{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4NW3QJ5STUL763SQDBDN7SOYFZ","short_pith_number":"pith:4NW3QJ5S","schema_version":"1.0","canonical_sha256":"e36db827b29d17ff6e501846dfc9d82e7a5e7735a4279e963fab32fd7e5eccf2","source":{"kind":"arxiv","id":"2606.13381","version":1},"attestation_state":"computed","paper":{"title":"H\\\"older++: Improving the Quality-Coherence Trade-off in Multimodal VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huyen Vo, Isabel Valera, Mar\\'ia Mart\\'inez-Garc\\'ia","submitted_at":"2026-06-11T14:08:32Z","abstract_excerpt":"Existing approaches for multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence-i.e., they struggle to generate realistic and diverse samples that, at the same time, are semantically consistent across modalities. A recent work shows that using a simple approximation to H\\\"older pooling as an aggregation method improves coherence over the SOTA MMVAE+, despite assuming a single shared representation across all modalities. Yet, it slightly compromises sample diversity. Inspired by this insight, we propose H\\\"older++, a novel multimodal VAE that improve"},"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":"2606.13381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T14:08:32Z","cross_cats_sorted":[],"title_canon_sha256":"dbc43a8a54b4a745b1547eb7550eaab23b9d9b9142327333cab76131d1a7699e","abstract_canon_sha256":"cfa3fc75bd3106d717d93764afb861ccdcb75e5872d669eeb4601841fe4a3034"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:58.865643Z","signature_b64":"Bs5GlSUwTAlQ7tWsGYtTCwczkTENoA5woJrVwWhtRxQdmRvQ7vxQh2txy+0YoIS5IRfM/zbmaKJODANUgcvMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36db827b29d17ff6e501846dfc9d82e7a5e7735a4279e963fab32fd7e5eccf2","last_reissued_at":"2026-06-12T01:09:58.864948Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:58.864948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"H\\\"older++: Improving the Quality-Coherence Trade-off in Multimodal VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huyen Vo, Isabel Valera, Mar\\'ia Mart\\'inez-Garc\\'ia","submitted_at":"2026-06-11T14:08:32Z","abstract_excerpt":"Existing approaches for multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence-i.e., they struggle to generate realistic and diverse samples that, at the same time, are semantically consistent across modalities. A recent work shows that using a simple approximation to H\\\"older pooling as an aggregation method improves coherence over the SOTA MMVAE+, despite assuming a single shared representation across all modalities. Yet, it slightly compromises sample diversity. Inspired by this insight, we propose H\\\"older++, a novel multimodal VAE that improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13381","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/2606.13381/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":"2606.13381","created_at":"2026-06-12T01:09:58.865050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13381v1","created_at":"2026-06-12T01:09:58.865050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13381","created_at":"2026-06-12T01:09:58.865050+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NW3QJ5STUL7","created_at":"2026-06-12T01:09:58.865050+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NW3QJ5STUL763SQ","created_at":"2026-06-12T01:09:58.865050+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NW3QJ5S","created_at":"2026-06-12T01:09:58.865050+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/4NW3QJ5STUL763SQDBDN7SOYFZ","json":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ.json","graph_json":"https://pith.science/api/pith-number/4NW3QJ5STUL763SQDBDN7SOYFZ/graph.json","events_json":"https://pith.science/api/pith-number/4NW3QJ5STUL763SQDBDN7SOYFZ/events.json","paper":"https://pith.science/paper/4NW3QJ5S"},"agent_actions":{"view_html":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ","download_json":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ.json","view_paper":"https://pith.science/paper/4NW3QJ5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13381&json=true","fetch_graph":"https://pith.science/api/pith-number/4NW3QJ5STUL763SQDBDN7SOYFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4NW3QJ5STUL763SQDBDN7SOYFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ/action/storage_attestation","attest_author":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ/action/author_attestation","sign_citation":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ/action/citation_signature","submit_replication":"https://pith.science/pith/4NW3QJ5STUL763SQDBDN7SOYFZ/action/replication_record"}},"created_at":"2026-06-12T01:09:58.865050+00:00","updated_at":"2026-06-12T01:09:58.865050+00:00"}