{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MI7XTEBMIWKGMHTMJSBIKCABIT","short_pith_number":"pith:MI7XTEBM","schema_version":"1.0","canonical_sha256":"623f79902c4594661e6c4c8285080144faffd3e6caec65887ae9bc60dfa577d5","source":{"kind":"arxiv","id":"2309.06588","version":2},"attestation_state":"computed","paper":{"title":"Convergence of Gradient-based MAML in LQR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Geir E. Dullerud, Negin Musavi","submitted_at":"2023-09-12T20:24:37Z","abstract_excerpt":"The main objective of this research paper is to investigate the local convergence characteristics of Model-agnostic Meta-learning (MAML) when applied to linear system quadratic optimal control (LQR). MAML and its variations have become popular techniques for quickly adapting to new tasks by leveraging previous learning knowledge in areas like regression, classification, and reinforcement learning. However, its theoretical guarantees remain unknown due to non-convexity and its structure, making it even more challenging to ensure stability in the dynamic system setting. This study focuses on exp"},"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":"2309.06588","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-09-12T20:24:37Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"e89d7ef453e28f7a1b10bd9c3ce82e1bd57e4c78e97b1aea3d7e706b18699015","abstract_canon_sha256":"d8caada14834a0ccb66c2ddd926aadc34916cc93ccdc8f49b3e14c563a681eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:58.759027Z","signature_b64":"Tzqsf2iN5RHb9g/lCFTmAWaX4H88l+jnc2vMOssISVA95162FT1YOqaoP+fOuGwrL88dT5dshzirVy/8ZSboDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623f79902c4594661e6c4c8285080144faffd3e6caec65887ae9bc60dfa577d5","last_reissued_at":"2026-07-05T06:50:58.758544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:58.758544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Gradient-based MAML in LQR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Geir E. Dullerud, Negin Musavi","submitted_at":"2023-09-12T20:24:37Z","abstract_excerpt":"The main objective of this research paper is to investigate the local convergence characteristics of Model-agnostic Meta-learning (MAML) when applied to linear system quadratic optimal control (LQR). MAML and its variations have become popular techniques for quickly adapting to new tasks by leveraging previous learning knowledge in areas like regression, classification, and reinforcement learning. However, its theoretical guarantees remain unknown due to non-convexity and its structure, making it even more challenging to ensure stability in the dynamic system setting. This study focuses on exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06588","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/2309.06588/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":"2309.06588","created_at":"2026-07-05T06:50:58.758626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06588v2","created_at":"2026-07-05T06:50:58.758626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06588","created_at":"2026-07-05T06:50:58.758626+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI7XTEBMIWKG","created_at":"2026-07-05T06:50:58.758626+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI7XTEBMIWKGMHTM","created_at":"2026-07-05T06:50:58.758626+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI7XTEBM","created_at":"2026-07-05T06:50:58.758626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02332","citing_title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT","json":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT.json","graph_json":"https://pith.science/api/pith-number/MI7XTEBMIWKGMHTMJSBIKCABIT/graph.json","events_json":"https://pith.science/api/pith-number/MI7XTEBMIWKGMHTMJSBIKCABIT/events.json","paper":"https://pith.science/paper/MI7XTEBM"},"agent_actions":{"view_html":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT","download_json":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT.json","view_paper":"https://pith.science/paper/MI7XTEBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06588&json=true","fetch_graph":"https://pith.science/api/pith-number/MI7XTEBMIWKGMHTMJSBIKCABIT/graph.json","fetch_events":"https://pith.science/api/pith-number/MI7XTEBMIWKGMHTMJSBIKCABIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT/action/storage_attestation","attest_author":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT/action/author_attestation","sign_citation":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT/action/citation_signature","submit_replication":"https://pith.science/pith/MI7XTEBMIWKGMHTMJSBIKCABIT/action/replication_record"}},"created_at":"2026-07-05T06:50:58.758626+00:00","updated_at":"2026-07-05T06:50:58.758626+00:00"}