{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JALWBCBD2XSK7WVJWACXRWQWLP","short_pith_number":"pith:JALWBCBD","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"},"canonical_sha256":"4817608823d5e4afdaa9b00578da165be782d7e8ca4dd8cc3382bc76bcb67800","source":{"kind":"arxiv","id":"2503.12505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12505","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12505v1","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12505","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"JALWBCBD2XSK","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_16","alias_value":"JALWBCBD2XSK7WVJ","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_8","alias_value":"JALWBCBD","created_at":"2026-07-05T10:32:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JALWBCBD2XSK7WVJWACXRWQWLP","target":"record","payload":{"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"},"canonical_sha256":"4817608823d5e4afdaa9b00578da165be782d7e8ca4dd8cc3382bc76bcb67800","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"},"source_kind":"arxiv","source_id":"2503.12505","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QixLbQjMMqd2kTIbyvTLwv9p1JOHdTeaGahzvhYHUHzCNbLGVSXs4VwKFIK4wpvLZtXXkreZrVHEWLlqNYRbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:52:14.178839Z"},"content_sha256":"fa1e6737c651dab2dbc190f62f6f406ae1fa0ebd3d822e28c0202fd166cad205","schema_version":"1.0","event_id":"sha256:fa1e6737c651dab2dbc190f62f6f406ae1fa0ebd3d822e28c0202fd166cad205"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JALWBCBD2XSK7WVJWACXRWQWLP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uz/l1alJMrD2BFzr55Ni1G9HPfje2l2uwTakYy5xN+S3i2ivs9vVmnd/n+aKE+a0aX6VHCuaANpX2wbmIcJZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:52:14.179240Z"},"content_sha256":"ee4229d5d2c0502daca9ef7a3c6612f81a9d4763db561f356b56dfc3d06c9f30","schema_version":"1.0","event_id":"sha256:ee4229d5d2c0502daca9ef7a3c6612f81a9d4763db561f356b56dfc3d06c9f30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/bundle.json","state_url":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JALWBCBD2XSK7WVJWACXRWQWLP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T05:52:14Z","links":{"resolver":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP","bundle":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/bundle.json","state":"https://pith.science/pith/JALWBCBD2XSK7WVJWACXRWQWLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JALWBCBD2XSK7WVJWACXRWQWLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JALWBCBD2XSK7WVJWACXRWQWLP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d977d256327c7e0982e3448e1827f362d835cb9d4b114e9dd18d9eb8d8e269d8","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-16T13:50:38Z","title_canon_sha256":"942dc988a6c94a749c18a3a6d3a013afbed15d4bccbef623294f5bbc98bed36c"},"schema_version":"1.0","source":{"id":"2503.12505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12505","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12505v1","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12505","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"JALWBCBD2XSK","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_16","alias_value":"JALWBCBD2XSK7WVJ","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_8","alias_value":"JALWBCBD","created_at":"2026-07-05T10:32:15Z"}],"graph_snapshots":[{"event_id":"sha256:ee4229d5d2c0502daca9ef7a3c6612f81a9d4763db561f356b56dfc3d06c9f30","target":"graph","created_at":"2026-07-05T10:32:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.12505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongxun Yao, Jiaxin Ai, Kaipeng Zhang, Kai Wang, Pengfei Zhou, Wangbo Zhao, Wenqi Shao, Xiaojiang Peng, Zhaopan Xu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-16T13:50:38Z","title":"MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12505","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fa1e6737c651dab2dbc190f62f6f406ae1fa0ebd3d822e28c0202fd166cad205","target":"record","created_at":"2026-07-05T10:32:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d977d256327c7e0982e3448e1827f362d835cb9d4b114e9dd18d9eb8d8e269d8","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-16T13:50:38Z","title_canon_sha256":"942dc988a6c94a749c18a3a6d3a013afbed15d4bccbef623294f5bbc98bed36c"},"schema_version":"1.0","source":{"id":"2503.12505","kind":"arxiv","version":1}},"canonical_sha256":"4817608823d5e4afdaa9b00578da165be782d7e8ca4dd8cc3382bc76bcb67800","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4817608823d5e4afdaa9b00578da165be782d7e8ca4dd8cc3382bc76bcb67800","first_computed_at":"2026-07-05T10:32:15.062608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:15.062608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1E1994enO6Qwdx7m3R9l2vrbYj+b+W4M6Bvge0hREA61zohJdTyEUwTQxDC031kAfQuyNx0Re4V8z4mfU5EeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:15.063488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa1e6737c651dab2dbc190f62f6f406ae1fa0ebd3d822e28c0202fd166cad205","sha256:ee4229d5d2c0502daca9ef7a3c6612f81a9d4763db561f356b56dfc3d06c9f30"],"state_sha256":"c980e37fdea90dc631a70f1324a14e52fe77f4299dd3e60241e41556e196ee9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTUCBRMX6JArYjW+6xkEtjuGtdSsTlEBuqb2sWUv0PuxCg1KPG14SMJrqjRCR2WQR3Y2r/XaQFvG+FmSgTKJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:52:14.181626Z","bundle_sha256":"7d52d6d4ddc5ad5c25b97dac64da675b321c4e458a23e1aeed14cea1d580d4cb"}}