{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLDIFCWNF3LD7WHWZDAKEENUM2","short_pith_number":"pith:WLDIFCWN","schema_version":"1.0","canonical_sha256":"b2c6828acd2ed63fd8f6c8c0a211b466a3d8e4f9637c7a08a7e78652762e5bff","source":{"kind":"arxiv","id":"2503.06553","version":1},"attestation_state":"computed","paper":{"title":"ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Baojin Huang, Fanrui Zhang, Jianwen Sun, Jiaxin Ai, Kaipeng Zhang, Ming Li, Pengfei Zhou, Yukang Feng, Zhaopan Xu, Zhongyuan Wang, Zizhen Li","submitted_at":"2025-03-09T10:55:51Z","abstract_excerpt":"As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grained model weaknesses. Since human evaluation is laborious and costly, prompting MLLMs as automated process judges has become a common practice. However, the reliability of these model-based judges remains uncertain. To address this, we introduce ProJudgeBench, the first comprehensive benchmark specifically designed for evaluating abilities of MLLM-based process judges. ProJudgeB"},"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":"2503.06553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-09T10:55:51Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0bf0cf302736d4cd930dc3e36c001aadef9c861de7340bc138438f83721f02cc","abstract_canon_sha256":"3b98002fdb6d7c410c1e842484c0c65005d3f4982dd15313b784ad8cc9889517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:36.866472Z","signature_b64":"COIa4ZGQsQy+vuMnE6MJh2Tq0fWAPf6L+8EnwRlCZN0NlPGwHC9V+gW0JyYUH+IvFF6E8c/G1UIocKTnpy9bDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2c6828acd2ed63fd8f6c8c0a211b466a3d8e4f9637c7a08a7e78652762e5bff","last_reissued_at":"2026-07-05T10:27:36.865588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:36.865588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Baojin Huang, Fanrui Zhang, Jianwen Sun, Jiaxin Ai, Kaipeng Zhang, Ming Li, Pengfei Zhou, Yukang Feng, Zhaopan Xu, Zhongyuan Wang, Zizhen Li","submitted_at":"2025-03-09T10:55:51Z","abstract_excerpt":"As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grained model weaknesses. Since human evaluation is laborious and costly, prompting MLLMs as automated process judges has become a common practice. However, the reliability of these model-based judges remains uncertain. To address this, we introduce ProJudgeBench, the first comprehensive benchmark specifically designed for evaluating abilities of MLLM-based process judges. ProJudgeB"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06553","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/2503.06553/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":"2503.06553","created_at":"2026-07-05T10:27:36.865715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06553v1","created_at":"2026-07-05T10:27:36.865715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06553","created_at":"2026-07-05T10:27:36.865715+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLDIFCWNF3LD","created_at":"2026-07-05T10:27:36.865715+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLDIFCWNF3LD7WHW","created_at":"2026-07-05T10:27:36.865715+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLDIFCWN","created_at":"2026-07-05T10:27:36.865715+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/WLDIFCWNF3LD7WHWZDAKEENUM2","json":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2.json","graph_json":"https://pith.science/api/pith-number/WLDIFCWNF3LD7WHWZDAKEENUM2/graph.json","events_json":"https://pith.science/api/pith-number/WLDIFCWNF3LD7WHWZDAKEENUM2/events.json","paper":"https://pith.science/paper/WLDIFCWN"},"agent_actions":{"view_html":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2","download_json":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2.json","view_paper":"https://pith.science/paper/WLDIFCWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06553&json=true","fetch_graph":"https://pith.science/api/pith-number/WLDIFCWNF3LD7WHWZDAKEENUM2/graph.json","fetch_events":"https://pith.science/api/pith-number/WLDIFCWNF3LD7WHWZDAKEENUM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2/action/storage_attestation","attest_author":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2/action/author_attestation","sign_citation":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2/action/citation_signature","submit_replication":"https://pith.science/pith/WLDIFCWNF3LD7WHWZDAKEENUM2/action/replication_record"}},"created_at":"2026-07-05T10:27:36.865715+00:00","updated_at":"2026-07-05T10:27:36.865715+00:00"}