{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HBEJJWAMBLJAFB7GXHSAYCYUYY","short_pith_number":"pith:HBEJJWAM","schema_version":"1.0","canonical_sha256":"384894d80c0ad20287e6b9e40c0b14c632046a850b2ef0bb81a5fbedf1c429b9","source":{"kind":"arxiv","id":"2403.05023","version":2},"attestation_state":"computed","paper":{"title":"Towards Multimodal Sentiment Analysis Debiasing via Bias Purification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dingkang Yang, Dongling Xiao, Ke Li, Kun Yang, Lihua Zhang, Mingcheng Li, Peng Zhai, Yang Liu, Yuzheng Wang, Zhaoyu Chen","submitted_at":"2024-03-08T03:55:27Z","abstract_excerpt":"Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably suffers from unplanned dataset biases, particularly multimodal utterance-level label bias and word-level context bias. These harmful biases potentially mislead models to focus on statistical shortcuts and spurious correlations, causing severe performance bottlenecks. To alleviate these issues, we present a Multimodal Counterfactual Inference Sentiment (MCIS) analysis framework ba"},"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":"2403.05023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T03:55:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b454078432429750b2470ecb7bb65d8793e0e1cdf60be02de07a7d259e08dd08","abstract_canon_sha256":"bee6ee016a402bb943aa66b323629320f287321985545dbe609f2e438cb65bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:14.537273Z","signature_b64":"EvZycvrOmb4L8vSa9k/Ccs/MU5WJjyWcRXaJmqZEWVM4O2K9nNA+sn2GzPzDVwl7GNXjoeXeb8I6ToLcKmR3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"384894d80c0ad20287e6b9e40c0b14c632046a850b2ef0bb81a5fbedf1c429b9","last_reissued_at":"2026-07-05T08:40:14.536736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:14.536736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Multimodal Sentiment Analysis Debiasing via Bias Purification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dingkang Yang, Dongling Xiao, Ke Li, Kun Yang, Lihua Zhang, Mingcheng Li, Peng Zhai, Yang Liu, Yuzheng Wang, Zhaoyu Chen","submitted_at":"2024-03-08T03:55:27Z","abstract_excerpt":"Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably suffers from unplanned dataset biases, particularly multimodal utterance-level label bias and word-level context bias. These harmful biases potentially mislead models to focus on statistical shortcuts and spurious correlations, causing severe performance bottlenecks. To alleviate these issues, we present a Multimodal Counterfactual Inference Sentiment (MCIS) analysis framework ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05023","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/2403.05023/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":"2403.05023","created_at":"2026-07-05T08:40:14.536796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05023v2","created_at":"2026-07-05T08:40:14.536796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05023","created_at":"2026-07-05T08:40:14.536796+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBEJJWAMBLJA","created_at":"2026-07-05T08:40:14.536796+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBEJJWAMBLJAFB7G","created_at":"2026-07-05T08:40:14.536796+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBEJJWAM","created_at":"2026-07-05T08:40:14.536796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17505","citing_title":"More is Less? A Simulation-Based Approach to Dynamic Interactions between Biases in Multimodal Models","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY","json":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY.json","graph_json":"https://pith.science/api/pith-number/HBEJJWAMBLJAFB7GXHSAYCYUYY/graph.json","events_json":"https://pith.science/api/pith-number/HBEJJWAMBLJAFB7GXHSAYCYUYY/events.json","paper":"https://pith.science/paper/HBEJJWAM"},"agent_actions":{"view_html":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY","download_json":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY.json","view_paper":"https://pith.science/paper/HBEJJWAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05023&json=true","fetch_graph":"https://pith.science/api/pith-number/HBEJJWAMBLJAFB7GXHSAYCYUYY/graph.json","fetch_events":"https://pith.science/api/pith-number/HBEJJWAMBLJAFB7GXHSAYCYUYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY/action/storage_attestation","attest_author":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY/action/author_attestation","sign_citation":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY/action/citation_signature","submit_replication":"https://pith.science/pith/HBEJJWAMBLJAFB7GXHSAYCYUYY/action/replication_record"}},"created_at":"2026-07-05T08:40:14.536796+00:00","updated_at":"2026-07-05T08:40:14.536796+00:00"}