{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MDSNDOHVYAAYWTW2LDIFLR2R2Q","short_pith_number":"pith:MDSNDOHV","schema_version":"1.0","canonical_sha256":"60e4d1b8f5c0018b4eda58d055c751d4173b0719d4d56664df7ccfc2cc699a92","source":{"kind":"arxiv","id":"2505.01134","version":1},"attestation_state":"computed","paper":{"title":"Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael Kampffmeyer, Robert Jenssen, Rogelio A Mancisidor, Shujian Yu","submitted_at":"2025-05-02T09:24:10Z","abstract_excerpt":"Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixture of experts, aggregate single-modality distributions assuming independence for simplicity, which is an overoptimistic assumption. This research introduces a novel methodology for aggregating single-modality distributions by exploiting the principle of consensus of dependent experts (CoDE), which circumvents the aforementioned assumption. Utilizing the CoDE method, we propose a novel ELBO that approximates the joint"},"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":"2505.01134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T09:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"3bf78f8b705d72d341d20b8d2209d99dc18e9b942e4b6150c86319bd5dcc4a21","abstract_canon_sha256":"edf039da77a490250eca158e9cb8e2f29e0d714d03a3f9ca8c414c91d516be33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:45.921278Z","signature_b64":"aeTRyrAiFe+rOY3L6OLhFvzIgQD479amoCZsDvKFlscqhFe03KZvSE21AjDM38vwR+ou301NnkfY0JUIuYruCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60e4d1b8f5c0018b4eda58d055c751d4173b0719d4d56664df7ccfc2cc699a92","last_reissued_at":"2026-07-05T10:57:45.920720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:45.920720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael Kampffmeyer, Robert Jenssen, Rogelio A Mancisidor, Shujian Yu","submitted_at":"2025-05-02T09:24:10Z","abstract_excerpt":"Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixture of experts, aggregate single-modality distributions assuming independence for simplicity, which is an overoptimistic assumption. This research introduces a novel methodology for aggregating single-modality distributions by exploiting the principle of consensus of dependent experts (CoDE), which circumvents the aforementioned assumption. Utilizing the CoDE method, we propose a novel ELBO that approximates the joint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01134","kind":"arxiv","version":1},"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/2505.01134/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":"2505.01134","created_at":"2026-07-05T10:57:45.920784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01134v1","created_at":"2026-07-05T10:57:45.920784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01134","created_at":"2026-07-05T10:57:45.920784+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDSNDOHVYAAY","created_at":"2026-07-05T10:57:45.920784+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDSNDOHVYAAYWTW2","created_at":"2026-07-05T10:57:45.920784+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDSNDOHV","created_at":"2026-07-05T10:57:45.920784+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/MDSNDOHVYAAYWTW2LDIFLR2R2Q","json":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q.json","graph_json":"https://pith.science/api/pith-number/MDSNDOHVYAAYWTW2LDIFLR2R2Q/graph.json","events_json":"https://pith.science/api/pith-number/MDSNDOHVYAAYWTW2LDIFLR2R2Q/events.json","paper":"https://pith.science/paper/MDSNDOHV"},"agent_actions":{"view_html":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q","download_json":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q.json","view_paper":"https://pith.science/paper/MDSNDOHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01134&json=true","fetch_graph":"https://pith.science/api/pith-number/MDSNDOHVYAAYWTW2LDIFLR2R2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/MDSNDOHVYAAYWTW2LDIFLR2R2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q/action/storage_attestation","attest_author":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q/action/author_attestation","sign_citation":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q/action/citation_signature","submit_replication":"https://pith.science/pith/MDSNDOHVYAAYWTW2LDIFLR2R2Q/action/replication_record"}},"created_at":"2026-07-05T10:57:45.920784+00:00","updated_at":"2026-07-05T10:57:45.920784+00:00"}