{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HLUFAHR2TZUZA2ZMXTWY2Z4JTF","short_pith_number":"pith:HLUFAHR2","schema_version":"1.0","canonical_sha256":"3ae8501e3a9e69906b2cbced8d67899940030d4ba3f846ac9aba1de42a8e0701","source":{"kind":"arxiv","id":"2206.03996","version":4},"attestation_state":"computed","paper":{"title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lisha Chen, Momin Abbas, Pin-Yu Chen, Quan Xiao, Tianyi Chen","submitted_at":"2022-06-08T16:20:11Z","abstract_excerpt":"Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem structure. Specifically, the loss landscape of MAML is much more complex with possibly more saddle points and local minimizers than its empirical risk minimization counterpart. To address this challenge, we leverage the recently invented sharpness-aware minimization and develop a sharpness-aware MAML approach that we term Sharp-MAML. We empirically demonstrate that Sharp-MAML and its"},"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":"2206.03996","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T16:20:11Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"efb6a1826b5905f6694a97b4d1bdfc2a3de904d4b1305db354effb60dcf7e2e3","abstract_canon_sha256":"3600f4dfac9b8e22f93ba53047a859adac8bd486434f2d5587bc1587e38e6272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:13.869699Z","signature_b64":"o9cX2U09evlxssFctcVH9QhFZpjLtizZTSaB/EQ+E3OPby5remOoN8ijNTPxpGrbuW6/oD+9lU/FYI36yjdeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ae8501e3a9e69906b2cbced8d67899940030d4ba3f846ac9aba1de42a8e0701","last_reissued_at":"2026-07-05T04:48:13.869190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:13.869190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lisha Chen, Momin Abbas, Pin-Yu Chen, Quan Xiao, Tianyi Chen","submitted_at":"2022-06-08T16:20:11Z","abstract_excerpt":"Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem structure. Specifically, the loss landscape of MAML is much more complex with possibly more saddle points and local minimizers than its empirical risk minimization counterpart. To address this challenge, we leverage the recently invented sharpness-aware minimization and develop a sharpness-aware MAML approach that we term Sharp-MAML. We empirically demonstrate that Sharp-MAML and its"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03996","kind":"arxiv","version":4},"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/2206.03996/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":"2206.03996","created_at":"2026-07-05T04:48:13.869261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03996v4","created_at":"2026-07-05T04:48:13.869261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03996","created_at":"2026-07-05T04:48:13.869261+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLUFAHR2TZUZ","created_at":"2026-07-05T04:48:13.869261+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLUFAHR2TZUZA2ZM","created_at":"2026-07-05T04:48:13.869261+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLUFAHR2","created_at":"2026-07-05T04:48:13.869261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.00066","citing_title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF","json":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF.json","graph_json":"https://pith.science/api/pith-number/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/graph.json","events_json":"https://pith.science/api/pith-number/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/events.json","paper":"https://pith.science/paper/HLUFAHR2"},"agent_actions":{"view_html":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF","download_json":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF.json","view_paper":"https://pith.science/paper/HLUFAHR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03996&json=true","fetch_graph":"https://pith.science/api/pith-number/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/graph.json","fetch_events":"https://pith.science/api/pith-number/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/action/storage_attestation","attest_author":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/action/author_attestation","sign_citation":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/action/citation_signature","submit_replication":"https://pith.science/pith/HLUFAHR2TZUZA2ZMXTWY2Z4JTF/action/replication_record"}},"created_at":"2026-07-05T04:48:13.869261+00:00","updated_at":"2026-07-05T04:48:13.869261+00:00"}