{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N6A7PEFIWMNSPTRLQBWTDSL3GP","short_pith_number":"pith:N6A7PEFI","schema_version":"1.0","canonical_sha256":"6f81f790a8b31b27ce2b806d31c97b33fedffc2eee2a62fd7981f6923f07e8a5","source":{"kind":"arxiv","id":"2505.16481","version":3},"attestation_state":"computed","paper":{"title":"Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mauricio A. \\'Alvarez, Xiaoyu Jiang, Xinxing Shi","submitted_at":"2025-05-22T10:07:33Z","abstract_excerpt":"Gaussian Process (GP) Variational Autoencoders (VAEs) extend standard VAEs by replacing the fully factorised Gaussian prior with a GP prior, thereby capturing richer correlations among latent variables. However, performing exact GP inference in large-scale GPVAEs is computationally prohibitive, often forcing existing approaches to rely on restrictive kernel assumptions or large sets of inducing points. In this work, we propose a neighbour-driven approximation strategy that exploits local adjacencies in the latent space to achieve scalable GPVAE inference. By confining computations to the neare"},"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":"2505.16481","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T10:07:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"875c69ac76474770a40f27736188b339832cfece1cfdaccddb8295835e44a174","abstract_canon_sha256":"5e31789990b8a05cb3d6fd95ea53e50fbe40bf5b829644753ecac0790e313c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:12.142063Z","signature_b64":"iFvZOCqvm8AtJSjqYVnxAOFZGRIqQnXuLDpy9qNiVHkUDMx3aL3vbLf5tlemQBb9zvPdO7FnfKLqVVhCJ4MODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f81f790a8b31b27ce2b806d31c97b33fedffc2eee2a62fd7981f6923f07e8a5","last_reissued_at":"2026-07-05T11:54:12.141631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:12.141631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mauricio A. \\'Alvarez, Xiaoyu Jiang, Xinxing Shi","submitted_at":"2025-05-22T10:07:33Z","abstract_excerpt":"Gaussian Process (GP) Variational Autoencoders (VAEs) extend standard VAEs by replacing the fully factorised Gaussian prior with a GP prior, thereby capturing richer correlations among latent variables. However, performing exact GP inference in large-scale GPVAEs is computationally prohibitive, often forcing existing approaches to rely on restrictive kernel assumptions or large sets of inducing points. In this work, we propose a neighbour-driven approximation strategy that exploits local adjacencies in the latent space to achieve scalable GPVAE inference. By confining computations to the neare"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16481","kind":"arxiv","version":3},"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/2505.16481/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":"2505.16481","created_at":"2026-07-05T11:54:12.141690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16481v3","created_at":"2026-07-05T11:54:12.141690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16481","created_at":"2026-07-05T11:54:12.141690+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6A7PEFIWMNS","created_at":"2026-07-05T11:54:12.141690+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6A7PEFIWMNSPTRL","created_at":"2026-07-05T11:54:12.141690+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6A7PEFI","created_at":"2026-07-05T11:54:12.141690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP","json":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP.json","graph_json":"https://pith.science/api/pith-number/N6A7PEFIWMNSPTRLQBWTDSL3GP/graph.json","events_json":"https://pith.science/api/pith-number/N6A7PEFIWMNSPTRLQBWTDSL3GP/events.json","paper":"https://pith.science/paper/N6A7PEFI"},"agent_actions":{"view_html":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP","download_json":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP.json","view_paper":"https://pith.science/paper/N6A7PEFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16481&json=true","fetch_graph":"https://pith.science/api/pith-number/N6A7PEFIWMNSPTRLQBWTDSL3GP/graph.json","fetch_events":"https://pith.science/api/pith-number/N6A7PEFIWMNSPTRLQBWTDSL3GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP/action/storage_attestation","attest_author":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP/action/author_attestation","sign_citation":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP/action/citation_signature","submit_replication":"https://pith.science/pith/N6A7PEFIWMNSPTRLQBWTDSL3GP/action/replication_record"}},"created_at":"2026-07-05T11:54:12.141690+00:00","updated_at":"2026-07-05T11:54:12.141690+00:00"}