{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JALWBCBD2XSK7WVJWACXRWQWLP","short_pith_number":"pith:JALWBCBD","schema_version":"1.0","canonical_sha256":"4817608823d5e4afdaa9b00578da165be782d7e8ca4dd8cc3382bc76bcb67800","source":{"kind":"arxiv","id":"2503.12505","version":1},"attestation_state":"computed","paper":{"title":"MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hongxun Yao, Jiaxin Ai, Kaipeng Zhang, Kai Wang, Pengfei Zhou, Wangbo Zhao, Wenqi Shao, Xiaojiang Peng, Zhaopan Xu","submitted_at":"2025-03-16T13:50:38Z","abstract_excerpt":"Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recently, process-level reward models (PRMs) were proposed to provide step-wise rewards that facilitate reinforcement learning and data production during training and guide LLMs toward correct steps during inference, thereby improving reasoning accuracy. However, existing benchmarks of PRMs are text-based and focus on error detection, neglecting other scenarios like reasoning search. To address this gap, we introduce MPBen"},"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":"2503.12505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-16T13:50:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"942dc988a6c94a749c18a3a6d3a013afbed15d4bccbef623294f5bbc98bed36c","abstract_canon_sha256":"d977d256327c7e0982e3448e1827f362d835cb9d4b114e9dd18d9eb8d8e269d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:15.063488Z","signature_b64":"1E1994enO6Qwdx7m3R9l2vrbYj+b+W4M6Bvge0hREA61zohJdTyEUwTQxDC031kAfQuyNx0Re4V8z4mfU5EeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4817608823d5e4afdaa9b00578da165be782d7e8ca4dd8cc3382bc76bcb67800","last_reissued_at":"2026-07-05T10:32:15.062608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:15.062608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hongxun Yao, Jiaxin Ai, Kaipeng Zhang, Kai Wang, Pengfei Zhou, Wangbo Zhao, Wenqi Shao, Xiaojiang Peng, Zhaopan Xu","submitted_at":"2025-03-16T13:50:38Z","abstract_excerpt":"Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recently, process-level reward models (PRMs) were proposed to provide step-wise rewards that facilitate reinforcement learning and data production during training and guide LLMs toward correct steps during inference, thereby improving reasoning accuracy. However, existing benchmarks of PRMs are text-based and focus on error detection, neglecting other scenarios like reasoning search. To address this gap, we introduce MPBen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12505","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/2503.12505/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":"2503.12505","created_at":"2026-07-05T10:32:15.062721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12505v1","created_at":"2026-07-05T10:32:15.062721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12505","created_at":"2026-07-05T10:32:15.062721+00:00"},{"alias_kind":"pith_short_12","alias_value":"JALWBCBD2XSK","created_at":"2026-07-05T10:32:15.062721+00:00"},{"alias_kind":"pith_short_16","alias_value":"JALWBCBD2XSK7WVJ","created_at":"2026-07-05T10:32:15.062721+00:00"},{"alias_kind":"pith_short_8","alias_value":"JALWBCBD","created_at":"2026-07-05T10:32:15.062721+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/JALWBCBD2XSK7WVJWACXRWQWLP","json":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP.json","graph_json":"https://pith.science/api/pith-number/JALWBCBD2XSK7WVJWACXRWQWLP/graph.json","events_json":"https://pith.science/api/pith-number/JALWBCBD2XSK7WVJWACXRWQWLP/events.json","paper":"https://pith.science/paper/JALWBCBD"},"agent_actions":{"view_html":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP","download_json":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP.json","view_paper":"https://pith.science/paper/JALWBCBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12505&json=true","fetch_graph":"https://pith.science/api/pith-number/JALWBCBD2XSK7WVJWACXRWQWLP/graph.json","fetch_events":"https://pith.science/api/pith-number/JALWBCBD2XSK7WVJWACXRWQWLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/action/storage_attestation","attest_author":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/action/author_attestation","sign_citation":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/action/citation_signature","submit_replication":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/action/replication_record"}},"created_at":"2026-07-05T10:32:15.062721+00:00","updated_at":"2026-07-05T10:32:15.062721+00:00"}