{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LOGUJVVKASQTCLHTGI6M6DLEJO","short_pith_number":"pith:LOGUJVVK","schema_version":"1.0","canonical_sha256":"5b8d44d6aa04a1312cf3323ccf0d644bbac3e6efeeee6d2b19dd7a6f294fd484","source":{"kind":"arxiv","id":"2002.06873","version":6},"attestation_state":"computed","paper":{"title":"$\\pi$VAE: a stochastic process prior for Bayesian deep learning with MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Harrison Zhu, Mikko Pakkanen, Samir Bhatt, Seth Flaxman, Swapnil Mishra, Tresnia Berah","submitted_at":"2020-02-17T10:23:18Z","abstract_excerpt":"Stochastic processes provide a mathematically elegant way model complex data. In theory, they provide flexible priors over function classes that can encode a wide range of interesting assumptions. In practice, however, efficient inference by optimisation or marginalisation is difficult, a problem further exacerbated with big data and high dimensional input spaces. We propose a novel variational autoencoder (VAE) called the prior encoding variational autoencoder ($\\pi$VAE). The $\\pi$VAE is finitely exchangeable and Kolmogorov consistent, and thus is a continuous stochastic process. We use $\\pi$"},"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":"2002.06873","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T10:23:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6bc6ac9d4dea7bfec6f4a5a0c1f275c2f9049fee8db10424177f7f1e749db398","abstract_canon_sha256":"c8e709baf4d5085ce6623b10bc8a5aa812a0c94c1edb81f9fc8fb7609b8f416b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:21.531459Z","signature_b64":"2PBxNbVjC3p5pKEE844ofL+omKInJr0Dk0PLddEy373oDZo/Jm0bcscUSq3wQ/zMryiwbDieIORo5tgXe7CnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8d44d6aa04a1312cf3323ccf0d644bbac3e6efeeee6d2b19dd7a6f294fd484","last_reissued_at":"2026-07-05T04:57:21.530891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:21.530891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\pi$VAE: a stochastic process prior for Bayesian deep learning with MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Harrison Zhu, Mikko Pakkanen, Samir Bhatt, Seth Flaxman, Swapnil Mishra, Tresnia Berah","submitted_at":"2020-02-17T10:23:18Z","abstract_excerpt":"Stochastic processes provide a mathematically elegant way model complex data. In theory, they provide flexible priors over function classes that can encode a wide range of interesting assumptions. In practice, however, efficient inference by optimisation or marginalisation is difficult, a problem further exacerbated with big data and high dimensional input spaces. We propose a novel variational autoencoder (VAE) called the prior encoding variational autoencoder ($\\pi$VAE). The $\\pi$VAE is finitely exchangeable and Kolmogorov consistent, and thus is a continuous stochastic process. We use $\\pi$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06873","kind":"arxiv","version":6},"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/2002.06873/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":"2002.06873","created_at":"2026-07-05T04:57:21.530971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06873v6","created_at":"2026-07-05T04:57:21.530971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06873","created_at":"2026-07-05T04:57:21.530971+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOGUJVVKASQT","created_at":"2026-07-05T04:57:21.530971+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOGUJVVKASQTCLHT","created_at":"2026-07-05T04:57:21.530971+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOGUJVVK","created_at":"2026-07-05T04:57:21.530971+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/LOGUJVVKASQTCLHTGI6M6DLEJO","json":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO.json","graph_json":"https://pith.science/api/pith-number/LOGUJVVKASQTCLHTGI6M6DLEJO/graph.json","events_json":"https://pith.science/api/pith-number/LOGUJVVKASQTCLHTGI6M6DLEJO/events.json","paper":"https://pith.science/paper/LOGUJVVK"},"agent_actions":{"view_html":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO","download_json":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO.json","view_paper":"https://pith.science/paper/LOGUJVVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06873&json=true","fetch_graph":"https://pith.science/api/pith-number/LOGUJVVKASQTCLHTGI6M6DLEJO/graph.json","fetch_events":"https://pith.science/api/pith-number/LOGUJVVKASQTCLHTGI6M6DLEJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO/action/storage_attestation","attest_author":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO/action/author_attestation","sign_citation":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO/action/citation_signature","submit_replication":"https://pith.science/pith/LOGUJVVKASQTCLHTGI6M6DLEJO/action/replication_record"}},"created_at":"2026-07-05T04:57:21.530971+00:00","updated_at":"2026-07-05T04:57:21.530971+00:00"}