{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z5LEDNXBBIS6SRVRTRZ6DXFIHL","short_pith_number":"pith:Z5LEDNXB","schema_version":"1.0","canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","source":{"kind":"arxiv","id":"2505.02331","version":2},"attestation_state":"computed","paper":{"title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Hao Cheng, Jia Li, Meng Wang, Richang Hong, Yichao He, Zhenzhen Hu, Zhiwei Zhao","submitted_at":"2025-05-05T03:00:51Z","abstract_excerpt":"Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issu"},"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":"2505.02331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T03:00:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3134381c6b0e45a5903dac9bcbe1034c5c9893fe8744e4d31336cdfc532bb78d","abstract_canon_sha256":"4e85b53e0fd14eb09864aa1beac0fe97f1642e16c77d616783a3f178cbd41838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:22.532017Z","signature_b64":"Qmpj6Qua9iPSuJ+ey8QB8lR/GfHCnrrTGXnB2X2eBwQnu0pY08qvNNRJfQebCmMUfOHOmsAewKVSeUWf6D56Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","last_reissued_at":"2026-07-05T11:47:22.531534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:22.531534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Hao Cheng, Jia Li, Meng Wang, Richang Hong, Yichao He, Zhenzhen Hu, Zhiwei Zhao","submitted_at":"2025-05-05T03:00:51Z","abstract_excerpt":"Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02331","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/2505.02331/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":"2505.02331","created_at":"2026-07-05T11:47:22.531586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02331v2","created_at":"2026-07-05T11:47:22.531586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02331","created_at":"2026-07-05T11:47:22.531586+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5LEDNXBBIS6","created_at":"2026-07-05T11:47:22.531586+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5LEDNXBBIS6SRVR","created_at":"2026-07-05T11:47:22.531586+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5LEDNXB","created_at":"2026-07-05T11:47:22.531586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL","json":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL.json","graph_json":"https://pith.science/api/pith-number/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/graph.json","events_json":"https://pith.science/api/pith-number/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/events.json","paper":"https://pith.science/paper/Z5LEDNXB"},"agent_actions":{"view_html":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL","download_json":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL.json","view_paper":"https://pith.science/paper/Z5LEDNXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02331&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/action/storage_attestation","attest_author":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/action/author_attestation","sign_citation":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/action/citation_signature","submit_replication":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/action/replication_record"}},"created_at":"2026-07-05T11:47:22.531586+00:00","updated_at":"2026-07-05T11:47:22.531586+00:00"}