{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O7MEP7BF24Z74CLR4B3TSMXBYB","short_pith_number":"pith:O7MEP7BF","schema_version":"1.0","canonical_sha256":"77d847fc25d733fe0971e0773932e1c07266b55b2923066e760edf03841f6ce5","source":{"kind":"arxiv","id":"1812.07172","version":1},"attestation_state":"computed","paper":{"title":"Toward Multimodal Model-Agnostic Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hexiang Hu, Joseph J. Lim, Risto Vuorio, Shao-Hua Sun","submitted_at":"2018-12-18T05:08:54Z","abstract_excerpt":"Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML alg"},"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":"1812.07172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T05:08:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e1b2ff87f2f683823e3617d3cfbcd76ab3b59878d46617c9a4a31b0b81888b3c","abstract_canon_sha256":"2ac169fc4e2e0d7db879c364f0c385772312e3425ad6451dae458276995e3fb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:07.763265Z","signature_b64":"Peep6tBhpdov8cytIx3JfiaNdDWEbO8un7+tfhj0qHDyXeVIsidoeuLx7wDG+O/vtSBe1EBKm5dquXEG9BXlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d847fc25d733fe0971e0773932e1c07266b55b2923066e760edf03841f6ce5","last_reissued_at":"2026-05-17T23:58:07.762837Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:07.762837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Multimodal Model-Agnostic Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hexiang Hu, Joseph J. Lim, Risto Vuorio, Shao-Hua Sun","submitted_at":"2018-12-18T05:08:54Z","abstract_excerpt":"Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07172","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.07172","created_at":"2026-05-17T23:58:07.762897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07172v1","created_at":"2026-05-17T23:58:07.762897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07172","created_at":"2026-05-17T23:58:07.762897+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7MEP7BF24Z7","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7MEP7BF24Z74CLR","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7MEP7BF","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB","json":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB.json","graph_json":"https://pith.science/api/pith-number/O7MEP7BF24Z74CLR4B3TSMXBYB/graph.json","events_json":"https://pith.science/api/pith-number/O7MEP7BF24Z74CLR4B3TSMXBYB/events.json","paper":"https://pith.science/paper/O7MEP7BF"},"agent_actions":{"view_html":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB","download_json":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB.json","view_paper":"https://pith.science/paper/O7MEP7BF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07172&json=true","fetch_graph":"https://pith.science/api/pith-number/O7MEP7BF24Z74CLR4B3TSMXBYB/graph.json","fetch_events":"https://pith.science/api/pith-number/O7MEP7BF24Z74CLR4B3TSMXBYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB/action/storage_attestation","attest_author":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB/action/author_attestation","sign_citation":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB/action/citation_signature","submit_replication":"https://pith.science/pith/O7MEP7BF24Z74CLR4B3TSMXBYB/action/replication_record"}},"created_at":"2026-05-17T23:58:07.762897+00:00","updated_at":"2026-05-17T23:58:07.762897+00:00"}