{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WTOX25YB3IFQCX5VR2UWXFG2WY","short_pith_number":"pith:WTOX25YB","schema_version":"1.0","canonical_sha256":"b4dd7d7701da0b015fb58ea96b94dab62aec4038811f5c071774778c131719c7","source":{"kind":"arxiv","id":"2303.14468","version":1},"attestation_state":"computed","paper":{"title":"Autoregressive Conditional Neural Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, Anna Vaughan, Anthony Buonomo, James Requiema, J. Scott Hosking, Richard E. Turner, Stratis Markou, Tom R. Andersson, Wessel P. Bruinsma","submitted_at":"2023-03-25T13:34:12Z","abstract_excerpt":"Conditional neural processes (CNPs; Garnelo et al., 2018a) are attractive meta-learning models which produce well-calibrated predictions and are trainable via a simple maximum likelihood procedure. Although CNPs have many advantages, they are unable to model dependencies in their predictions. Various works propose solutions to this, but these come at the cost of either requiring approximate inference or being limited to Gaussian predictions. In this work, we instead propose to change how CNPs are deployed at test time, without any modifications to the model or training procedure. Instead of ma"},"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":"2303.14468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-03-25T13:34:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c71ca7b88d35fe88646764d5571d0359864670f13b46ff9bc00a9d5a93878d20","abstract_canon_sha256":"44f68649f0c608b2a453da244b3a61569990349efcbdd365cded1203fb01f992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:42.143346Z","signature_b64":"bdTjwbSS5CuebXQqZR23MEoFdLQbKA6mLQfLsgG9g24ZPmts+QbC7Oa+DJV1k7aHrDJ+RX+4PZzn0soIHejVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4dd7d7701da0b015fb58ea96b94dab62aec4038811f5c071774778c131719c7","last_reissued_at":"2026-07-05T05:54:42.142895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:42.142895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Conditional Neural Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, Anna Vaughan, Anthony Buonomo, James Requiema, J. Scott Hosking, Richard E. Turner, Stratis Markou, Tom R. Andersson, Wessel P. Bruinsma","submitted_at":"2023-03-25T13:34:12Z","abstract_excerpt":"Conditional neural processes (CNPs; Garnelo et al., 2018a) are attractive meta-learning models which produce well-calibrated predictions and are trainable via a simple maximum likelihood procedure. Although CNPs have many advantages, they are unable to model dependencies in their predictions. Various works propose solutions to this, but these come at the cost of either requiring approximate inference or being limited to Gaussian predictions. In this work, we instead propose to change how CNPs are deployed at test time, without any modifications to the model or training procedure. Instead of ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14468","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/2303.14468/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":"2303.14468","created_at":"2026-07-05T05:54:42.142950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14468v1","created_at":"2026-07-05T05:54:42.142950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14468","created_at":"2026-07-05T05:54:42.142950+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTOX25YB3IFQ","created_at":"2026-07-05T05:54:42.142950+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTOX25YB3IFQCX5V","created_at":"2026-07-05T05:54:42.142950+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTOX25YB","created_at":"2026-07-05T05:54:42.142950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27527","citing_title":"Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01172","citing_title":"Revisiting Neural Processes via Fourier Transform and Volterra Series","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2411.12502","citing_title":"Transformer Neural Processes - Kernel Regression","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY","json":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY.json","graph_json":"https://pith.science/api/pith-number/WTOX25YB3IFQCX5VR2UWXFG2WY/graph.json","events_json":"https://pith.science/api/pith-number/WTOX25YB3IFQCX5VR2UWXFG2WY/events.json","paper":"https://pith.science/paper/WTOX25YB"},"agent_actions":{"view_html":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY","download_json":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY.json","view_paper":"https://pith.science/paper/WTOX25YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14468&json=true","fetch_graph":"https://pith.science/api/pith-number/WTOX25YB3IFQCX5VR2UWXFG2WY/graph.json","fetch_events":"https://pith.science/api/pith-number/WTOX25YB3IFQCX5VR2UWXFG2WY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY/action/storage_attestation","attest_author":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY/action/author_attestation","sign_citation":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY/action/citation_signature","submit_replication":"https://pith.science/pith/WTOX25YB3IFQCX5VR2UWXFG2WY/action/replication_record"}},"created_at":"2026-07-05T05:54:42.142950+00:00","updated_at":"2026-07-05T05:54:42.142950+00:00"}