{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HNHK77BURCN3HEQPGEHXD2PES3","short_pith_number":"pith:HNHK77BU","canonical_record":{"source":{"id":"1807.01613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:36:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5ef1faa30c1447462aa3ae3b4fee98aa5265841a9dca14afa40da9918d696188","abstract_canon_sha256":"f89bf270a384fb6c5cbdec8a1b8712c383a6109ae9c56a99682eb34a70119178"},"schema_version":"1.0"},"canonical_sha256":"3b4eaffc34889bb3920f310f71e9e496d98e920edd52dc0ba0f3c6e19f2da0ed","source":{"kind":"arxiv","id":"1807.01613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01613","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01613v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01613","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"HNHK77BURCN3","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HNHK77BURCN3HEQP","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HNHK77BU","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HNHK77BURCN3HEQPGEHXD2PES3","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:36:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5ef1faa30c1447462aa3ae3b4fee98aa5265841a9dca14afa40da9918d696188","abstract_canon_sha256":"f89bf270a384fb6c5cbdec8a1b8712c383a6109ae9c56a99682eb34a70119178"},"schema_version":"1.0"},"canonical_sha256":"3b4eaffc34889bb3920f310f71e9e496d98e920edd52dc0ba0f3c6e19f2da0ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:29.339873Z","signature_b64":"yvKSDYxaNaZ9xAlT7JA5qoG5c/AOTH0/J3Wp5r2KIILSSSA+FE/YM+gfzDmKr5+KoulhMPt8115fLPxV6FcEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b4eaffc34889bb3920f310f71e9e496d98e920edd52dc0ba0f3c6e19f2da0ed","last_reissued_at":"2026-05-18T00:11:29.339257Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:29.339257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01613","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T065Jo/RBmj5Gg3xM+ePDxq7B7MiYAO6Rssa0Cx7yg1vy18YKCJUpNkNo0b8B/z1fThGiY49d9Uq1V+hGV4WAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:57:06.794085Z"},"content_sha256":"a72114f2827e632450689bce35fad4e746e50fb62a82fd6e775b0459851760e1","schema_version":"1.0","event_id":"sha256:a72114f2827e632450689bce35fad4e746e50fb62a82fd6e775b0459851760e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HNHK77BURCN3HEQPGEHXD2PES3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Neural Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris J. Maddison, Danilo J. Rezende, Dan Rosenbaum, David Saxton, Marta Garnelo, Murray Shanahan, S. M. Ali Eslami, Tiago Ramalho, Yee Whye Teh","submitted_at":"2018-07-04T14:36:15Z","abstract_excerpt":"Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the shape of a new function at test time. Yet GPs are computationally expensive, and it can be hard to design appropriate priors. In this paper we propose a family of neural models, Conditional Neural Processes (CNPs), that combine the benefits of both. CNPs are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01613","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2O0onTxgFvm11X6q/AmzfoRFEu49Q4COFLY6LUdQyacLJiVTd1li/fCidivl7yiSryEu62vJ84eHDIswmQGUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:57:06.794507Z"},"content_sha256":"69d5c1ea78ad65c714bdbf865332af0903c6c33df15afa10277e8fd19789026f","schema_version":"1.0","event_id":"sha256:69d5c1ea78ad65c714bdbf865332af0903c6c33df15afa10277e8fd19789026f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HNHK77BURCN3HEQPGEHXD2PES3/bundle.json","state_url":"https://pith.science/pith/HNHK77BURCN3HEQPGEHXD2PES3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HNHK77BURCN3HEQPGEHXD2PES3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T07:57:06Z","links":{"resolver":"https://pith.science/pith/HNHK77BURCN3HEQPGEHXD2PES3","bundle":"https://pith.science/pith/HNHK77BURCN3HEQPGEHXD2PES3/bundle.json","state":"https://pith.science/pith/HNHK77BURCN3HEQPGEHXD2PES3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HNHK77BURCN3HEQPGEHXD2PES3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HNHK77BURCN3HEQPGEHXD2PES3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f89bf270a384fb6c5cbdec8a1b8712c383a6109ae9c56a99682eb34a70119178","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:36:15Z","title_canon_sha256":"5ef1faa30c1447462aa3ae3b4fee98aa5265841a9dca14afa40da9918d696188"},"schema_version":"1.0","source":{"id":"1807.01613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01613","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01613v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01613","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"HNHK77BURCN3","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HNHK77BURCN3HEQP","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HNHK77BU","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:69d5c1ea78ad65c714bdbf865332af0903c6c33df15afa10277e8fd19789026f","target":"graph","created_at":"2026-05-18T00:11:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the shape of a new function at test time. Yet GPs are computationally expensive, and it can be hard to design appropriate priors. In this paper we propose a family of neural models, Conditional Neural Processes (CNPs), that combine the benefits of both. CNPs are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks a","authors_text":"Chris J. Maddison, Danilo J. Rezende, Dan Rosenbaum, David Saxton, Marta Garnelo, Murray Shanahan, S. M. Ali Eslami, Tiago Ramalho, Yee Whye Teh","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:36:15Z","title":"Conditional Neural Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01613","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a72114f2827e632450689bce35fad4e746e50fb62a82fd6e775b0459851760e1","target":"record","created_at":"2026-05-18T00:11:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f89bf270a384fb6c5cbdec8a1b8712c383a6109ae9c56a99682eb34a70119178","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:36:15Z","title_canon_sha256":"5ef1faa30c1447462aa3ae3b4fee98aa5265841a9dca14afa40da9918d696188"},"schema_version":"1.0","source":{"id":"1807.01613","kind":"arxiv","version":1}},"canonical_sha256":"3b4eaffc34889bb3920f310f71e9e496d98e920edd52dc0ba0f3c6e19f2da0ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b4eaffc34889bb3920f310f71e9e496d98e920edd52dc0ba0f3c6e19f2da0ed","first_computed_at":"2026-05-18T00:11:29.339257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:29.339257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yvKSDYxaNaZ9xAlT7JA5qoG5c/AOTH0/J3Wp5r2KIILSSSA+FE/YM+gfzDmKr5+KoulhMPt8115fLPxV6FcEDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:29.339873Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a72114f2827e632450689bce35fad4e746e50fb62a82fd6e775b0459851760e1","sha256:69d5c1ea78ad65c714bdbf865332af0903c6c33df15afa10277e8fd19789026f"],"state_sha256":"44490f3f060d28e20e71dce6783338395eb664b5423545ec56672ba4c8512def"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H1H7HJbAc11KVibqYQ+J6EBomj/kDg9I8s59LqAr5tq2EEbIbl26obtL4B0WsuSNrE+a7CZ1WFWEY+0RUigCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:57:06.797990Z","bundle_sha256":"3103342fefda7d4bab6247682877c5b053d779c1098ab05e9b3eebe9a1ce024a"}}