{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YO2NQVXCLY6G55JFYJOSDAJPBM","short_pith_number":"pith:YO2NQVXC","schema_version":"1.0","canonical_sha256":"c3b4d856e25e3c6ef525c25d21812f0b02991716667d1d0be32316dc52baa011","source":{"kind":"arxiv","id":"2105.04504","version":2},"attestation_state":"computed","paper":{"title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl Henrik Ek, James Hensman, Mark van der Wilk, Nicolas Durrande, Vincent Dutordoir, Zoubin Ghahramani","submitted_at":"2021-05-10T16:55:17Z","abstract_excerpt":"Neural networks and Gaussian processes are complementary in their strengths and weaknesses. Having a better understanding of their relationship comes with the promise to make each method benefit from the strengths of the other. In this work, we establish an equivalence between the forward passes of neural networks and (deep) sparse Gaussian process models. The theory we develop is based on interpreting activation functions as interdomain inducing features through a rigorous analysis of the interplay between activation functions and kernels. This results in models that can either be seen as neu"},"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":"2105.04504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-05-10T16:55:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab6a52048c408011af70b7d3f7f1cb9f566be04f7562120b330c3ef69cf7871b","abstract_canon_sha256":"9d495324d4d3cc6aab9bb5be670ccf78b56195232e5b3a3ed758b8337e4434c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:14.737757Z","signature_b64":"ANz1AQ3YCIFpaHMcgs1NdqpYGBhi2Xi/UvuPq64+BUBLiuo/1+r3uQ+gqdC1nSIVaZ1qs6MccemwFc4FtsS6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3b4d856e25e3c6ef525c25d21812f0b02991716667d1d0be32316dc52baa011","last_reissued_at":"2026-07-05T03:39:14.737121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:14.737121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl Henrik Ek, James Hensman, Mark van der Wilk, Nicolas Durrande, Vincent Dutordoir, Zoubin Ghahramani","submitted_at":"2021-05-10T16:55:17Z","abstract_excerpt":"Neural networks and Gaussian processes are complementary in their strengths and weaknesses. Having a better understanding of their relationship comes with the promise to make each method benefit from the strengths of the other. In this work, we establish an equivalence between the forward passes of neural networks and (deep) sparse Gaussian process models. The theory we develop is based on interpreting activation functions as interdomain inducing features through a rigorous analysis of the interplay between activation functions and kernels. This results in models that can either be seen as neu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04504","kind":"arxiv","version":2},"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/2105.04504/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":"2105.04504","created_at":"2026-07-05T03:39:14.737192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04504v2","created_at":"2026-07-05T03:39:14.737192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04504","created_at":"2026-07-05T03:39:14.737192+00:00"},{"alias_kind":"pith_short_12","alias_value":"YO2NQVXCLY6G","created_at":"2026-07-05T03:39:14.737192+00:00"},{"alias_kind":"pith_short_16","alias_value":"YO2NQVXCLY6G55JF","created_at":"2026-07-05T03:39:14.737192+00:00"},{"alias_kind":"pith_short_8","alias_value":"YO2NQVXC","created_at":"2026-07-05T03:39:14.737192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09716","citing_title":"Medical Model Synthesis Architectures: A Case Study","ref_index":297,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM","json":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM.json","graph_json":"https://pith.science/api/pith-number/YO2NQVXCLY6G55JFYJOSDAJPBM/graph.json","events_json":"https://pith.science/api/pith-number/YO2NQVXCLY6G55JFYJOSDAJPBM/events.json","paper":"https://pith.science/paper/YO2NQVXC"},"agent_actions":{"view_html":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM","download_json":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM.json","view_paper":"https://pith.science/paper/YO2NQVXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04504&json=true","fetch_graph":"https://pith.science/api/pith-number/YO2NQVXCLY6G55JFYJOSDAJPBM/graph.json","fetch_events":"https://pith.science/api/pith-number/YO2NQVXCLY6G55JFYJOSDAJPBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM/action/storage_attestation","attest_author":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM/action/author_attestation","sign_citation":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM/action/citation_signature","submit_replication":"https://pith.science/pith/YO2NQVXCLY6G55JFYJOSDAJPBM/action/replication_record"}},"created_at":"2026-07-05T03:39:14.737192+00:00","updated_at":"2026-07-05T03:39:14.737192+00:00"}