{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XHE7D2ZOYYDAIJJMNKGR5VV2IB","short_pith_number":"pith:XHE7D2ZO","canonical_record":{"source":{"id":"1802.05335","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T22:08:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b16a7b61b4864d850927c96371051f5bc5cb1c0d4938c9ca13a25b03a2d07f08","abstract_canon_sha256":"21d026f7b3b4a406e2cb4d6f86eae76a840352ab4cb25f59b7fb9f9a667c8cf9"},"schema_version":"1.0"},"canonical_sha256":"b9c9f1eb2ec60604252c6a8d1ed6ba406aa8bc35232fe07c7fc49b272f69672f","source":{"kind":"arxiv","id":"1802.05335","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05335","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05335v3","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05335","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"pith_short_12","alias_value":"XHE7D2ZOYYDA","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XHE7D2ZOYYDAIJJM","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XHE7D2ZO","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XHE7D2ZOYYDAIJJMNKGR5VV2IB","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05335","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T22:08:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b16a7b61b4864d850927c96371051f5bc5cb1c0d4938c9ca13a25b03a2d07f08","abstract_canon_sha256":"21d026f7b3b4a406e2cb4d6f86eae76a840352ab4cb25f59b7fb9f9a667c8cf9"},"schema_version":"1.0"},"canonical_sha256":"b9c9f1eb2ec60604252c6a8d1ed6ba406aa8bc35232fe07c7fc49b272f69672f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:09.789668Z","signature_b64":"TuyUcZbXaCkJw30SNYjHxiVhcYq3VhM66+w9tSS5V+p016hfRd0KjVrrq/BOeaTOMxeknyc8HOXoEaBYqEcPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c9f1eb2ec60604252c6a8d1ed6ba406aa8bc35232fe07c7fc49b272f69672f","last_reissued_at":"2026-05-18T00:01:09.789021Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:09.789021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05335","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":"2026-05-18T00:01:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OzM56YiYvd/Hds2lUfZa+582PYqbWg1qfFeZz5/7drdZKcOzse3didKR5zSvMce/LAUl0wZoBBfs2FmQ1G+MBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:20:48.327654Z"},"content_sha256":"1cd42814265e8d64dc759821ba1d31ed95339747e3478288ef4ae3fa45a7a317","schema_version":"1.0","event_id":"sha256:1cd42814265e8d64dc759821ba1d31ed95339747e3478288ef4ae3fa45a7a317"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XHE7D2ZOYYDAIJJMNKGR5VV2IB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Generative Models for Scalable Weakly-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mike Wu, Noah Goodman","submitted_at":"2018-02-14T22:08:05Z","abstract_excerpt":"Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not learn a joint distribution or require additional computation to handle missing data. Here, we introduce a multimodal variational autoencoder (MVAE) that uses a product-of-experts inference network and a sub-sampled training paradigm to solve the multi-modal inference problem. Notably, our model shares parameters to efficiently learn under any combination of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05335","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":"2026-05-18T00:01:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9O4tDDLCwVJomGd8dBEemcGK6cFzMaiULbFDlqykD2k81Zd6+Gl4CXfdcPv5LhaiuzeirMqbtFnjY0MK0ex8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:20:48.328308Z"},"content_sha256":"42fc9ce125dff6d348d1fbb1793b45241f0a6de885699120e8d2da6066086262","schema_version":"1.0","event_id":"sha256:42fc9ce125dff6d348d1fbb1793b45241f0a6de885699120e8d2da6066086262"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB/bundle.json","state_url":"https://pith.science/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB/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":"2026-05-27T23:20:48Z","links":{"resolver":"https://pith.science/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB","bundle":"https://pith.science/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB/bundle.json","state":"https://pith.science/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHE7D2ZOYYDAIJJMNKGR5VV2IB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XHE7D2ZOYYDAIJJMNKGR5VV2IB","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":"21d026f7b3b4a406e2cb4d6f86eae76a840352ab4cb25f59b7fb9f9a667c8cf9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T22:08:05Z","title_canon_sha256":"b16a7b61b4864d850927c96371051f5bc5cb1c0d4938c9ca13a25b03a2d07f08"},"schema_version":"1.0","source":{"id":"1802.05335","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05335","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05335v3","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05335","created_at":"2026-05-18T00:01:09Z"},{"alias_kind":"pith_short_12","alias_value":"XHE7D2ZOYYDA","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XHE7D2ZOYYDAIJJM","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XHE7D2ZO","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:42fc9ce125dff6d348d1fbb1793b45241f0a6de885699120e8d2da6066086262","target":"graph","created_at":"2026-05-18T00:01:09Z","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":"Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not learn a joint distribution or require additional computation to handle missing data. Here, we introduce a multimodal variational autoencoder (MVAE) that uses a product-of-experts inference network and a sub-sampled training paradigm to solve the multi-modal inference problem. Notably, our model shares parameters to efficiently learn under any combination of","authors_text":"Mike Wu, Noah Goodman","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T22:08:05Z","title":"Multimodal Generative Models for Scalable Weakly-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05335","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":"sha256:1cd42814265e8d64dc759821ba1d31ed95339747e3478288ef4ae3fa45a7a317","target":"record","created_at":"2026-05-18T00:01:09Z","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":"21d026f7b3b4a406e2cb4d6f86eae76a840352ab4cb25f59b7fb9f9a667c8cf9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T22:08:05Z","title_canon_sha256":"b16a7b61b4864d850927c96371051f5bc5cb1c0d4938c9ca13a25b03a2d07f08"},"schema_version":"1.0","source":{"id":"1802.05335","kind":"arxiv","version":3}},"canonical_sha256":"b9c9f1eb2ec60604252c6a8d1ed6ba406aa8bc35232fe07c7fc49b272f69672f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9c9f1eb2ec60604252c6a8d1ed6ba406aa8bc35232fe07c7fc49b272f69672f","first_computed_at":"2026-05-18T00:01:09.789021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:09.789021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TuyUcZbXaCkJw30SNYjHxiVhcYq3VhM66+w9tSS5V+p016hfRd0KjVrrq/BOeaTOMxeknyc8HOXoEaBYqEcPAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:09.789668Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05335","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cd42814265e8d64dc759821ba1d31ed95339747e3478288ef4ae3fa45a7a317","sha256:42fc9ce125dff6d348d1fbb1793b45241f0a6de885699120e8d2da6066086262"],"state_sha256":"9ef73c3db64d8d725a867cfe5d72385ae7979d65ca26995e4c1ee1b27dac303e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GgCT9/nx2tNfsylkjaNtPFA4IIqZ5eLJsROAL7Rdi9/v46vK1BCTvAQRWkVplEdjiXpmn8uzxUMMex0XYwEnDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:20:48.331846Z","bundle_sha256":"59c317fee12ca80e12d119e882517e1688cf2891e0291b5a47afb6a281bae6c6"}}