{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2FZTZ5AD6WKUARKPA56V4EH6DF","short_pith_number":"pith:2FZTZ5AD","schema_version":"1.0","canonical_sha256":"d1733cf403f59540454f077d5e10fe1950b60f23d369eb50e0e9c4867993e852","source":{"kind":"arxiv","id":"2409.02850","version":2},"attestation_state":"computed","paper":{"title":"Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Franck Vermet, Ian Reid, Jack Valmadre, Luke Smith, Mathias L\\\"owe, Raphael Lafargue, Vincent Gripon","submitted_at":"2024-09-04T16:20:57Z","abstract_excerpt":"The predominant method for computing confidence intervals (CI) in few-shot learning (FSL) is based on sampling the tasks with replacement, i.e.\\ allowing the same samples to appear in multiple tasks. This makes the CI misleading in that it takes into account the randomness of the sampler but not the data itself. To quantify the extent of this problem, we conduct a comparative analysis between CIs computed with and without replacement. These reveal a notable underestimation by the predominant method. This observation calls for a reevaluation of how we interpret confidence intervals and the resu"},"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":"2409.02850","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-04T16:20:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4e8c47aa34fd039a62b70e615ca964ea8d717b1eafc50339cd5e31814db9719c","abstract_canon_sha256":"ec64185c298c66afda826586efc7598c8e492e4f9d7f4331d8c827b022d713d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:56.225147Z","signature_b64":"A2htyVK3DTkR4BfEl6BA5o7LTu6ZSqGgO9tp3Yk+c3rGhu2GAFSufegUuK5Ntx6EQ0nszkXx67zT9DL7ibc1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1733cf403f59540454f077d5e10fe1950b60f23d369eb50e0e9c4867993e852","last_reissued_at":"2026-07-05T09:03:56.224776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:56.224776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Franck Vermet, Ian Reid, Jack Valmadre, Luke Smith, Mathias L\\\"owe, Raphael Lafargue, Vincent Gripon","submitted_at":"2024-09-04T16:20:57Z","abstract_excerpt":"The predominant method for computing confidence intervals (CI) in few-shot learning (FSL) is based on sampling the tasks with replacement, i.e.\\ allowing the same samples to appear in multiple tasks. This makes the CI misleading in that it takes into account the randomness of the sampler but not the data itself. To quantify the extent of this problem, we conduct a comparative analysis between CIs computed with and without replacement. These reveal a notable underestimation by the predominant method. This observation calls for a reevaluation of how we interpret confidence intervals and the resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02850","kind":"arxiv","version":2},"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/2409.02850/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":"2409.02850","created_at":"2026-07-05T09:03:56.224836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02850v2","created_at":"2026-07-05T09:03:56.224836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02850","created_at":"2026-07-05T09:03:56.224836+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FZTZ5AD6WKU","created_at":"2026-07-05T09:03:56.224836+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FZTZ5AD6WKUARKP","created_at":"2026-07-05T09:03:56.224836+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FZTZ5AD","created_at":"2026-07-05T09:03:56.224836+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/2FZTZ5AD6WKUARKPA56V4EH6DF","json":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF.json","graph_json":"https://pith.science/api/pith-number/2FZTZ5AD6WKUARKPA56V4EH6DF/graph.json","events_json":"https://pith.science/api/pith-number/2FZTZ5AD6WKUARKPA56V4EH6DF/events.json","paper":"https://pith.science/paper/2FZTZ5AD"},"agent_actions":{"view_html":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF","download_json":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF.json","view_paper":"https://pith.science/paper/2FZTZ5AD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02850&json=true","fetch_graph":"https://pith.science/api/pith-number/2FZTZ5AD6WKUARKPA56V4EH6DF/graph.json","fetch_events":"https://pith.science/api/pith-number/2FZTZ5AD6WKUARKPA56V4EH6DF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF/action/storage_attestation","attest_author":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF/action/author_attestation","sign_citation":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF/action/citation_signature","submit_replication":"https://pith.science/pith/2FZTZ5AD6WKUARKPA56V4EH6DF/action/replication_record"}},"created_at":"2026-07-05T09:03:56.224836+00:00","updated_at":"2026-07-05T09:03:56.224836+00:00"}