{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NQKYYSQMNP6Y5SRVYAQ43QLYJM","short_pith_number":"pith:NQKYYSQM","schema_version":"1.0","canonical_sha256":"6c158c4a0c6bfd8eca35c021cdc1784b1f621705f92baf9280b0d0493079b7f2","source":{"kind":"arxiv","id":"2110.03909","version":2},"attestation_state":"computed","paper":{"title":"Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dohee Cho, Heewon Kim, Jaesik Min, Janghoon Choi, Kyoung Mu Lee, Sungyong Baik","submitted_at":"2021-10-08T06:07:21Z","abstract_excerpt":"In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnostic meta-learning (MAML) has gained the popularity as one of the representative few-shot learning methods for its flexibility and applicability to diverse problems. However, MAML and its variants often resort to a simple loss function without any auxiliary loss function or regularization terms that can help achieve better generalization. The problem lies in that each application and task may require different auxiliar"},"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":"2110.03909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T06:07:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3e2955c85d093164314b9fdd68cfa7fc634af2cd7997c145d8ee9400d180035b","abstract_canon_sha256":"7f7df246552e9d3cd53293ba67f25cf63df1443654c9c4bacdab7437e8e9bc8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:15.107397Z","signature_b64":"P8pxfwF2TowtKT7cGsnecl/cIs/rORCTqjrvn0Ciduo8bsvvCBQLDb5T97Df5OMo/6NFbJaNsKbAFPBTbiBYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c158c4a0c6bfd8eca35c021cdc1784b1f621705f92baf9280b0d0493079b7f2","last_reissued_at":"2026-07-05T03:23:15.106960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:15.106960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dohee Cho, Heewon Kim, Jaesik Min, Janghoon Choi, Kyoung Mu Lee, Sungyong Baik","submitted_at":"2021-10-08T06:07:21Z","abstract_excerpt":"In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnostic meta-learning (MAML) has gained the popularity as one of the representative few-shot learning methods for its flexibility and applicability to diverse problems. However, MAML and its variants often resort to a simple loss function without any auxiliary loss function or regularization terms that can help achieve better generalization. The problem lies in that each application and task may require different auxiliar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03909","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/2110.03909/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":"2110.03909","created_at":"2026-07-05T03:23:15.107013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03909v2","created_at":"2026-07-05T03:23:15.107013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03909","created_at":"2026-07-05T03:23:15.107013+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQKYYSQMNP6Y","created_at":"2026-07-05T03:23:15.107013+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQKYYSQMNP6Y5SRV","created_at":"2026-07-05T03:23:15.107013+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQKYYSQM","created_at":"2026-07-05T03:23:15.107013+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/NQKYYSQMNP6Y5SRVYAQ43QLYJM","json":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM.json","graph_json":"https://pith.science/api/pith-number/NQKYYSQMNP6Y5SRVYAQ43QLYJM/graph.json","events_json":"https://pith.science/api/pith-number/NQKYYSQMNP6Y5SRVYAQ43QLYJM/events.json","paper":"https://pith.science/paper/NQKYYSQM"},"agent_actions":{"view_html":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM","download_json":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM.json","view_paper":"https://pith.science/paper/NQKYYSQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03909&json=true","fetch_graph":"https://pith.science/api/pith-number/NQKYYSQMNP6Y5SRVYAQ43QLYJM/graph.json","fetch_events":"https://pith.science/api/pith-number/NQKYYSQMNP6Y5SRVYAQ43QLYJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM/action/storage_attestation","attest_author":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM/action/author_attestation","sign_citation":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM/action/citation_signature","submit_replication":"https://pith.science/pith/NQKYYSQMNP6Y5SRVYAQ43QLYJM/action/replication_record"}},"created_at":"2026-07-05T03:23:15.107013+00:00","updated_at":"2026-07-05T03:23:15.107013+00:00"}