{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OJC2HZHZHYDUXHZQFWGXGLURSG","short_pith_number":"pith:OJC2HZHZ","canonical_record":{"source":{"id":"2104.05344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T10:47:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0d75968022683ee0d69915fc65b8cd0513bb01ffc7f0785462a69f9de42a4038","abstract_canon_sha256":"9208b38899cf60664b016e7c840cfaaeeef022a838b5bb9d025f3b08a8026d1b"},"schema_version":"1.0"},"canonical_sha256":"7245a3e4f93e074b9f302d8d732e91918c1213474c7dc14fb8b8d6b6d31b7e1b","source":{"kind":"arxiv","id":"2104.05344","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05344","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05344v1","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05344","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"OJC2HZHZHYDU","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"OJC2HZHZHYDUXHZQ","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"OJC2HZHZ","created_at":"2026-07-05T02:31:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OJC2HZHZHYDUXHZQFWGXGLURSG","target":"record","payload":{"canonical_record":{"source":{"id":"2104.05344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T10:47:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0d75968022683ee0d69915fc65b8cd0513bb01ffc7f0785462a69f9de42a4038","abstract_canon_sha256":"9208b38899cf60664b016e7c840cfaaeeef022a838b5bb9d025f3b08a8026d1b"},"schema_version":"1.0"},"canonical_sha256":"7245a3e4f93e074b9f302d8d732e91918c1213474c7dc14fb8b8d6b6d31b7e1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:11.451660Z","signature_b64":"JlssderxSTEqXCq2ighDRmGu0fyLhrfGTFpnytNGuP51T2qamVYfO/5mWquUdtImlaHutgcEWt33lQV4qYDbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7245a3e4f93e074b9f302d8d732e91918c1213474c7dc14fb8b8d6b6d31b7e1b","last_reissued_at":"2026-07-05T02:31:11.451249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:11.451249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.05344","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmgPSsXWwmEsWpcyw2GOoapmY0vOym9T8krX/YPFrOl9x0fFXsl6btS99jmV/9sAUPViNjApu8XvG4MAjnZoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:19:31.092181Z"},"content_sha256":"56919f80314e8cf903ada70a639b62e4d231b676194e471dc49fe932f4597e74","schema_version":"1.0","event_id":"sha256:56919f80314e8cf903ada70a639b62e4d231b676194e471dc49fe932f4597e74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OJC2HZHZHYDUXHZQFWGXGLURSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Sensitive are Meta-Learners to Dataset Imbalance?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amos Storkey, Jose Vazquez, Massimiliano Patacchiola, Mateusz Ochal, Sen Wang","submitted_at":"2021-04-12T10:47:42Z","abstract_excerpt":"Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the real-world where object classes are likely to occur at different frequencies. While it is generally understood that imbalanced tasks harm the performance of supervised methods, there is no significant research examining the impact of imbalanced meta-datasets on the FSL evaluation task. This study exposes the magnitude and extent of this problem. Our results show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05344","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/2104.05344/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+olamx+7mPWypvdu+nmYodcVBI8jypyjAt3eQkhrfdcHHCO3SkH//ZBS/CIYL1jdF+cJnxt4V1o7jpMjZmspAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:19:31.092864Z"},"content_sha256":"37c1c0048a547da027e6028b6771f04825e51eb29e6639bbf0d4ad87ed48c7ba","schema_version":"1.0","event_id":"sha256:37c1c0048a547da027e6028b6771f04825e51eb29e6639bbf0d4ad87ed48c7ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJC2HZHZHYDUXHZQFWGXGLURSG/bundle.json","state_url":"https://pith.science/pith/OJC2HZHZHYDUXHZQFWGXGLURSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJC2HZHZHYDUXHZQFWGXGLURSG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T07:19:31Z","links":{"resolver":"https://pith.science/pith/OJC2HZHZHYDUXHZQFWGXGLURSG","bundle":"https://pith.science/pith/OJC2HZHZHYDUXHZQFWGXGLURSG/bundle.json","state":"https://pith.science/pith/OJC2HZHZHYDUXHZQFWGXGLURSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJC2HZHZHYDUXHZQFWGXGLURSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OJC2HZHZHYDUXHZQFWGXGLURSG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9208b38899cf60664b016e7c840cfaaeeef022a838b5bb9d025f3b08a8026d1b","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T10:47:42Z","title_canon_sha256":"0d75968022683ee0d69915fc65b8cd0513bb01ffc7f0785462a69f9de42a4038"},"schema_version":"1.0","source":{"id":"2104.05344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05344","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05344v1","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05344","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"OJC2HZHZHYDU","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"OJC2HZHZHYDUXHZQ","created_at":"2026-07-05T02:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"OJC2HZHZ","created_at":"2026-07-05T02:31:11Z"}],"graph_snapshots":[{"event_id":"sha256:37c1c0048a547da027e6028b6771f04825e51eb29e6639bbf0d4ad87ed48c7ba","target":"graph","created_at":"2026-07-05T02:31:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.05344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the real-world where object classes are likely to occur at different frequencies. While it is generally understood that imbalanced tasks harm the performance of supervised methods, there is no significant research examining the impact of imbalanced meta-datasets on the FSL evaluation task. This study exposes the magnitude and extent of this problem. Our results show","authors_text":"Amos Storkey, Jose Vazquez, Massimiliano Patacchiola, Mateusz Ochal, Sen Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T10:47:42Z","title":"How Sensitive are Meta-Learners to Dataset Imbalance?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05344","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:56919f80314e8cf903ada70a639b62e4d231b676194e471dc49fe932f4597e74","target":"record","created_at":"2026-07-05T02:31:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9208b38899cf60664b016e7c840cfaaeeef022a838b5bb9d025f3b08a8026d1b","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T10:47:42Z","title_canon_sha256":"0d75968022683ee0d69915fc65b8cd0513bb01ffc7f0785462a69f9de42a4038"},"schema_version":"1.0","source":{"id":"2104.05344","kind":"arxiv","version":1}},"canonical_sha256":"7245a3e4f93e074b9f302d8d732e91918c1213474c7dc14fb8b8d6b6d31b7e1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7245a3e4f93e074b9f302d8d732e91918c1213474c7dc14fb8b8d6b6d31b7e1b","first_computed_at":"2026-07-05T02:31:11.451249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:11.451249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JlssderxSTEqXCq2ighDRmGu0fyLhrfGTFpnytNGuP51T2qamVYfO/5mWquUdtImlaHutgcEWt33lQV4qYDbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:11.451660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56919f80314e8cf903ada70a639b62e4d231b676194e471dc49fe932f4597e74","sha256:37c1c0048a547da027e6028b6771f04825e51eb29e6639bbf0d4ad87ed48c7ba"],"state_sha256":"5ba20e1bf6e40b54bbef1eb599af2b8f8ac4eaf335f6176c739c25630580d9c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tow6CNH+Nrj3/BjpmF2t5XWwSUTZeKq8+8zRHiyFGDzD7uxeSNqgSzuGKoOp6I+8K2owjOFNj5ET0ohWY0pWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:19:31.096180Z","bundle_sha256":"1f005044c409ef2164b33466f63af0a4104f8c689a559682696175dbbac4f501"}}