{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VCXGM2XHW4T2VD2R45NVL73W6P","short_pith_number":"pith:VCXGM2XH","schema_version":"1.0","canonical_sha256":"a8ae666ae7b727aa8f51e75b55ff76f3dbf75cea84c6caa774810ecead48bd0e","source":{"kind":"arxiv","id":"2109.13305","version":1},"attestation_state":"computed","paper":{"title":"ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arshdeep Sekhon, Jake Grigsby, Yanjun Qi, Zhe Wang","submitted_at":"2021-09-27T18:54:50Z","abstract_excerpt":"Optimization-based meta-learning typically assumes tasks are sampled from a single distribution - an assumption oversimplifies and limits the diversity of tasks that meta-learning can model. Handling tasks from multiple different distributions is challenging for meta-learning due to a so-called task ambiguity issue. This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions. ST-MAML encodes tasks using a stochastic neural network module, that summarizes every task with a stochastic representation. The proposed Stocha"},"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":"2109.13305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T18:54:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8e0f2908f46963e94dfd426b404d28cfe2bc6dcf013479e0e1ee877d61402da4","abstract_canon_sha256":"57a0cad5ef5c8993bbf9e0d65315599cbbd0c9248986d2c48206e60c9d0ea9ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:01.476142Z","signature_b64":"nH/858zlgMZI32ojWva8oF5fi7GDHxGB+bOqk0kg8+QjAl/KJXwNR01D4tsswrcRvM1rq3a1dXwN1Zwc24DzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8ae666ae7b727aa8f51e75b55ff76f3dbf75cea84c6caa774810ecead48bd0e","last_reissued_at":"2026-07-05T03:18:01.475553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:01.475553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arshdeep Sekhon, Jake Grigsby, Yanjun Qi, Zhe Wang","submitted_at":"2021-09-27T18:54:50Z","abstract_excerpt":"Optimization-based meta-learning typically assumes tasks are sampled from a single distribution - an assumption oversimplifies and limits the diversity of tasks that meta-learning can model. Handling tasks from multiple different distributions is challenging for meta-learning due to a so-called task ambiguity issue. This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions. ST-MAML encodes tasks using a stochastic neural network module, that summarizes every task with a stochastic representation. The proposed Stocha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13305","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.13305/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":"2109.13305","created_at":"2026-07-05T03:18:01.475606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13305v1","created_at":"2026-07-05T03:18:01.475606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13305","created_at":"2026-07-05T03:18:01.475606+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCXGM2XHW4T2","created_at":"2026-07-05T03:18:01.475606+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCXGM2XHW4T2VD2R","created_at":"2026-07-05T03:18:01.475606+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCXGM2XH","created_at":"2026-07-05T03:18:01.475606+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/VCXGM2XHW4T2VD2R45NVL73W6P","json":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P.json","graph_json":"https://pith.science/api/pith-number/VCXGM2XHW4T2VD2R45NVL73W6P/graph.json","events_json":"https://pith.science/api/pith-number/VCXGM2XHW4T2VD2R45NVL73W6P/events.json","paper":"https://pith.science/paper/VCXGM2XH"},"agent_actions":{"view_html":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P","download_json":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P.json","view_paper":"https://pith.science/paper/VCXGM2XH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13305&json=true","fetch_graph":"https://pith.science/api/pith-number/VCXGM2XHW4T2VD2R45NVL73W6P/graph.json","fetch_events":"https://pith.science/api/pith-number/VCXGM2XHW4T2VD2R45NVL73W6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P/action/storage_attestation","attest_author":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P/action/author_attestation","sign_citation":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P/action/citation_signature","submit_replication":"https://pith.science/pith/VCXGM2XHW4T2VD2R45NVL73W6P/action/replication_record"}},"created_at":"2026-07-05T03:18:01.475606+00:00","updated_at":"2026-07-05T03:18:01.475606+00:00"}