{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2VXBQJPKHCD5X5JE2NWGO3XZRH","short_pith_number":"pith:2VXBQJPK","schema_version":"1.0","canonical_sha256":"d56e1825ea3887dbf524d36c676ef989e82220901e5d3bfcb581df9b02fe104a","source":{"kind":"arxiv","id":"2101.11201","version":1},"attestation_state":"computed","paper":{"title":"Similarity of Classification Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Gustavo Carneiro, Thanh-Toan Do","submitted_at":"2021-01-27T04:37:34Z","abstract_excerpt":"Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation. We, therefore, propose a generative approach based on a variant of Latent Dirichlet Allocation to analyse task similarity to optimise and better understand the performance of meta-learning. We demonstrate that the proposed method can provide an insightful evaluation for meta-learning algorithms on two few-shot classification benchmarks that matches common intu"},"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":"2101.11201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-27T04:37:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"193f828da310dd26f75d0ba63ccef8243872e88de46b4b78729d5e63fd8098dd","abstract_canon_sha256":"d85bd62b56375d57ad869c697dc66a649b08be96f526bf5d01f58caa658a28a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:10.015484Z","signature_b64":"FBAWVGN4em/WOGpW+JbEfJIoHdFAdP/oSjLcWYc+aukdnH36B3KwixY7VkP4bmRdVwyQNU2CYetWKEvtrEpBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d56e1825ea3887dbf524d36c676ef989e82220901e5d3bfcb581df9b02fe104a","last_reissued_at":"2026-07-05T02:10:10.015097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:10.015097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similarity of Classification Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Gustavo Carneiro, Thanh-Toan Do","submitted_at":"2021-01-27T04:37:34Z","abstract_excerpt":"Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation. We, therefore, propose a generative approach based on a variant of Latent Dirichlet Allocation to analyse task similarity to optimise and better understand the performance of meta-learning. We demonstrate that the proposed method can provide an insightful evaluation for meta-learning algorithms on two few-shot classification benchmarks that matches common intu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11201","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/2101.11201/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":"2101.11201","created_at":"2026-07-05T02:10:10.015153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11201v1","created_at":"2026-07-05T02:10:10.015153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11201","created_at":"2026-07-05T02:10:10.015153+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VXBQJPKHCD5","created_at":"2026-07-05T02:10:10.015153+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VXBQJPKHCD5X5JE","created_at":"2026-07-05T02:10:10.015153+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VXBQJPK","created_at":"2026-07-05T02:10:10.015153+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/2VXBQJPKHCD5X5JE2NWGO3XZRH","json":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH.json","graph_json":"https://pith.science/api/pith-number/2VXBQJPKHCD5X5JE2NWGO3XZRH/graph.json","events_json":"https://pith.science/api/pith-number/2VXBQJPKHCD5X5JE2NWGO3XZRH/events.json","paper":"https://pith.science/paper/2VXBQJPK"},"agent_actions":{"view_html":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH","download_json":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH.json","view_paper":"https://pith.science/paper/2VXBQJPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11201&json=true","fetch_graph":"https://pith.science/api/pith-number/2VXBQJPKHCD5X5JE2NWGO3XZRH/graph.json","fetch_events":"https://pith.science/api/pith-number/2VXBQJPKHCD5X5JE2NWGO3XZRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH/action/storage_attestation","attest_author":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH/action/author_attestation","sign_citation":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH/action/citation_signature","submit_replication":"https://pith.science/pith/2VXBQJPKHCD5X5JE2NWGO3XZRH/action/replication_record"}},"created_at":"2026-07-05T02:10:10.015153+00:00","updated_at":"2026-07-05T02:10:10.015153+00:00"}