{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C5V5E46EEZYZXS72U2NHRIDCOG","short_pith_number":"pith:C5V5E46E","schema_version":"1.0","canonical_sha256":"176bd273c426719bcbfaa69a78a06271af3128e288f3f43b2dd55ca80e79ed75","source":{"kind":"arxiv","id":"2209.02604","version":1},"attestation_state":"computed","paper":{"title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hua Xu, Huisheng Mao, Kai Gao, Tie Cheng, Wanqiuyue Yang, Xiaoteng Li, Yihe Liu, Yuanzhe Qiu, Zhiyun Liang, Ziqi Yuan","submitted_at":"2022-08-22T03:31:33Z","abstract_excerpt":"Multimodal sentiment analysis (MSA), which supposes to improve text-based sentiment analysis with associated acoustic and visual modalities, is an emerging research area due to its potential applications in Human-Computer Interaction (HCI). However, the existing researches observe that the acoustic and visual modalities contribute much less than the textual modality, termed as text-predominant. Under such circumstances, in this work, we emphasize making non-verbal cues matter for the MSA task. Firstly, from the resource perspective, we present the CH-SIMS v2.0 dataset, an extension and enhance"},"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":"2209.02604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2022-08-22T03:31:33Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"ae046021b49aeb8dcc610f8623d12aea4bbde0378291fd4d6900246468e6fae1","abstract_canon_sha256":"76b1beeb6c14df01fd7c223ff9b7fa6f42b035dd7c4f2ae9dddd9ba3d21561ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:13.044335Z","signature_b64":"nJiLEMZhBfKdXXr3qFha6+rmMfc7asgF8aWpao+wvaWq0mKIuEOOamKUtVs81VSZowoO6GJmiW+NpYB5XRMcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"176bd273c426719bcbfaa69a78a06271af3128e288f3f43b2dd55ca80e79ed75","last_reissued_at":"2026-07-05T04:55:13.043915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:13.043915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hua Xu, Huisheng Mao, Kai Gao, Tie Cheng, Wanqiuyue Yang, Xiaoteng Li, Yihe Liu, Yuanzhe Qiu, Zhiyun Liang, Ziqi Yuan","submitted_at":"2022-08-22T03:31:33Z","abstract_excerpt":"Multimodal sentiment analysis (MSA), which supposes to improve text-based sentiment analysis with associated acoustic and visual modalities, is an emerging research area due to its potential applications in Human-Computer Interaction (HCI). However, the existing researches observe that the acoustic and visual modalities contribute much less than the textual modality, termed as text-predominant. Under such circumstances, in this work, we emphasize making non-verbal cues matter for the MSA task. Firstly, from the resource perspective, we present the CH-SIMS v2.0 dataset, an extension and enhance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.02604","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/2209.02604/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":"2209.02604","created_at":"2026-07-05T04:55:13.043972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.02604v1","created_at":"2026-07-05T04:55:13.043972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.02604","created_at":"2026-07-05T04:55:13.043972+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5V5E46EEZYZ","created_at":"2026-07-05T04:55:13.043972+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5V5E46EEZYZXS72","created_at":"2026-07-05T04:55:13.043972+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5V5E46E","created_at":"2026-07-05T04:55:13.043972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18162","citing_title":"SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG","json":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG.json","graph_json":"https://pith.science/api/pith-number/C5V5E46EEZYZXS72U2NHRIDCOG/graph.json","events_json":"https://pith.science/api/pith-number/C5V5E46EEZYZXS72U2NHRIDCOG/events.json","paper":"https://pith.science/paper/C5V5E46E"},"agent_actions":{"view_html":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG","download_json":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG.json","view_paper":"https://pith.science/paper/C5V5E46E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.02604&json=true","fetch_graph":"https://pith.science/api/pith-number/C5V5E46EEZYZXS72U2NHRIDCOG/graph.json","fetch_events":"https://pith.science/api/pith-number/C5V5E46EEZYZXS72U2NHRIDCOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG/action/storage_attestation","attest_author":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG/action/author_attestation","sign_citation":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG/action/citation_signature","submit_replication":"https://pith.science/pith/C5V5E46EEZYZXS72U2NHRIDCOG/action/replication_record"}},"created_at":"2026-07-05T04:55:13.043972+00:00","updated_at":"2026-07-05T04:55:13.043972+00:00"}