{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ZIGGQUVNFUVSSCFE3UH7J53NEO","short_pith_number":"pith:ZIGGQUVN","canonical_record":{"source":{"id":"1505.07765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-28T17:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"8d028b0b5af5e90cf84d552c3f4bce0d47bdc3e498b07a3b487e69acc4d716ac","abstract_canon_sha256":"cc8c28a919098bbaef7b3c06fe96ccec0fce95e36ab6a39d98cba36e7cd9ac2b"},"schema_version":"1.0"},"canonical_sha256":"ca0c6852ad2d2b2908a4dd0ff4f76d2389af1c2423e3e6ad6b30e5e2f812947b","source":{"kind":"arxiv","id":"1505.07765","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.07765","created_at":"2026-05-18T01:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"1505.07765v3","created_at":"2026-05-18T01:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.07765","created_at":"2026-05-18T01:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZIGGQUVNFUVS","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZIGGQUVNFUVSSCFE","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZIGGQUVN","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ZIGGQUVNFUVSSCFE3UH7J53NEO","target":"record","payload":{"canonical_record":{"source":{"id":"1505.07765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-28T17:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"8d028b0b5af5e90cf84d552c3f4bce0d47bdc3e498b07a3b487e69acc4d716ac","abstract_canon_sha256":"cc8c28a919098bbaef7b3c06fe96ccec0fce95e36ab6a39d98cba36e7cd9ac2b"},"schema_version":"1.0"},"canonical_sha256":"ca0c6852ad2d2b2908a4dd0ff4f76d2389af1c2423e3e6ad6b30e5e2f812947b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:45.052978Z","signature_b64":"2nCCC0fycdSJwK65UzkePY+edbw2dnApab3TIpf89owsdivHZoTIi9fs7OgYO0lRX9LBh7xPHlOncv1+e7GgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca0c6852ad2d2b2908a4dd0ff4f76d2389af1c2423e3e6ad6b30e5e2f812947b","last_reissued_at":"2026-05-18T01:34:45.052364Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:45.052364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.07765","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erNvrAAf2uFAx8NPi1pLcPVfBjLC3ffyweEnmDO4Ji4G9GgSMw21gCKIy1Tk9WDZweNeXO0JbhZBnBF+wmN4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:21:05.033266Z"},"content_sha256":"4e0c84fd474b08253255142a4bf1d48a33264706373412df6110b77db3556444","schema_version":"1.0","event_id":"sha256:4e0c84fd474b08253255142a4bf1d48a33264706373412df6110b77db3556444"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ZIGGQUVNFUVSSCFE3UH7J53NEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Relevance Determination For Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Gunnar R\\\"atsch, Theofanis Karaletsos","submitted_at":"2015-05-28T17:33:43Z","abstract_excerpt":"A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with latent variables, this problem has been adressed with Automatic Relevance Determination (ARD) employing Monte Carlo inference. We present a variational inference approach to ARD for Deep Generative Models using doubly stochastic variational inference to provide fast and scalable learning. We show empirical results on a standard dataset illustrating the effects of contracting the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.07765","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WaEM1ejBak8xk1ZPzGUHy5xGlCrZDJxlCGgv7/SDGOevVLD+JQivi3bp0dQw7vKkwaYH79C3F8mUibCjfaR5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:21:05.033646Z"},"content_sha256":"0f0ccd6763eb7f9f0bb9ba1f2430a2cc15e4d15df4c87ea54469c73884552206","schema_version":"1.0","event_id":"sha256:0f0ccd6763eb7f9f0bb9ba1f2430a2cc15e4d15df4c87ea54469c73884552206"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO/bundle.json","state_url":"https://pith.science/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T18:21:05Z","links":{"resolver":"https://pith.science/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO","bundle":"https://pith.science/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO/bundle.json","state":"https://pith.science/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIGGQUVNFUVSSCFE3UH7J53NEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ZIGGQUVNFUVSSCFE3UH7J53NEO","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":"cc8c28a919098bbaef7b3c06fe96ccec0fce95e36ab6a39d98cba36e7cd9ac2b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-28T17:33:43Z","title_canon_sha256":"8d028b0b5af5e90cf84d552c3f4bce0d47bdc3e498b07a3b487e69acc4d716ac"},"schema_version":"1.0","source":{"id":"1505.07765","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.07765","created_at":"2026-05-18T01:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"1505.07765v3","created_at":"2026-05-18T01:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.07765","created_at":"2026-05-18T01:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZIGGQUVNFUVS","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZIGGQUVNFUVSSCFE","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZIGGQUVN","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:0f0ccd6763eb7f9f0bb9ba1f2430a2cc15e4d15df4c87ea54469c73884552206","target":"graph","created_at":"2026-05-18T01:34:45Z","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":"A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with latent variables, this problem has been adressed with Automatic Relevance Determination (ARD) employing Monte Carlo inference. We present a variational inference approach to ARD for Deep Generative Models using doubly stochastic variational inference to provide fast and scalable learning. We show empirical results on a standard dataset illustrating the effects of contracting the l","authors_text":"Gunnar R\\\"atsch, Theofanis Karaletsos","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-28T17:33:43Z","title":"Automatic Relevance Determination For Deep Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.07765","kind":"arxiv","version":3},"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":"sha256:4e0c84fd474b08253255142a4bf1d48a33264706373412df6110b77db3556444","target":"record","created_at":"2026-05-18T01:34:45Z","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":"cc8c28a919098bbaef7b3c06fe96ccec0fce95e36ab6a39d98cba36e7cd9ac2b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-28T17:33:43Z","title_canon_sha256":"8d028b0b5af5e90cf84d552c3f4bce0d47bdc3e498b07a3b487e69acc4d716ac"},"schema_version":"1.0","source":{"id":"1505.07765","kind":"arxiv","version":3}},"canonical_sha256":"ca0c6852ad2d2b2908a4dd0ff4f76d2389af1c2423e3e6ad6b30e5e2f812947b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca0c6852ad2d2b2908a4dd0ff4f76d2389af1c2423e3e6ad6b30e5e2f812947b","first_computed_at":"2026-05-18T01:34:45.052364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:45.052364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2nCCC0fycdSJwK65UzkePY+edbw2dnApab3TIpf89owsdivHZoTIi9fs7OgYO0lRX9LBh7xPHlOncv1+e7GgCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:45.052978Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.07765","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e0c84fd474b08253255142a4bf1d48a33264706373412df6110b77db3556444","sha256:0f0ccd6763eb7f9f0bb9ba1f2430a2cc15e4d15df4c87ea54469c73884552206"],"state_sha256":"7fbbd67ae90243ddc2f3ed817b0f8e8f06cb5f0515bb0a710a4756089bb07d11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S6SPn9mBonmlAoxHHf0k4d4BG9tczHsCY01w5B+kPQ4XG0pj0HGWjLjxkkOM3Io/tZKwsOv59ENhisPsuUmECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:21:05.036027Z","bundle_sha256":"4fc5c2fa6a79fd3a63de3893225df1a93a522fd2b3091c9dc56aba145a7e8d06"}}