{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7YIRLOI2744WTWVXMUS3P7FYKD","short_pith_number":"pith:7YIRLOI2","schema_version":"1.0","canonical_sha256":"fe1115b91aff3969dab76525b7fcb850d11d828c30bc1e0ada1f2b368224ae29","source":{"kind":"arxiv","id":"2311.09215","version":3},"attestation_state":"computed","paper":{"title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu","submitted_at":"2023-11-15T18:56:51Z","abstract_excerpt":"Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are compared by their classification accuracy on ImageNet. However, this single metric does not fully capture performance nuances critical for specialized tasks. In this work, we conduct an in-depth comparative analysis of model behaviors beyond ImageNet accuracy, for both ConvNet and Vision Transformer architectures, each across supervised and CLIP training paradi"},"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":"2311.09215","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-15T18:56:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c28d92b14b69e44777df7a49921f9cce125a40cfa5ab90c62c3dbada58d701a4","abstract_canon_sha256":"0e7614023b8f059660d2ac752aafa7041d833e9c46643220b83fb9e0b6e6a04f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:08.696986Z","signature_b64":"MwsaAEHZjqcnzH1kCpfSA0Oz9wm8/B2FUyWv3AUcdHG6sD5LITQxzp715+mp/HdmnCfcES2h5RG2s5NanvB/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe1115b91aff3969dab76525b7fcb850d11d828c30bc1e0ada1f2b368224ae29","last_reissued_at":"2026-07-05T08:47:08.696454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:08.696454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu","submitted_at":"2023-11-15T18:56:51Z","abstract_excerpt":"Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are compared by their classification accuracy on ImageNet. However, this single metric does not fully capture performance nuances critical for specialized tasks. In this work, we conduct an in-depth comparative analysis of model behaviors beyond ImageNet accuracy, for both ConvNet and Vision Transformer architectures, each across supervised and CLIP training paradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09215","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.09215/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.09215","created_at":"2026-07-05T08:47:08.696525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09215v3","created_at":"2026-07-05T08:47:08.696525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09215","created_at":"2026-07-05T08:47:08.696525+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YIRLOI2744W","created_at":"2026-07-05T08:47:08.696525+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YIRLOI2744WTWVX","created_at":"2026-07-05T08:47:08.696525+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YIRLOI2","created_at":"2026-07-05T08:47:08.696525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD","json":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD.json","graph_json":"https://pith.science/api/pith-number/7YIRLOI2744WTWVXMUS3P7FYKD/graph.json","events_json":"https://pith.science/api/pith-number/7YIRLOI2744WTWVXMUS3P7FYKD/events.json","paper":"https://pith.science/paper/7YIRLOI2"},"agent_actions":{"view_html":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD","download_json":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD.json","view_paper":"https://pith.science/paper/7YIRLOI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09215&json=true","fetch_graph":"https://pith.science/api/pith-number/7YIRLOI2744WTWVXMUS3P7FYKD/graph.json","fetch_events":"https://pith.science/api/pith-number/7YIRLOI2744WTWVXMUS3P7FYKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD/action/storage_attestation","attest_author":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD/action/author_attestation","sign_citation":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD/action/citation_signature","submit_replication":"https://pith.science/pith/7YIRLOI2744WTWVXMUS3P7FYKD/action/replication_record"}},"created_at":"2026-07-05T08:47:08.696525+00:00","updated_at":"2026-07-05T08:47:08.696525+00:00"}