{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2RBCINDFTHCB53VJTR545QYLV7","short_pith_number":"pith:2RBCINDF","schema_version":"1.0","canonical_sha256":"d44224346599c41eeea99c7bcec30bafce72841b7a0a08232231c6e5da87a038","source":{"kind":"arxiv","id":"1901.05761","version":2},"attestation_state":"computed","paper":{"title":"Attentive Neural Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Eslami, Andriy Mnih, Dan Rosenbaum, Hyunjik Kim, Jonathan Schwarz, Marta Garnelo, Oriol Vinyals, Yee Whye Teh","submitted_at":"2019-01-17T12:37:26Z","abstract_excerpt":"Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, conditioned on the context. NPs have the benefit of fitting observed data efficiently with linear complexity in the number of context input-output pairs, and can learn a wide family of conditional distributions; they learn predictive distributions conditioned on context sets of arbitrary size. Nonetheless, we show that NPs suffer a fundamental drawback o"},"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":"1901.05761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-17T12:37:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"07999d05ced4fb462726157def71df073a21e9f41341493413c9ab7320b520aa","abstract_canon_sha256":"ec9e2acc6fe06cf09d0757208bd78825610c3dc558430d07a507299749b29ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:12.268900Z","signature_b64":"r46uhKWsAepAhQ+hpBa+fqUbOkhCvkjq4Y84/E8u9bLSe+Yuq4PTzMtlQaScY9jNm1wPPd/PpXetyY9LGKqrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d44224346599c41eeea99c7bcec30bafce72841b7a0a08232231c6e5da87a038","last_reissued_at":"2026-05-17T23:41:12.268274Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:12.268274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attentive Neural Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Eslami, Andriy Mnih, Dan Rosenbaum, Hyunjik Kim, Jonathan Schwarz, Marta Garnelo, Oriol Vinyals, Yee Whye Teh","submitted_at":"2019-01-17T12:37:26Z","abstract_excerpt":"Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, conditioned on the context. NPs have the benefit of fitting observed data efficiently with linear complexity in the number of context input-output pairs, and can learn a wide family of conditional distributions; they learn predictive distributions conditioned on context sets of arbitrary size. Nonetheless, we show that NPs suffer a fundamental drawback o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05761","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":""},"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":"1901.05761","created_at":"2026-05-17T23:41:12.268382+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.05761v2","created_at":"2026-05-17T23:41:12.268382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05761","created_at":"2026-05-17T23:41:12.268382+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RBCINDFTHCB","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RBCINDFTHCB53VJ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RBCINDF","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09498","citing_title":"Spectral Transformer Neural Processes","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25732","citing_title":"Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":155,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7","json":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7.json","graph_json":"https://pith.science/api/pith-number/2RBCINDFTHCB53VJTR545QYLV7/graph.json","events_json":"https://pith.science/api/pith-number/2RBCINDFTHCB53VJTR545QYLV7/events.json","paper":"https://pith.science/paper/2RBCINDF"},"agent_actions":{"view_html":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7","download_json":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7.json","view_paper":"https://pith.science/paper/2RBCINDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.05761&json=true","fetch_graph":"https://pith.science/api/pith-number/2RBCINDFTHCB53VJTR545QYLV7/graph.json","fetch_events":"https://pith.science/api/pith-number/2RBCINDFTHCB53VJTR545QYLV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7/action/storage_attestation","attest_author":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7/action/author_attestation","sign_citation":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7/action/citation_signature","submit_replication":"https://pith.science/pith/2RBCINDFTHCB53VJTR545QYLV7/action/replication_record"}},"created_at":"2026-05-17T23:41:12.268382+00:00","updated_at":"2026-05-17T23:41:12.268382+00:00"}