{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VDKUPKMBUA2ZUII7FQ22MXM4FU","short_pith_number":"pith:VDKUPKMB","schema_version":"1.0","canonical_sha256":"a8d547a981a0359a211f2c35a65d9c2d0c3e1b7f13f0a6a479ebabe22bf589cc","source":{"kind":"arxiv","id":"2410.11403","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Masahiro Suzuki, Yutaka Matsuo, Yuta Oshima","submitted_at":"2024-10-15T08:49:38Z","abstract_excerpt":"Multimodal variational autoencoders (VAEs) aim to capture shared latent representations by integrating information from different data modalities. A significant challenge is accurately inferring representations from any subset of modalities without training an impractical number (2^M) of inference networks for all possible modality combinations. Mixture-based models simplify this by requiring only as many inference models as there are modalities, aggregating unimodal inferences. However, they suffer from information loss when modalities are missing. Alignment-based VAEs address this by alignin"},"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":"2410.11403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T08:49:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a27a8fc0010421fcf4d0b17bd2535d0b77ab5563d3d7c484e7c84d36401de2c1","abstract_canon_sha256":"3857a3d206eb50926ea63193342f3766030fd421f0ba5726ed28299134a56419"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:52.948116Z","signature_b64":"py10m9j6eyftc5t/95UfwKZYXyH8/fW3dcF1OdtaC6EIpDGh0Kulqtm265njnoI7oF01netzZCNQ4SSaBscBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8d547a981a0359a211f2c35a65d9c2d0c3e1b7f13f0a6a479ebabe22bf589cc","last_reissued_at":"2026-07-05T09:20:52.947675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:52.947675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Masahiro Suzuki, Yutaka Matsuo, Yuta Oshima","submitted_at":"2024-10-15T08:49:38Z","abstract_excerpt":"Multimodal variational autoencoders (VAEs) aim to capture shared latent representations by integrating information from different data modalities. A significant challenge is accurately inferring representations from any subset of modalities without training an impractical number (2^M) of inference networks for all possible modality combinations. Mixture-based models simplify this by requiring only as many inference models as there are modalities, aggregating unimodal inferences. However, they suffer from information loss when modalities are missing. Alignment-based VAEs address this by alignin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11403","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/2410.11403/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":"2410.11403","created_at":"2026-07-05T09:20:52.947733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11403v1","created_at":"2026-07-05T09:20:52.947733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11403","created_at":"2026-07-05T09:20:52.947733+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDKUPKMBUA2Z","created_at":"2026-07-05T09:20:52.947733+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDKUPKMBUA2ZUII7","created_at":"2026-07-05T09:20:52.947733+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDKUPKMB","created_at":"2026-07-05T09:20:52.947733+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/VDKUPKMBUA2ZUII7FQ22MXM4FU","json":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU.json","graph_json":"https://pith.science/api/pith-number/VDKUPKMBUA2ZUII7FQ22MXM4FU/graph.json","events_json":"https://pith.science/api/pith-number/VDKUPKMBUA2ZUII7FQ22MXM4FU/events.json","paper":"https://pith.science/paper/VDKUPKMB"},"agent_actions":{"view_html":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU","download_json":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU.json","view_paper":"https://pith.science/paper/VDKUPKMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11403&json=true","fetch_graph":"https://pith.science/api/pith-number/VDKUPKMBUA2ZUII7FQ22MXM4FU/graph.json","fetch_events":"https://pith.science/api/pith-number/VDKUPKMBUA2ZUII7FQ22MXM4FU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU/action/storage_attestation","attest_author":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU/action/author_attestation","sign_citation":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU/action/citation_signature","submit_replication":"https://pith.science/pith/VDKUPKMBUA2ZUII7FQ22MXM4FU/action/replication_record"}},"created_at":"2026-07-05T09:20:52.947733+00:00","updated_at":"2026-07-05T09:20:52.947733+00:00"}