{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3DPSJNI3I4CXBM6H5VTIDZC7AQ","short_pith_number":"pith:3DPSJNI3","schema_version":"1.0","canonical_sha256":"d8df24b51b470570b3c7ed6681e45f040f294bec51e3d1dde42a97ea6020ebf6","source":{"kind":"arxiv","id":"2503.11241","version":1},"attestation_state":"computed","paper":{"title":"Compound Expression Recognition via Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Yu, Xilong Lu","submitted_at":"2025-03-14T09:46:05Z","abstract_excerpt":"Compound Expression Recognition (CER) is crucial for understanding human emotions and improving human-computer interaction. However, CER faces challenges due to the complexity of facial expressions and the difficulty of capturing subtle emotional cues. To address these issues, we propose a novel approach leveraging Large Vision-Language Models (LVLMs). Our method employs a two-stage fine-tuning process: first, pre-trained LVLMs are fine-tuned on basic facial expressions to establish foundational patterns; second, the model is further optimized on a compound-expression dataset to refine visual-"},"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":"2503.11241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T09:46:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5e02904dd872025e05eb20e027adbb95c09c77f1d2ec674b17cadbf64cd29747","abstract_canon_sha256":"8ed3e08324f42ff4626bc033758e38aed2b20b434da85a71e8aa6a183dd28c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:15.018801Z","signature_b64":"P3HTwAo0W7P5UnERIdfCLVcQfk2IxQkuh3JAYmoXVe55f/tDqOlBJ1vwxKXmucQTXlwixVZ/BzDx+5AnJaFXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8df24b51b470570b3c7ed6681e45f040f294bec51e3d1dde42a97ea6020ebf6","last_reissued_at":"2026-07-05T10:31:15.017935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:15.017935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compound Expression Recognition via Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Yu, Xilong Lu","submitted_at":"2025-03-14T09:46:05Z","abstract_excerpt":"Compound Expression Recognition (CER) is crucial for understanding human emotions and improving human-computer interaction. However, CER faces challenges due to the complexity of facial expressions and the difficulty of capturing subtle emotional cues. To address these issues, we propose a novel approach leveraging Large Vision-Language Models (LVLMs). Our method employs a two-stage fine-tuning process: first, pre-trained LVLMs are fine-tuned on basic facial expressions to establish foundational patterns; second, the model is further optimized on a compound-expression dataset to refine visual-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11241","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/2503.11241/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":"2503.11241","created_at":"2026-07-05T10:31:15.018046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11241v1","created_at":"2026-07-05T10:31:15.018046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11241","created_at":"2026-07-05T10:31:15.018046+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DPSJNI3I4CX","created_at":"2026-07-05T10:31:15.018046+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DPSJNI3I4CXBM6H","created_at":"2026-07-05T10:31:15.018046+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DPSJNI3","created_at":"2026-07-05T10:31:15.018046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03166","citing_title":"Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ","json":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ.json","graph_json":"https://pith.science/api/pith-number/3DPSJNI3I4CXBM6H5VTIDZC7AQ/graph.json","events_json":"https://pith.science/api/pith-number/3DPSJNI3I4CXBM6H5VTIDZC7AQ/events.json","paper":"https://pith.science/paper/3DPSJNI3"},"agent_actions":{"view_html":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ","download_json":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ.json","view_paper":"https://pith.science/paper/3DPSJNI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11241&json=true","fetch_graph":"https://pith.science/api/pith-number/3DPSJNI3I4CXBM6H5VTIDZC7AQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3DPSJNI3I4CXBM6H5VTIDZC7AQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ/action/storage_attestation","attest_author":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ/action/author_attestation","sign_citation":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ/action/citation_signature","submit_replication":"https://pith.science/pith/3DPSJNI3I4CXBM6H5VTIDZC7AQ/action/replication_record"}},"created_at":"2026-07-05T10:31:15.018046+00:00","updated_at":"2026-07-05T10:31:15.018046+00:00"}