{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WS3O55TUT34WXRNC7PTDYQMW74","short_pith_number":"pith:WS3O55TU","schema_version":"1.0","canonical_sha256":"b4b6eef6749ef96bc5a2fbe63c4196ff0b3ab1fe8999cd76a643eecbf5806a96","source":{"kind":"arxiv","id":"2307.01088","version":1},"attestation_state":"computed","paper":{"title":"Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Kevin Kasa","submitted_at":"2023-07-03T15:08:28Z","abstract_excerpt":"Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to degrade under distribution shift and long-tailed class distributions, which are often present in real world applications. Here, we characterize the performance of several post-hoc and training-based conformal prediction methods under these settings, providing the first empirical evaluation on large-scale datasets and models. We show that across numerous conformal methods and neural network families, performance greatl"},"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":"2307.01088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T15:08:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"d08f7206ec5fb16e7b7bafad586877f13e88244402a8e7a6541f68cd0818fd5c","abstract_canon_sha256":"47eba6649df0cd0e772530c557c6399d002a6f6204b7290c0be1eb213be1b1fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:52.775890Z","signature_b64":"JwDuwXDkkoCEIylulP0adR5AePL0QozpjM9wxldBh87xwEDOcHPpS5Mg+v2ZJNTjj/MExUY0a1zM8iA20uv+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4b6eef6749ef96bc5a2fbe63c4196ff0b3ab1fe8999cd76a643eecbf5806a96","last_reissued_at":"2026-07-05T06:27:52.775428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:52.775428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Kevin Kasa","submitted_at":"2023-07-03T15:08:28Z","abstract_excerpt":"Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to degrade under distribution shift and long-tailed class distributions, which are often present in real world applications. Here, we characterize the performance of several post-hoc and training-based conformal prediction methods under these settings, providing the first empirical evaluation on large-scale datasets and models. We show that across numerous conformal methods and neural network families, performance greatl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01088","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.01088/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":"2307.01088","created_at":"2026-07-05T06:27:52.775501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01088v1","created_at":"2026-07-05T06:27:52.775501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01088","created_at":"2026-07-05T06:27:52.775501+00:00"},{"alias_kind":"pith_short_12","alias_value":"WS3O55TUT34W","created_at":"2026-07-05T06:27:52.775501+00:00"},{"alias_kind":"pith_short_16","alias_value":"WS3O55TUT34WXRNC","created_at":"2026-07-05T06:27:52.775501+00:00"},{"alias_kind":"pith_short_8","alias_value":"WS3O55TU","created_at":"2026-07-05T06:27:52.775501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11345","citing_title":"Conformal Prediction Meets Long-tail Classification","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74","json":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74.json","graph_json":"https://pith.science/api/pith-number/WS3O55TUT34WXRNC7PTDYQMW74/graph.json","events_json":"https://pith.science/api/pith-number/WS3O55TUT34WXRNC7PTDYQMW74/events.json","paper":"https://pith.science/paper/WS3O55TU"},"agent_actions":{"view_html":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74","download_json":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74.json","view_paper":"https://pith.science/paper/WS3O55TU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01088&json=true","fetch_graph":"https://pith.science/api/pith-number/WS3O55TUT34WXRNC7PTDYQMW74/graph.json","fetch_events":"https://pith.science/api/pith-number/WS3O55TUT34WXRNC7PTDYQMW74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74/action/storage_attestation","attest_author":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74/action/author_attestation","sign_citation":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74/action/citation_signature","submit_replication":"https://pith.science/pith/WS3O55TUT34WXRNC7PTDYQMW74/action/replication_record"}},"created_at":"2026-07-05T06:27:52.775501+00:00","updated_at":"2026-07-05T06:27:52.775501+00:00"}