{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZPBMUAQUIYD4K67CXODV2DPX37","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":"b5ce73146521f3841e0b3f284470f496f2b1b000a6e6ba729a441fae39a4bac2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T18:26:53Z","title_canon_sha256":"b5d486b786d3367761e05fe40dddb77e35f6bd5357269e625b292dbcdd1878fb"},"schema_version":"1.0","source":{"id":"1905.06982","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06982","created_at":"2026-05-17T23:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06982v1","created_at":"2026-05-17T23:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06982","created_at":"2026-05-17T23:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZPBMUAQUIYD4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZPBMUAQUIYD4K67C","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZPBMUAQU","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:2b09b39becc7cd6016012c78993cb9161876671176fd2658959d7eba39077667","target":"graph","created_at":"2026-05-17T23:45:57Z","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 Gaussian processes (DGP) have appealing Bayesian properties, can handle variable-sized data, and learn deep features. Their limitation is that they do not scale well with the size of the data. Existing approaches address this using a deep random feature (DRF) expansion model, which makes inference tractable by approximating DGPs. However, DRF is not suitable for variable-sized input data such as trees, graphs, and sequences. We introduce the GP-DRF, a novel Bayesian model with an input layer of GPs, followed by DRF layers. The key advantage is that the combination of GP and DRF leads to a","authors_text":"Issam H. Laradji, Mark Schmidt, Minyoung Kim, Vladimir Pavlovic","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T18:26:53Z","title":"Efficient Deep Gaussian Process Models for Variable-Sized Input"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06982","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":"sha256:9f87f1cb42301c3183dc82dfe6e9254ad6e84f2512fe4ac58467d6404f5c9dd2","target":"record","created_at":"2026-05-17T23:45:57Z","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":"b5ce73146521f3841e0b3f284470f496f2b1b000a6e6ba729a441fae39a4bac2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T18:26:53Z","title_canon_sha256":"b5d486b786d3367761e05fe40dddb77e35f6bd5357269e625b292dbcdd1878fb"},"schema_version":"1.0","source":{"id":"1905.06982","kind":"arxiv","version":1}},"canonical_sha256":"cbc2ca02144607c57be2bb875d0df7dfeb172576bc97334e0f0681e4be8d0198","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbc2ca02144607c57be2bb875d0df7dfeb172576bc97334e0f0681e4be8d0198","first_computed_at":"2026-05-17T23:45:57.592708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:57.592708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AlDDUVSIQIVFtg201pl5QLkiiiPEnCBIDUraY8E6urasCDFXgn+k+K6cQs5KkexofOFg+WYtzHyPAwwgbFrBCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:57.593192Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06982","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f87f1cb42301c3183dc82dfe6e9254ad6e84f2512fe4ac58467d6404f5c9dd2","sha256:2b09b39becc7cd6016012c78993cb9161876671176fd2658959d7eba39077667"],"state_sha256":"c7a9a7ff7667ee0c3e2819f1be8f2d56a520653c3f8eba5e387235892cddcbb1"}