{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LYKYQ6DIPGZX2WRLKPFS5FSVOG","short_pith_number":"pith:LYKYQ6DI","schema_version":"1.0","canonical_sha256":"5e1588786879b37d5a2b53cb2e965571856984f6b1e16609c5d63f19690043a8","source":{"kind":"arxiv","id":"2402.03226","version":4},"attestation_state":"computed","paper":{"title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Harris, Huy Nguyen, Nhat Ho, Suchi Saria, Xing Han","submitted_at":"2024-02-05T17:37:46Z","abstract_excerpt":"As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples. Successfully leveraging this complex data, while overcoming the scarcity of high-quality training samples, is key to improving these models' predictive performance. We introduce ``FuseMoE'', a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE i"},"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":"2402.03226","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:37:46Z","cross_cats_sorted":[],"title_canon_sha256":"27dd8706ad5dd935f3e2d988315b7a46c9b964d8fe65eb23567ddef0317e04b6","abstract_canon_sha256":"5e2a8a5151d568d8e3af36535f66dba1f540465b03a879ac22cb93c630ef890e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:36.329467Z","signature_b64":"nA/bPApSKR/JTauXCtbHPDda+RaOhqbra4/IPrU/IDAL5rg/UxZLVBRzZSD5Pnw7pspEf7e6Lm51P2FguKwmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e1588786879b37d5a2b53cb2e965571856984f6b1e16609c5d63f19690043a8","last_reissued_at":"2026-07-05T10:46:36.328974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:36.328974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Harris, Huy Nguyen, Nhat Ho, Suchi Saria, Xing Han","submitted_at":"2024-02-05T17:37:46Z","abstract_excerpt":"As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples. Successfully leveraging this complex data, while overcoming the scarcity of high-quality training samples, is key to improving these models' predictive performance. We introduce ``FuseMoE'', a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03226","kind":"arxiv","version":4},"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/2402.03226/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":"2402.03226","created_at":"2026-07-05T10:46:36.329026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03226v4","created_at":"2026-07-05T10:46:36.329026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03226","created_at":"2026-07-05T10:46:36.329026+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYKYQ6DIPGZX","created_at":"2026-07-05T10:46:36.329026+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYKYQ6DIPGZX2WRL","created_at":"2026-07-05T10:46:36.329026+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYKYQ6DI","created_at":"2026-07-05T10:46:36.329026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24985","citing_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15235","citing_title":"MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19525","citing_title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG","json":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG.json","graph_json":"https://pith.science/api/pith-number/LYKYQ6DIPGZX2WRLKPFS5FSVOG/graph.json","events_json":"https://pith.science/api/pith-number/LYKYQ6DIPGZX2WRLKPFS5FSVOG/events.json","paper":"https://pith.science/paper/LYKYQ6DI"},"agent_actions":{"view_html":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG","download_json":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG.json","view_paper":"https://pith.science/paper/LYKYQ6DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03226&json=true","fetch_graph":"https://pith.science/api/pith-number/LYKYQ6DIPGZX2WRLKPFS5FSVOG/graph.json","fetch_events":"https://pith.science/api/pith-number/LYKYQ6DIPGZX2WRLKPFS5FSVOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG/action/storage_attestation","attest_author":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG/action/author_attestation","sign_citation":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG/action/citation_signature","submit_replication":"https://pith.science/pith/LYKYQ6DIPGZX2WRLKPFS5FSVOG/action/replication_record"}},"created_at":"2026-07-05T10:46:36.329026+00:00","updated_at":"2026-07-05T10:46:36.329026+00:00"}