{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4MRBYMA3MYKNJ5BFN35RLPOOBG","short_pith_number":"pith:4MRBYMA3","schema_version":"1.0","canonical_sha256":"e3221c301b6614d4f4256efb15bdce09ae86bb0bdd7346971b6944fff623ceef","source":{"kind":"arxiv","id":"2106.02695","version":2},"attestation_state":"computed","paper":{"title":"Meta-Learning with Fewer Tasks through Task Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Huaxiu Yao, Linjun Zhang","submitted_at":"2021-06-04T20:15:34Z","abstract_excerpt":"Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a large number of meta-training tasks, which may not be accessible in real-world scenarios. To address the challenge that available tasks may not densely sample the space of tasks, we propose to augment the task set through interpolation. By meta-learning with task interpolation (MLTI), our approach effectively generates additional tasks by randomly sampling a p"},"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":"2106.02695","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T20:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"3c0b21146e520075d9a8acc76a4c582471bbc7a186995148547fd83d9edc501b","abstract_canon_sha256":"b5c411d5b4b5b677bc33f4a2e2235f3690fd6e3d957b653f911df5b7024ddfe9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:58.707333Z","signature_b64":"wrMjoLECMiOWQNyZMITzPMExF0sXuhbbfcRcHqnWNNZ27cA4ienpFolX766R6J0nkUkeWduyeS+BUqxxscleBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3221c301b6614d4f4256efb15bdce09ae86bb0bdd7346971b6944fff623ceef","last_reissued_at":"2026-07-05T04:05:58.706889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:58.706889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning with Fewer Tasks through Task Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Huaxiu Yao, Linjun Zhang","submitted_at":"2021-06-04T20:15:34Z","abstract_excerpt":"Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a large number of meta-training tasks, which may not be accessible in real-world scenarios. To address the challenge that available tasks may not densely sample the space of tasks, we propose to augment the task set through interpolation. By meta-learning with task interpolation (MLTI), our approach effectively generates additional tasks by randomly sampling a p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02695","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/2106.02695/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":"2106.02695","created_at":"2026-07-05T04:05:58.706945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02695v2","created_at":"2026-07-05T04:05:58.706945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02695","created_at":"2026-07-05T04:05:58.706945+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MRBYMA3MYKN","created_at":"2026-07-05T04:05:58.706945+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MRBYMA3MYKNJ5BF","created_at":"2026-07-05T04:05:58.706945+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MRBYMA3","created_at":"2026-07-05T04:05:58.706945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24792","citing_title":"Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classification","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG","json":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG.json","graph_json":"https://pith.science/api/pith-number/4MRBYMA3MYKNJ5BFN35RLPOOBG/graph.json","events_json":"https://pith.science/api/pith-number/4MRBYMA3MYKNJ5BFN35RLPOOBG/events.json","paper":"https://pith.science/paper/4MRBYMA3"},"agent_actions":{"view_html":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG","download_json":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG.json","view_paper":"https://pith.science/paper/4MRBYMA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02695&json=true","fetch_graph":"https://pith.science/api/pith-number/4MRBYMA3MYKNJ5BFN35RLPOOBG/graph.json","fetch_events":"https://pith.science/api/pith-number/4MRBYMA3MYKNJ5BFN35RLPOOBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG/action/storage_attestation","attest_author":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG/action/author_attestation","sign_citation":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG/action/citation_signature","submit_replication":"https://pith.science/pith/4MRBYMA3MYKNJ5BFN35RLPOOBG/action/replication_record"}},"created_at":"2026-07-05T04:05:58.706945+00:00","updated_at":"2026-07-05T04:05:58.706945+00:00"}