{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DA3KHFW6AB56QLG3YNMVFBN4RD","short_pith_number":"pith:DA3KHFW6","schema_version":"1.0","canonical_sha256":"1836a396de007be82cdbc3595285bc88de01adf09862bc9e04fe948471eabcac","source":{"kind":"arxiv","id":"2508.02133","version":4},"attestation_state":"computed","paper":{"title":"Hierarchical MoE: Continuous Multimodal Emotion Recognition with Incomplete and Asynchronous Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Guanxuan Jiang, Lei Han, Pengyuan Zhou, Yitong Zhu, Yuyang Wang","submitted_at":"2025-08-04T07:29:17Z","abstract_excerpt":"Multimodal emotion recognition (MER) is crucial for human-computer interaction, yet real-world challenges like dynamic modality incompleteness and asynchrony severely limit its robustness. Existing methods often assume consistently complete data or lack dynamic adaptability. To address these limitations, we propose a novel Hi-MoE~(Hierarchical Mixture-of-Experts) framework for robust continuous emotion prediction. This framework employs a dual-layer expert structure. A Modality Expert Bank utilizes soft routing to dynamically handle missing modalities and achieve robust information fusion. A s"},"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":"2508.02133","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-08-04T07:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"a7f092b57b2528863c85a64a19459a1d35f0dc0daaf7f0ed7b4c7839cbf35173","abstract_canon_sha256":"52e0bcaaaa00648f949cdf562557e7182d3b837bec4678f61d982f2034c49a89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:20.906853Z","signature_b64":"aF+cdK3kUSZqqJBjss6UvrTP7pcfu2L6Gs9DvA9Wn+lnrKXm/YHI19as/Gnn1Bfr7o57+XWNyS43cC7EzOMnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1836a396de007be82cdbc3595285bc88de01adf09862bc9e04fe948471eabcac","last_reissued_at":"2026-07-05T11:55:20.906401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:20.906401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical MoE: Continuous Multimodal Emotion Recognition with Incomplete and Asynchronous Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Guanxuan Jiang, Lei Han, Pengyuan Zhou, Yitong Zhu, Yuyang Wang","submitted_at":"2025-08-04T07:29:17Z","abstract_excerpt":"Multimodal emotion recognition (MER) is crucial for human-computer interaction, yet real-world challenges like dynamic modality incompleteness and asynchrony severely limit its robustness. Existing methods often assume consistently complete data or lack dynamic adaptability. To address these limitations, we propose a novel Hi-MoE~(Hierarchical Mixture-of-Experts) framework for robust continuous emotion prediction. This framework employs a dual-layer expert structure. A Modality Expert Bank utilizes soft routing to dynamically handle missing modalities and achieve robust information fusion. A s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02133","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/2508.02133/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":"2508.02133","created_at":"2026-07-05T11:55:20.906460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02133v4","created_at":"2026-07-05T11:55:20.906460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02133","created_at":"2026-07-05T11:55:20.906460+00:00"},{"alias_kind":"pith_short_12","alias_value":"DA3KHFW6AB56","created_at":"2026-07-05T11:55:20.906460+00:00"},{"alias_kind":"pith_short_16","alias_value":"DA3KHFW6AB56QLG3","created_at":"2026-07-05T11:55:20.906460+00:00"},{"alias_kind":"pith_short_8","alias_value":"DA3KHFW6","created_at":"2026-07-05T11:55:20.906460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06023","citing_title":"BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion Recognition","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD","json":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD.json","graph_json":"https://pith.science/api/pith-number/DA3KHFW6AB56QLG3YNMVFBN4RD/graph.json","events_json":"https://pith.science/api/pith-number/DA3KHFW6AB56QLG3YNMVFBN4RD/events.json","paper":"https://pith.science/paper/DA3KHFW6"},"agent_actions":{"view_html":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD","download_json":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD.json","view_paper":"https://pith.science/paper/DA3KHFW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02133&json=true","fetch_graph":"https://pith.science/api/pith-number/DA3KHFW6AB56QLG3YNMVFBN4RD/graph.json","fetch_events":"https://pith.science/api/pith-number/DA3KHFW6AB56QLG3YNMVFBN4RD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD/action/storage_attestation","attest_author":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD/action/author_attestation","sign_citation":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD/action/citation_signature","submit_replication":"https://pith.science/pith/DA3KHFW6AB56QLG3YNMVFBN4RD/action/replication_record"}},"created_at":"2026-07-05T11:55:20.906460+00:00","updated_at":"2026-07-05T11:55:20.906460+00:00"}