7f0258f5b4df3cadd54f5ea5df3b58fa67cafb3a359f5eb479d206ef649a5bb1","abstract_canon_sha256":"66398f3818580986b7a724cd6eef849ae70b23a67b6d43379a3b2e5e18bb0bc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:17.990264Z","signature_b64":"ZnxFM0C6H/y6imsoiTInXaEC+HUu/s43Eg26mEJ7J3FgSM8UVqNFT4py6C4t4c/MD/sLyu+fVhbxHKsWzx5vAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebed4e38052afd03f7219cc347a0077856ae30c99d5548209232efc899bbb222","last_reissued_at":"2026-05-17T23:43:17.989605Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:17.989605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Better ImageNet Models Transfer Better?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jonathon Shlens, Quoc V. Le, Simon Kornblith","submitted_at":"2018-05-23T06:12:35Z","abstract_excerpt":"Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform better on ImageNet necessarily perform better on other vision tasks. However, this hypothesis has never been systematically tested. Here, we compare the performance of 16 classification networks on 12 image classification datasets. We find that, when networks are used as fixed feature extractors or fine-tuned, there is a strong correlation between ImageNet accura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08974","kind":"arxiv","version":3},"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":"1805.08974","created_at":"2026-05-17T23:43:17.989712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08974v3","created_at":"2026-05-17T23:43:17.989712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08974","created_at":"2026-05-17T23:43:17.989712+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PWU4OAFFL6Q","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PWU4OAFFL6QH5ZB","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PWU4OAF","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.18700","citing_title":"A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2010.01412","citing_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2210.08402","citing_title":"LAION-5B: An open large-scale dataset for training next generation image-text models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB","json":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB.json","graph_json":"https://pith.science/api/pith-number/5PWU4OAFFL6QH5ZBTTBUPIAHPB/graph.json","events_json":"https://pith.science/api/pith-number/5PWU4OAFFL6QH5ZBTTBUPIAHPB/events.json","paper":"https://pith.science/paper/5PWU4OAF"},"agent_actions":{"view_html":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB","download_json":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB.json","view_paper":"https://pith.science/paper/5PWU4OAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08974&json=true","fetch_graph":"https://pith.science/api/pith-number/5PWU4OAFFL6QH5ZBTTBUPIAHPB/graph.json","fetch_events":"https://pith.science/api/pith-number/5PWU4OAFFL6QH5ZBTTBUPIAHPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB/action/storage_attestation","attest_author":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB/action/author_attestation","sign_citation":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB/action/citation_signature","submit_replication":"https://pith.science/pith/5PWU4OAFFL6QH5ZBTTBUPIAHPB/action/replication_record"}},"created_at":"2026-05-17T23:43:17.989712+00:00","updated_at":"2026-05-17T23:43:17.989712+00:00"}