{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TTXGKYRZNMSPCHE5LNI354FCDA","short_pith_number":"pith:TTXGKYRZ","schema_version":"1.0","canonical_sha256":"9cee6562396b24f11c9d5b51bef0a218194873580fe993fc66b58206f9406230","source":{"kind":"arxiv","id":"2008.12284","version":2},"attestation_state":"computed","paper":{"title":"learn2learn: A Library for Meta-Learning Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debajyoti Datta, Ian Bunner, Konstantinos Saitas Zarkias, Praateek Mahajan, S\\'ebastien M. R. Arnold","submitted_at":"2020-08-27T17:41:34Z","abstract_excerpt":"Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new algorithms and tasks because modern meta-learning methods rely on unconventional functionalities of machine learning frameworks. In turn, reproducing existing results becomes a tedious endeavour -- a situation exacerbated by the lack of standardized implementations and benchmarks. As a result, researchers spend inordinate amounts of time on implementing software rather than understanding and developing new ideas.\n  This manu"},"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":"2008.12284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-08-27T17:41:34Z","cross_cats_sorted":["cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"0ef9df92974c283586ff6849361354261da99a00f4091925288950abb4821d55","abstract_canon_sha256":"23d9646c435d9e2743d796162b7882cc8e34cea8801a364a1c3ca4c167c75cb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:13.748442Z","signature_b64":"JkcM/lsA8gHbaxLA7Mxcj0XGErLw0fEI+JTpWiIsEsg/JFEvblZLisJliBKry4J+r38G0X7K4WSrXgbPxXr5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cee6562396b24f11c9d5b51bef0a218194873580fe993fc66b58206f9406230","last_reissued_at":"2026-07-05T01:31:13.747903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:13.747903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"learn2learn: A Library for Meta-Learning Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debajyoti Datta, Ian Bunner, Konstantinos Saitas Zarkias, Praateek Mahajan, S\\'ebastien M. R. Arnold","submitted_at":"2020-08-27T17:41:34Z","abstract_excerpt":"Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new algorithms and tasks because modern meta-learning methods rely on unconventional functionalities of machine learning frameworks. In turn, reproducing existing results becomes a tedious endeavour -- a situation exacerbated by the lack of standardized implementations and benchmarks. As a result, researchers spend inordinate amounts of time on implementing software rather than understanding and developing new ideas.\n  This manu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12284","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/2008.12284/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":"2008.12284","created_at":"2026-07-05T01:31:13.747973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.12284v2","created_at":"2026-07-05T01:31:13.747973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12284","created_at":"2026-07-05T01:31:13.747973+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTXGKYRZNMSP","created_at":"2026-07-05T01:31:13.747973+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTXGKYRZNMSPCHE5","created_at":"2026-07-05T01:31:13.747973+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTXGKYRZ","created_at":"2026-07-05T01:31:13.747973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20115","citing_title":"On the Stability and Generalization of First-order Bilevel Minimax Optimization","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13263","citing_title":"Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA","json":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA.json","graph_json":"https://pith.science/api/pith-number/TTXGKYRZNMSPCHE5LNI354FCDA/graph.json","events_json":"https://pith.science/api/pith-number/TTXGKYRZNMSPCHE5LNI354FCDA/events.json","paper":"https://pith.science/paper/TTXGKYRZ"},"agent_actions":{"view_html":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA","download_json":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA.json","view_paper":"https://pith.science/paper/TTXGKYRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.12284&json=true","fetch_graph":"https://pith.science/api/pith-number/TTXGKYRZNMSPCHE5LNI354FCDA/graph.json","fetch_events":"https://pith.science/api/pith-number/TTXGKYRZNMSPCHE5LNI354FCDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA/action/storage_attestation","attest_author":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA/action/author_attestation","sign_citation":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA/action/citation_signature","submit_replication":"https://pith.science/pith/TTXGKYRZNMSPCHE5LNI354FCDA/action/replication_record"}},"created_at":"2026-07-05T01:31:13.747973+00:00","updated_at":"2026-07-05T01:31:13.747973+00:00"}