{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F2ETASIMJ2P4GR6YJMLG4EXIUA","short_pith_number":"pith:F2ETASIM","schema_version":"1.0","canonical_sha256":"2e8930490c4e9fc347d84b166e12e8a03684f0ca8d546a351e8c97ee772cdbdd","source":{"kind":"arxiv","id":"2104.05674","version":1},"attestation_state":"computed","paper":{"title":"GPflux: A Library for Deep Gaussian Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artem Artemev, Eric Hambro, Felix Leibfried, Hugh Salimbeni, James Hensman, John Mcleod, Marc P. Deisenroth, Mark van der Wilk, ST John, Vincent Dutordoir","submitted_at":"2021-04-12T17:41:18Z","abstract_excerpt":"We introduce GPflux, a Python library for Bayesian deep learning with a strong emphasis on deep Gaussian processes (DGPs). Implementing DGPs is a challenging endeavour due to the various mathematical subtleties that arise when dealing with multivariate Gaussian distributions and the complex bookkeeping of indices. To date, there are no actively maintained, open-sourced and extendable libraries available that support research activities in this area. GPflux aims to fill this gap by providing a library with state-of-the-art DGP algorithms, as well as building blocks for implementing novel Bayesi"},"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":"2104.05674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-04-12T17:41:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4af09c195f3b2b64e4196e1419d6dc4474305a574c4d6a207279899d7e821c0d","abstract_canon_sha256":"98dfc48c39b3bb2b17a9de2a9e38a08f64c7c0c0c1cdc58ff270720697089b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:15.124739Z","signature_b64":"1ZXponl2t5pGVD+7JHMY3iLTBklMvlEd+9kF+S4wbmS20cNeHiU5TG6ZQolymsF7tygJgHRsBFNtmWeGcVfUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e8930490c4e9fc347d84b166e12e8a03684f0ca8d546a351e8c97ee772cdbdd","last_reissued_at":"2026-07-05T02:31:15.124232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:15.124232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPflux: A Library for Deep Gaussian Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artem Artemev, Eric Hambro, Felix Leibfried, Hugh Salimbeni, James Hensman, John Mcleod, Marc P. Deisenroth, Mark van der Wilk, ST John, Vincent Dutordoir","submitted_at":"2021-04-12T17:41:18Z","abstract_excerpt":"We introduce GPflux, a Python library for Bayesian deep learning with a strong emphasis on deep Gaussian processes (DGPs). Implementing DGPs is a challenging endeavour due to the various mathematical subtleties that arise when dealing with multivariate Gaussian distributions and the complex bookkeeping of indices. To date, there are no actively maintained, open-sourced and extendable libraries available that support research activities in this area. GPflux aims to fill this gap by providing a library with state-of-the-art DGP algorithms, as well as building blocks for implementing novel Bayesi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05674","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/2104.05674/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":"2104.05674","created_at":"2026-07-05T02:31:15.124290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05674v1","created_at":"2026-07-05T02:31:15.124290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05674","created_at":"2026-07-05T02:31:15.124290+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2ETASIMJ2P4","created_at":"2026-07-05T02:31:15.124290+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2ETASIMJ2P4GR6Y","created_at":"2026-07-05T02:31:15.124290+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2ETASIM","created_at":"2026-07-05T02:31:15.124290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25882","citing_title":"An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA","json":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA.json","graph_json":"https://pith.science/api/pith-number/F2ETASIMJ2P4GR6YJMLG4EXIUA/graph.json","events_json":"https://pith.science/api/pith-number/F2ETASIMJ2P4GR6YJMLG4EXIUA/events.json","paper":"https://pith.science/paper/F2ETASIM"},"agent_actions":{"view_html":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA","download_json":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA.json","view_paper":"https://pith.science/paper/F2ETASIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05674&json=true","fetch_graph":"https://pith.science/api/pith-number/F2ETASIMJ2P4GR6YJMLG4EXIUA/graph.json","fetch_events":"https://pith.science/api/pith-number/F2ETASIMJ2P4GR6YJMLG4EXIUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA/action/storage_attestation","attest_author":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA/action/author_attestation","sign_citation":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA/action/citation_signature","submit_replication":"https://pith.science/pith/F2ETASIMJ2P4GR6YJMLG4EXIUA/action/replication_record"}},"created_at":"2026-07-05T02:31:15.124290+00:00","updated_at":"2026-07-05T02:31:15.124290+00:00"}