{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O32VZDF774ZABHUKAZOXZ7LVAR","short_pith_number":"pith:O32VZDF7","schema_version":"1.0","canonical_sha256":"76f55c8cbfff32009e8a065d7cfd750455f3ab4bc8f39c8ec7979b3e57ac4f10","source":{"kind":"arxiv","id":"1805.09921","version":4},"attestation_state":"computed","paper":{"title":"Meta-Learning Probabilistic Inference For Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"John Bronskill, Jonathan Gordon, Matthias Bauer, Richard E. Turner, Sebastian Nowozin","submitted_at":"2018-05-24T22:08:27Z","abstract_excerpt":"This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class of methods. 2) We introduce VERSA, an instance of the framework employing a flexible and versatile amortization network that takes few-shot learning datasets as inputs, with arbitrary numbers of shots, and outputs a distribution over task-specific parameters in a single forward pass. VERSA substitu"},"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":"1805.09921","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T22:08:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e99dcfa7912edbff7b14134f9d89e26e6d0f1c45ab3e0cf673a389083f582b0","abstract_canon_sha256":"0d8abecc7d41c9bfa3c7d5065d731508a82cebb5d87c21a14b2e837bf55dd798"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:55.080433Z","signature_b64":"FQ+F+eyowHhV1xLZ0KsalXUQ4cgnbef4HF7BgUwUWl0GBxKKCcYP5+fLbsnkVKV06mvaNQEOKKzc7O1mhXQZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76f55c8cbfff32009e8a065d7cfd750455f3ab4bc8f39c8ec7979b3e57ac4f10","last_reissued_at":"2026-07-05T01:17:55.080077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:55.080077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning Probabilistic Inference For Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"John Bronskill, Jonathan Gordon, Matthias Bauer, Richard E. Turner, Sebastian Nowozin","submitted_at":"2018-05-24T22:08:27Z","abstract_excerpt":"This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class of methods. 2) We introduce VERSA, an instance of the framework employing a flexible and versatile amortization network that takes few-shot learning datasets as inputs, with arbitrary numbers of shots, and outputs a distribution over task-specific parameters in a single forward pass. VERSA substitu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09921","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/1805.09921/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":"1805.09921","created_at":"2026-07-05T01:17:55.080132+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09921v4","created_at":"2026-07-05T01:17:55.080132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09921","created_at":"2026-07-05T01:17:55.080132+00:00"},{"alias_kind":"pith_short_12","alias_value":"O32VZDF774ZA","created_at":"2026-07-05T01:17:55.080132+00:00"},{"alias_kind":"pith_short_16","alias_value":"O32VZDF774ZABHUK","created_at":"2026-07-05T01:17:55.080132+00:00"},{"alias_kind":"pith_short_8","alias_value":"O32VZDF7","created_at":"2026-07-05T01:17:55.080132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07488","citing_title":"CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR","json":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR.json","graph_json":"https://pith.science/api/pith-number/O32VZDF774ZABHUKAZOXZ7LVAR/graph.json","events_json":"https://pith.science/api/pith-number/O32VZDF774ZABHUKAZOXZ7LVAR/events.json","paper":"https://pith.science/paper/O32VZDF7"},"agent_actions":{"view_html":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR","download_json":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR.json","view_paper":"https://pith.science/paper/O32VZDF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09921&json=true","fetch_graph":"https://pith.science/api/pith-number/O32VZDF774ZABHUKAZOXZ7LVAR/graph.json","fetch_events":"https://pith.science/api/pith-number/O32VZDF774ZABHUKAZOXZ7LVAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR/action/storage_attestation","attest_author":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR/action/author_attestation","sign_citation":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR/action/citation_signature","submit_replication":"https://pith.science/pith/O32VZDF774ZABHUKAZOXZ7LVAR/action/replication_record"}},"created_at":"2026-07-05T01:17:55.080132+00:00","updated_at":"2026-07-05T01:17:55.080132+00:00"}