{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6R3HMRXO7FHUW5P76NDEG2FKPJ","short_pith_number":"pith:6R3HMRXO","schema_version":"1.0","canonical_sha256":"f4767646eef94f4b75fff3464368aa7a5b1645e48590c1c5a5749fe772fb8645","source":{"kind":"arxiv","id":"2508.02429","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiesen Long, Miaosen Luo, Sijie Mai, Yuncheng Jiang, Yunying Yang, Zequn Li","submitted_at":"2025-08-04T13:49:03Z","abstract_excerpt":"Multimodal Affective Computing (MAC) aims to recognize and interpret human emotions by integrating information from diverse modalities such as text, video, and audio. Recent advancements in Multimodal Large Language Models (MLLMs) have significantly reshaped the landscape of MAC by offering a unified framework for processing and aligning cross-modal information. However, practical challenges remain, including performance variability across complex MAC tasks and insufficient understanding of how architectural designs and data characteristics impact affective analysis. To address these gaps, we "},"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":"2508.02429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T13:49:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a1e787ed67d9a32a422499925ac87965385f9d67a5df6080348f7f025487976d","abstract_canon_sha256":"25214a2539a44bae2ef6aa262758cf3503bac7d4146a433d690aed4315a2ec46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:14.262253Z","signature_b64":"BOHv0pE6pR3d8GBoPR7PCpiY2BCdpo0PRpEIZthorQdIdbezhvk/KGbCNulN+4e0tPoL6zFl2bHQSJ1IPiTSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4767646eef94f4b75fff3464368aa7a5b1645e48590c1c5a5749fe772fb8645","last_reissued_at":"2026-07-05T11:48:14.261769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:14.261769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiesen Long, Miaosen Luo, Sijie Mai, Yuncheng Jiang, Yunying Yang, Zequn Li","submitted_at":"2025-08-04T13:49:03Z","abstract_excerpt":"Multimodal Affective Computing (MAC) aims to recognize and interpret human emotions by integrating information from diverse modalities such as text, video, and audio. Recent advancements in Multimodal Large Language Models (MLLMs) have significantly reshaped the landscape of MAC by offering a unified framework for processing and aligning cross-modal information. However, practical challenges remain, including performance variability across complex MAC tasks and insufficient understanding of how architectural designs and data characteristics impact affective analysis. To address these gaps, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02429","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/2508.02429/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":"2508.02429","created_at":"2026-07-05T11:48:14.261827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02429v1","created_at":"2026-07-05T11:48:14.261827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02429","created_at":"2026-07-05T11:48:14.261827+00:00"},{"alias_kind":"pith_short_12","alias_value":"6R3HMRXO7FHU","created_at":"2026-07-05T11:48:14.261827+00:00"},{"alias_kind":"pith_short_16","alias_value":"6R3HMRXO7FHUW5P7","created_at":"2026-07-05T11:48:14.261827+00:00"},{"alias_kind":"pith_short_8","alias_value":"6R3HMRXO","created_at":"2026-07-05T11:48:14.261827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.00013","citing_title":"C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ","json":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ.json","graph_json":"https://pith.science/api/pith-number/6R3HMRXO7FHUW5P76NDEG2FKPJ/graph.json","events_json":"https://pith.science/api/pith-number/6R3HMRXO7FHUW5P76NDEG2FKPJ/events.json","paper":"https://pith.science/paper/6R3HMRXO"},"agent_actions":{"view_html":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ","download_json":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ.json","view_paper":"https://pith.science/paper/6R3HMRXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02429&json=true","fetch_graph":"https://pith.science/api/pith-number/6R3HMRXO7FHUW5P76NDEG2FKPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6R3HMRXO7FHUW5P76NDEG2FKPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ/action/storage_attestation","attest_author":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ/action/author_attestation","sign_citation":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ/action/citation_signature","submit_replication":"https://pith.science/pith/6R3HMRXO7FHUW5P76NDEG2FKPJ/action/replication_record"}},"created_at":"2026-07-05T11:48:14.261827+00:00","updated_at":"2026-07-05T11:48:14.261827+00:00"}