{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JUD7TLHYSPZ4S6STUD4LNYDVY4","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":"5719fd60727938d770281ed7993c8a8ea9ba7fbc5045611f165264e1159cfd8d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T17:54:35Z","title_canon_sha256":"8b9cd447edeae279eebf69c4e5eddc4cee948540721070571f12557f833923d6"},"schema_version":"1.0","source":{"id":"2106.12570","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12570","created_at":"2026-07-05T05:25:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12570v3","created_at":"2026-07-05T05:25:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12570","created_at":"2026-07-05T05:25:46Z"},{"alias_kind":"pith_short_12","alias_value":"JUD7TLHYSPZ4","created_at":"2026-07-05T05:25:46Z"},{"alias_kind":"pith_short_16","alias_value":"JUD7TLHYSPZ4S6ST","created_at":"2026-07-05T05:25:46Z"},{"alias_kind":"pith_short_8","alias_value":"JUD7TLHY","created_at":"2026-07-05T05:25:46Z"}],"graph_snapshots":[{"event_id":"sha256:d2944a76161cccaa76f81827d38d001e2a65a7f2325c1767b4079fc11f7ab168","target":"graph","created_at":"2026-07-05T05:25:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.12570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities by reconciling idiosyncratic representations directly in the recognition model through explicit products, mixtures, or other such factorisations. Here we introduce a novel alternative, the MEME, that avoids such explicit combinations by repurposing semi-supervised VAEs to combine information between modalities implicitly through mutual supervision. This formu","authors_text":"N. Siddharth, Philip H.S. Torr, Sebastian M. Schmon, Tom Joy, Tom Rainforth, Yuge Shi","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T17:54:35Z","title":"Learning Multimodal VAEs through Mutual Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12570","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":"sha256:781958723dcd953fd2eb7b53306ac4e2d17397cb43b5301ff954df65ec14d46f","target":"record","created_at":"2026-07-05T05:25:46Z","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":"5719fd60727938d770281ed7993c8a8ea9ba7fbc5045611f165264e1159cfd8d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T17:54:35Z","title_canon_sha256":"8b9cd447edeae279eebf69c4e5eddc4cee948540721070571f12557f833923d6"},"schema_version":"1.0","source":{"id":"2106.12570","kind":"arxiv","version":3}},"canonical_sha256":"4d07f9acf893f3c97a53a0f8b6e075c711434958142f9fdf02f4709afedd36e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d07f9acf893f3c97a53a0f8b6e075c711434958142f9fdf02f4709afedd36e3","first_computed_at":"2026-07-05T05:25:46.885239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:46.885239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RCfp748w++52XQCNJedXM+cJ0SxawxUzKt1m8HgrF8BBAnbEVuWFV8jyWQV7Hn7ZeCSF7QwaHNC+R0Wr58v5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:46.885713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.12570","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:781958723dcd953fd2eb7b53306ac4e2d17397cb43b5301ff954df65ec14d46f","sha256:d2944a76161cccaa76f81827d38d001e2a65a7f2325c1767b4079fc11f7ab168"],"state_sha256":"411f56d16d70c80c763cde348f8568ccd02fdc7b36ec5420ba44ffb44cf7e287"}