{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZONUMWNNH2Q7JCZB3K3OLYCI6V","short_pith_number":"pith:ZONUMWNN","schema_version":"1.0","canonical_sha256":"cb9b4659ad3ea1f48b21dab6e5e048f550fbdac76068af873b1e4b81bd22ab5f","source":{"kind":"arxiv","id":"2404.17858","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"FuChen Zhang, Keqin Li, Nan Yin, Tao Meng, Yuntao Shou","submitted_at":"2024-04-27T10:22:03Z","abstract_excerpt":"Multi-modal Emotion Recognition in Conversation (MERC) has received considerable attention in various fields, e.g., human-computer interaction and recommendation systems. Most existing works perform feature disentanglement and fusion to extract emotional contextual information from multi-modal features and emotion classification. After revisiting the characteristic of MERC, we argue that long-range contextual semantic information should be extracted in the feature disentanglement stage and the inter-modal semantic information consistency should be maximized in the feature fusion stage. Inspire"},"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":"2404.17858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T10:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"fe2670eb9e2993554858d8b3ed8778263653c3dcf94eb3df188e3dd87c9bc37b","abstract_canon_sha256":"eb049eae5b062f2e1d631bb6bf46cb1eebf65acb4527040748f1bca0b5786c8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:56.354954Z","signature_b64":"RhBwCAkBSa2ggeoviUsXLLXafZLTC8khdjDlrMVYIJhGaSvDsTMCNTWwUUWwt0eV2x/jlc2IMg5s5QaTfa60BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb9b4659ad3ea1f48b21dab6e5e048f550fbdac76068af873b1e4b81bd22ab5f","last_reissued_at":"2026-07-05T08:14:56.354426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:56.354426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"FuChen Zhang, Keqin Li, Nan Yin, Tao Meng, Yuntao Shou","submitted_at":"2024-04-27T10:22:03Z","abstract_excerpt":"Multi-modal Emotion Recognition in Conversation (MERC) has received considerable attention in various fields, e.g., human-computer interaction and recommendation systems. Most existing works perform feature disentanglement and fusion to extract emotional contextual information from multi-modal features and emotion classification. After revisiting the characteristic of MERC, we argue that long-range contextual semantic information should be extracted in the feature disentanglement stage and the inter-modal semantic information consistency should be maximized in the feature fusion stage. Inspire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17858","kind":"arxiv","version":2},"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/2404.17858/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":"2404.17858","created_at":"2026-07-05T08:14:56.354483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17858v2","created_at":"2026-07-05T08:14:56.354483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17858","created_at":"2026-07-05T08:14:56.354483+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZONUMWNNH2Q7","created_at":"2026-07-05T08:14:56.354483+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZONUMWNNH2Q7JCZB","created_at":"2026-07-05T08:14:56.354483+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZONUMWNN","created_at":"2026-07-05T08:14:56.354483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12325","citing_title":"GSDNet: Revisiting Incomplete Multimodal-Diffusion from Graph Spectrum Perspective for Conversation Emotion Recognition","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V","json":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V.json","graph_json":"https://pith.science/api/pith-number/ZONUMWNNH2Q7JCZB3K3OLYCI6V/graph.json","events_json":"https://pith.science/api/pith-number/ZONUMWNNH2Q7JCZB3K3OLYCI6V/events.json","paper":"https://pith.science/paper/ZONUMWNN"},"agent_actions":{"view_html":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V","download_json":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V.json","view_paper":"https://pith.science/paper/ZONUMWNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17858&json=true","fetch_graph":"https://pith.science/api/pith-number/ZONUMWNNH2Q7JCZB3K3OLYCI6V/graph.json","fetch_events":"https://pith.science/api/pith-number/ZONUMWNNH2Q7JCZB3K3OLYCI6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V/action/storage_attestation","attest_author":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V/action/author_attestation","sign_citation":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V/action/citation_signature","submit_replication":"https://pith.science/pith/ZONUMWNNH2Q7JCZB3K3OLYCI6V/action/replication_record"}},"created_at":"2026-07-05T08:14:56.354483+00:00","updated_at":"2026-07-05T08:14:56.354483+00:00"}