{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2U537QR5VTBYOJAPDF54GOEKQU","short_pith_number":"pith:2U537QR5","schema_version":"1.0","canonical_sha256":"d53bbfc23dacc387240f197bc3388a8534af14b5246054f0a3c548439bfb2d09","source":{"kind":"arxiv","id":"2002.11684","version":5},"attestation_state":"computed","paper":{"title":"Provable Meta-Learning of Linear Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Michael I. Jordan, Nilesh Tripuraneni","submitted_at":"2020-02-26T18:21:34Z","abstract_excerpt":"Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a data representation that can transfer knowledge across multiple tasks, which is essential in regimes where data is scarce. Despite a recent surge of interest in the practice of meta-learning, the theoretical underpinnings of meta-learning algorithms are lacking, especially in the context of learning transferable representations. In this paper, we focus on the "},"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":"2002.11684","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T18:21:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"eb5944aec06c4d665f8d2a5c94179fb3ee0647671b88f022b002aa43f0ae4573","abstract_canon_sha256":"9c4b15d39210fef24c858dfa198168401a9f002386703282744004f7d21accac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:49.452389Z","signature_b64":"PRH1Y7RhMGaHeRO/tQ+IRKK8UnBm1Lgs07isN+qvuAiQxYRKJ8awFTTUye4CS8bbcMGq6RZTpi+morTg3P5fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d53bbfc23dacc387240f197bc3388a8534af14b5246054f0a3c548439bfb2d09","last_reissued_at":"2026-07-05T03:44:49.452035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:49.452035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Meta-Learning of Linear Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Michael I. Jordan, Nilesh Tripuraneni","submitted_at":"2020-02-26T18:21:34Z","abstract_excerpt":"Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a data representation that can transfer knowledge across multiple tasks, which is essential in regimes where data is scarce. Despite a recent surge of interest in the practice of meta-learning, the theoretical underpinnings of meta-learning algorithms are lacking, especially in the context of learning transferable representations. In this paper, we focus on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11684","kind":"arxiv","version":5},"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/2002.11684/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":"2002.11684","created_at":"2026-07-05T03:44:49.452087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11684v5","created_at":"2026-07-05T03:44:49.452087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11684","created_at":"2026-07-05T03:44:49.452087+00:00"},{"alias_kind":"pith_short_12","alias_value":"2U537QR5VTBY","created_at":"2026-07-05T03:44:49.452087+00:00"},{"alias_kind":"pith_short_16","alias_value":"2U537QR5VTBYOJAP","created_at":"2026-07-05T03:44:49.452087+00:00"},{"alias_kind":"pith_short_8","alias_value":"2U537QR5","created_at":"2026-07-05T03:44:49.452087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04243","citing_title":"Attention-based representations for multi-task computation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU","json":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU.json","graph_json":"https://pith.science/api/pith-number/2U537QR5VTBYOJAPDF54GOEKQU/graph.json","events_json":"https://pith.science/api/pith-number/2U537QR5VTBYOJAPDF54GOEKQU/events.json","paper":"https://pith.science/paper/2U537QR5"},"agent_actions":{"view_html":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU","download_json":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU.json","view_paper":"https://pith.science/paper/2U537QR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11684&json=true","fetch_graph":"https://pith.science/api/pith-number/2U537QR5VTBYOJAPDF54GOEKQU/graph.json","fetch_events":"https://pith.science/api/pith-number/2U537QR5VTBYOJAPDF54GOEKQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU/action/storage_attestation","attest_author":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU/action/author_attestation","sign_citation":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU/action/citation_signature","submit_replication":"https://pith.science/pith/2U537QR5VTBYOJAPDF54GOEKQU/action/replication_record"}},"created_at":"2026-07-05T03:44:49.452087+00:00","updated_at":"2026-07-05T03:44:49.452087+00:00"}