{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JESYMTFR32Y2MSPFXZYHZTMSTS","short_pith_number":"pith:JESYMTFR","schema_version":"1.0","canonical_sha256":"4925864cb1deb1a649e5be707ccd929c8e3b3f0e1df89809f1776a19dd8243c5","source":{"kind":"arxiv","id":"1912.03820","version":3},"attestation_state":"computed","paper":{"title":"Meta-Learning without Memorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, George Tucker, Mingyuan Zhou, Mingzhang Yin, Sergey Levine","submitted_at":"2019-12-09T02:30:46Z","abstract_excerpt":"The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks. However, most meta-learning algorithms implicitly require that the meta-training tasks be mutually-exclusive, such that no single model can solve all of the tasks at once. For example, when creating tasks for few-shot image classification, prior work uses a per-task random assignment of image classes to N-way cl"},"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":"1912.03820","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-09T02:30:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"162ddb289ace864829483d29f6c3d3817ee8ce59c991f7484293eb846ffa6002","abstract_canon_sha256":"f21acf8c00a2d04f33ca54f58cfe8d102b5ac87ebddc8c7352b09a5ef65e0dea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:44.245954Z","signature_b64":"myLS9hVIkR0A2lFvHe3uSPP0uP61sOfhnwwtKvaWF1jRWbXhFYUbL3cU9sxYivBsM+tRnitBrIMKAJIrXe2nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4925864cb1deb1a649e5be707ccd929c8e3b3f0e1df89809f1776a19dd8243c5","last_reissued_at":"2026-07-05T00:58:44.245463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:44.245463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning without Memorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, George Tucker, Mingyuan Zhou, Mingzhang Yin, Sergey Levine","submitted_at":"2019-12-09T02:30:46Z","abstract_excerpt":"The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks. However, most meta-learning algorithms implicitly require that the meta-training tasks be mutually-exclusive, such that no single model can solve all of the tasks at once. For example, when creating tasks for few-shot image classification, prior work uses a per-task random assignment of image classes to N-way cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03820","kind":"arxiv","version":3},"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/1912.03820/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":"1912.03820","created_at":"2026-07-05T00:58:44.245528+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03820v3","created_at":"2026-07-05T00:58:44.245528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03820","created_at":"2026-07-05T00:58:44.245528+00:00"},{"alias_kind":"pith_short_12","alias_value":"JESYMTFR32Y2","created_at":"2026-07-05T00:58:44.245528+00:00"},{"alias_kind":"pith_short_16","alias_value":"JESYMTFR32Y2MSPF","created_at":"2026-07-05T00:58:44.245528+00:00"},{"alias_kind":"pith_short_8","alias_value":"JESYMTFR","created_at":"2026-07-05T00:58:44.245528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12005","citing_title":"BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS","json":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS.json","graph_json":"https://pith.science/api/pith-number/JESYMTFR32Y2MSPFXZYHZTMSTS/graph.json","events_json":"https://pith.science/api/pith-number/JESYMTFR32Y2MSPFXZYHZTMSTS/events.json","paper":"https://pith.science/paper/JESYMTFR"},"agent_actions":{"view_html":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS","download_json":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS.json","view_paper":"https://pith.science/paper/JESYMTFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03820&json=true","fetch_graph":"https://pith.science/api/pith-number/JESYMTFR32Y2MSPFXZYHZTMSTS/graph.json","fetch_events":"https://pith.science/api/pith-number/JESYMTFR32Y2MSPFXZYHZTMSTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS/action/storage_attestation","attest_author":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS/action/author_attestation","sign_citation":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS/action/citation_signature","submit_replication":"https://pith.science/pith/JESYMTFR32Y2MSPFXZYHZTMSTS/action/replication_record"}},"created_at":"2026-07-05T00:58:44.245528+00:00","updated_at":"2026-07-05T00:58:44.245528+00:00"}