{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FU7EEXD2TWPFMEUGBNZOGWMGG3","short_pith_number":"pith:FU7EEXD2","schema_version":"1.0","canonical_sha256":"2d3e425c7a9d9e5612860b72e3598636d6ce03b9dc964bfea8ca4ee3bfb93551","source":{"kind":"arxiv","id":"2503.14941","version":1},"attestation_state":"computed","paper":{"title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ye, Li Yuan, Munan Ning, Qihui Zhang, Shuo Yang, Xiao Chen, Yanbo Wang, Yibing Song, Yue Huang, Zheyuan Liu","submitted_at":"2025-03-19T07:15:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation methods face limitations due to the significant human workload required to design Q&A pairs for visual images, which inherently restricts the scale and scope of evaluations. Although automated MLLM-as-judge approaches attempt to reduce the human workload through automatic evaluations, they often introduce biases. To address these problems, we propose an Unsupervised Peer review M"},"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":"2503.14941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T07:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"192c39202567e46ec8cbfc666b1fa54f954acb43a8ffdc5051918f14aead3a90","abstract_canon_sha256":"2f26806e716590be976d27df65ed1e974728293bcfdedccd5cc64873ed87b698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:28.000587Z","signature_b64":"obtkrFnrGNSFK4cyx9UTz85SPhWTrZt2nAro3mI5jJ2xT5EpG82coy3uIXdpHME1Z8uU1IKhU8I9rBVOjCh5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3e425c7a9d9e5612860b72e3598636d6ce03b9dc964bfea8ca4ee3bfb93551","last_reissued_at":"2026-07-05T10:34:27.999765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:27.999765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ye, Li Yuan, Munan Ning, Qihui Zhang, Shuo Yang, Xiao Chen, Yanbo Wang, Yibing Song, Yue Huang, Zheyuan Liu","submitted_at":"2025-03-19T07:15:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation methods face limitations due to the significant human workload required to design Q&A pairs for visual images, which inherently restricts the scale and scope of evaluations. Although automated MLLM-as-judge approaches attempt to reduce the human workload through automatic evaluations, they often introduce biases. To address these problems, we propose an Unsupervised Peer review M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14941","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/2503.14941/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":"2503.14941","created_at":"2026-07-05T10:34:27.999883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14941v1","created_at":"2026-07-05T10:34:27.999883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14941","created_at":"2026-07-05T10:34:27.999883+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU7EEXD2TWPF","created_at":"2026-07-05T10:34:27.999883+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU7EEXD2TWPFMEUG","created_at":"2026-07-05T10:34:27.999883+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU7EEXD2","created_at":"2026-07-05T10:34:27.999883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21008","citing_title":"The Metanym Game: A Self-Contained, Self-Consistent LLM Peer-Community Benchmark for Structural Intelligence","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3","json":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3.json","graph_json":"https://pith.science/api/pith-number/FU7EEXD2TWPFMEUGBNZOGWMGG3/graph.json","events_json":"https://pith.science/api/pith-number/FU7EEXD2TWPFMEUGBNZOGWMGG3/events.json","paper":"https://pith.science/paper/FU7EEXD2"},"agent_actions":{"view_html":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3","download_json":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3.json","view_paper":"https://pith.science/paper/FU7EEXD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14941&json=true","fetch_graph":"https://pith.science/api/pith-number/FU7EEXD2TWPFMEUGBNZOGWMGG3/graph.json","fetch_events":"https://pith.science/api/pith-number/FU7EEXD2TWPFMEUGBNZOGWMGG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3/action/storage_attestation","attest_author":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3/action/author_attestation","sign_citation":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3/action/citation_signature","submit_replication":"https://pith.science/pith/FU7EEXD2TWPFMEUGBNZOGWMGG3/action/replication_record"}},"created_at":"2026-07-05T10:34:27.999883+00:00","updated_at":"2026-07-05T10:34:27.999883+00:00"}