{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Q7HSEGISGPDLXAR45ZAID54SJB","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":"3db485c6e1fedea10f5924079b282f6ab42638009520c000933aa7b6b8ed13e7","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-06T07:05:00Z","title_canon_sha256":"d6d4c0311e68c426250af64250ff127e7678719a0fc37c56704cdb44f9afe74b"},"schema_version":"1.0","source":{"id":"2105.02470","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.02470","created_at":"2026-07-05T02:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"2105.02470v2","created_at":"2026-07-05T02:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02470","created_at":"2026-07-05T02:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"Q7HSEGISGPDL","created_at":"2026-07-05T02:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"Q7HSEGISGPDLXAR4","created_at":"2026-07-05T02:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"Q7HSEGIS","created_at":"2026-07-05T02:52:16Z"}],"graph_snapshots":[{"event_id":"sha256:7c0eed29950a90bd964c0ec05b44abe3a79d7637acd34ea261cae00783fe9767","target":"graph","created_at":"2026-07-05T02:52:16Z","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/2105.02470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple data types naturally co-occur when describing real-world phenomena and learning from them is a long-standing goal in machine learning research. However, existing self-supervised generative models approximating an ELBO are not able to fulfill all desired requirements of multimodal models: their posterior approximation functions lead to a trade-off between the semantic coherence and the ability to learn the joint data distribution. We propose a new, generalized ELBO formulation for multimodal data that overcomes these limitations. The new objective encompasses two previous methods as sp","authors_text":"Imant Daunhawer, Julia E. Vogt, Thomas M. Sutter","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-06T07:05:00Z","title":"Generalized Multimodal ELBO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02470","kind":"arxiv","version":2},"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":"sha256:30c2417be0a58c6edceb7e8ec72c1ed1e61110debc72831e7850166688009c05","target":"record","created_at":"2026-07-05T02:52:16Z","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":"3db485c6e1fedea10f5924079b282f6ab42638009520c000933aa7b6b8ed13e7","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-06T07:05:00Z","title_canon_sha256":"d6d4c0311e68c426250af64250ff127e7678719a0fc37c56704cdb44f9afe74b"},"schema_version":"1.0","source":{"id":"2105.02470","kind":"arxiv","version":2}},"canonical_sha256":"87cf22191233c6bb823cee4081f7924852da77ac2c89a5e53b9d97219ef6ed53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87cf22191233c6bb823cee4081f7924852da77ac2c89a5e53b9d97219ef6ed53","first_computed_at":"2026-07-05T02:52:16.284279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:16.284279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sUJlDaNjLzAXQbxBo3fE+VVqta4aae/QK0NWkkUCMHXswxjWK4E0DkVwOz71u+ZnjEEvAGLKl2AuokZBWyLgAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:16.284628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.02470","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30c2417be0a58c6edceb7e8ec72c1ed1e61110debc72831e7850166688009c05","sha256:7c0eed29950a90bd964c0ec05b44abe3a79d7637acd34ea261cae00783fe9767"],"state_sha256":"79812261955231d121a30e386f307bc427f6380e68e731a87aa27256c20b9bfb"}