{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2JHNZTVMCVB2O62QJODC4HDZ26","short_pith_number":"pith:2JHNZTVM","schema_version":"1.0","canonical_sha256":"d24edcceac1543a77b504b862e1c79d7839fbda0fc26a43a7662ac299da6b5a3","source":{"kind":"arxiv","id":"1910.13556","version":5},"attestation_state":"computed","paper":{"title":"Convolutional 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, James Requeima, Jonathan Gordon, Richard E. Turner, Wessel P. Bruinsma, Yann Dubois","submitted_at":"2019-10-29T21:56:00Z","abstract_excerpt":"We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for many learning problems including time series modelling, spatial data, and images. The model embeds data sets into an infinite-dimensional function space as opposed to a finite-dimensional vector space. To formalize this notion, we extend the theory of neural representations of sets to include functional representations, and demonstrate that any translation-equivariant embeddin"},"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":"1910.13556","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-29T21:56:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15de110c00eb6f26c970af65925cd22d15e55b5532426458cac9f9b90baca774","abstract_canon_sha256":"cdcbfab271f12a57c7a57c9b247b2e480338df34249dc4d3d6011af5e1f75021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:23.962778Z","signature_b64":"8k7nYZa7a7gEwVljkNGkYElWcp2wyUSZCKIHdpW62EgQKf5Ex9SW9sZfH1tH1Bx5iuxUN3qQZMB/UqjA+A6yDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d24edcceac1543a77b504b862e1c79d7839fbda0fc26a43a7662ac299da6b5a3","last_reissued_at":"2026-07-05T01:13:23.962344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:23.962344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional 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, James Requeima, Jonathan Gordon, Richard E. Turner, Wessel P. Bruinsma, Yann Dubois","submitted_at":"2019-10-29T21:56:00Z","abstract_excerpt":"We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for many learning problems including time series modelling, spatial data, and images. The model embeds data sets into an infinite-dimensional function space as opposed to a finite-dimensional vector space. To formalize this notion, we extend the theory of neural representations of sets to include functional representations, and demonstrate that any translation-equivariant embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13556","kind":"arxiv","version":5},"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/1910.13556/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":"1910.13556","created_at":"2026-07-05T01:13:23.962403+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13556v5","created_at":"2026-07-05T01:13:23.962403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13556","created_at":"2026-07-05T01:13:23.962403+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JHNZTVMCVB2","created_at":"2026-07-05T01:13:23.962403+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JHNZTVMCVB2O62Q","created_at":"2026-07-05T01:13:23.962403+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JHNZTVM","created_at":"2026-07-05T01:13:23.962403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22346","citing_title":"Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03355","citing_title":"APIC: Amortized Physics-Informed Calibration using Neural Processes","ref_index":34,"is_internal_anchor":false},{"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01172","citing_title":"Revisiting Neural Processes via Fourier Transform and Volterra Series","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09498","citing_title":"Spectral Transformer Neural Processes","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08418","citing_title":"Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26","json":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26.json","graph_json":"https://pith.science/api/pith-number/2JHNZTVMCVB2O62QJODC4HDZ26/graph.json","events_json":"https://pith.science/api/pith-number/2JHNZTVMCVB2O62QJODC4HDZ26/events.json","paper":"https://pith.science/paper/2JHNZTVM"},"agent_actions":{"view_html":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26","download_json":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26.json","view_paper":"https://pith.science/paper/2JHNZTVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13556&json=true","fetch_graph":"https://pith.science/api/pith-number/2JHNZTVMCVB2O62QJODC4HDZ26/graph.json","fetch_events":"https://pith.science/api/pith-number/2JHNZTVMCVB2O62QJODC4HDZ26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26/action/storage_attestation","attest_author":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26/action/author_attestation","sign_citation":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26/action/citation_signature","submit_replication":"https://pith.science/pith/2JHNZTVMCVB2O62QJODC4HDZ26/action/replication_record"}},"created_at":"2026-07-05T01:13:23.962403+00:00","updated_at":"2026-07-05T01:13:23.962403+00:00"}