{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KF2D5P2AJTCECB5RDSJQDQIVH3","short_pith_number":"pith:KF2D5P2A","schema_version":"1.0","canonical_sha256":"51743ebf404cc44107b11c9301c1153ec4552c0927406ba3b57f9a947de4d770","source":{"kind":"arxiv","id":"2408.04203","version":2},"attestation_state":"computed","paper":{"title":"MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen, Yanqi Dai, Zhiwu Lu","submitted_at":"2024-08-08T03:57:20Z","abstract_excerpt":"Recently, Role-Playing Agents (RPAs) have garnered increasing attention for their potential to deliver emotional value and facilitate sociological research. However, existing studies are primarily confined to the textual modality, unable to simulate humans' multimodal perceptual capabilities. To bridge this gap, we introduce the concept of Multimodal Role-Playing Agents (MRPAs), and propose a comprehensive framework, MMRole, for their development and evaluation, which comprises a personalized multimodal dataset and a robust evaluation approach. Specifically, we construct a large-scale, high-qu"},"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":"2408.04203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-08T03:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"9b5113d1a44d5021f1f5f8f8f74136532f71fd90ebd771bf6ffccb8ef5f72732","abstract_canon_sha256":"55c39fc8ad07bd61468ff1221369fa886b3df897b3170e413457563b52931ba9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:18.794816Z","signature_b64":"KsuVijBQuLhtXskvP/W0/E4JdsNn2uigfjZH1y8/kl+NvyfAnYTNP9Z3mY/nTYh2x1BgftviTZ6gvw8w4KPdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51743ebf404cc44107b11c9301c1153ec4552c0927406ba3b57f9a947de4d770","last_reissued_at":"2026-07-05T10:15:18.794295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:18.794295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen, Yanqi Dai, Zhiwu Lu","submitted_at":"2024-08-08T03:57:20Z","abstract_excerpt":"Recently, Role-Playing Agents (RPAs) have garnered increasing attention for their potential to deliver emotional value and facilitate sociological research. However, existing studies are primarily confined to the textual modality, unable to simulate humans' multimodal perceptual capabilities. To bridge this gap, we introduce the concept of Multimodal Role-Playing Agents (MRPAs), and propose a comprehensive framework, MMRole, for their development and evaluation, which comprises a personalized multimodal dataset and a robust evaluation approach. Specifically, we construct a large-scale, high-qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04203","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/2408.04203/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":"2408.04203","created_at":"2026-07-05T10:15:18.794365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04203v2","created_at":"2026-07-05T10:15:18.794365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04203","created_at":"2026-07-05T10:15:18.794365+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF2D5P2AJTCE","created_at":"2026-07-05T10:15:18.794365+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF2D5P2AJTCECB5R","created_at":"2026-07-05T10:15:18.794365+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF2D5P2A","created_at":"2026-07-05T10:15:18.794365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01552","citing_title":"RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11103","citing_title":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15127","citing_title":"MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3","json":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3.json","graph_json":"https://pith.science/api/pith-number/KF2D5P2AJTCECB5RDSJQDQIVH3/graph.json","events_json":"https://pith.science/api/pith-number/KF2D5P2AJTCECB5RDSJQDQIVH3/events.json","paper":"https://pith.science/paper/KF2D5P2A"},"agent_actions":{"view_html":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3","download_json":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3.json","view_paper":"https://pith.science/paper/KF2D5P2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04203&json=true","fetch_graph":"https://pith.science/api/pith-number/KF2D5P2AJTCECB5RDSJQDQIVH3/graph.json","fetch_events":"https://pith.science/api/pith-number/KF2D5P2AJTCECB5RDSJQDQIVH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3/action/storage_attestation","attest_author":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3/action/author_attestation","sign_citation":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3/action/citation_signature","submit_replication":"https://pith.science/pith/KF2D5P2AJTCECB5RDSJQDQIVH3/action/replication_record"}},"created_at":"2026-07-05T10:15:18.794365+00:00","updated_at":"2026-07-05T10:15:18.794365+00:00"}