{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4QW3B5Q3P6OOWHNMOFTPPC7PNR","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":"5dcb59c3affc11e7dbb94813c3bb265e115f80a9daa481b2cbe3d1e2558bf644","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T15:25:24Z","title_canon_sha256":"27ef9f0a050d34357f73134ebaa98eae727e06c4416c99058a56b0e2789df648"},"schema_version":"1.0","source":{"id":"2508.03556","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03556","created_at":"2026-05-22T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03556v3","created_at":"2026-05-22T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03556","created_at":"2026-05-22T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"4QW3B5Q3P6OO","created_at":"2026-05-22T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"4QW3B5Q3P6OOWHNM","created_at":"2026-05-22T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"4QW3B5Q3","created_at":"2026-05-22T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:7744cae41e628426a9d4d0c62e48f047d15712fba1e65e45a8cf7045c03c84f0","target":"graph","created_at":"2026-05-22T01:03:44Z","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/2508.03556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep thinking capabilities. On the other hand, although a few works have tried to introduce Chain-of-Thought (CoT) capability into PRMs, the annotation cost of CoT-PRM data is too expensive to play a stable role in various tasks. To address the above challenges, we propose VRPRM, a process reward model via visual reasoning, and design an efficient two-stage trainin","authors_text":"Bangwei Liu, Chaochao Lu, Chongying Yue, Xinquan Chen, Xuhong Wang, Yingchun Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T15:25:24Z","title":"VRPRM: Process Reward Modeling via Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03556","kind":"arxiv","version":3},"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":"sha256:5757b32e0f0c8200f3dcba62f06a0ae8222eb395dd1b176a33bb7acceaa45cce","target":"record","created_at":"2026-05-22T01:03:44Z","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":"5dcb59c3affc11e7dbb94813c3bb265e115f80a9daa481b2cbe3d1e2558bf644","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T15:25:24Z","title_canon_sha256":"27ef9f0a050d34357f73134ebaa98eae727e06c4416c99058a56b0e2789df648"},"schema_version":"1.0","source":{"id":"2508.03556","kind":"arxiv","version":3}},"canonical_sha256":"e42db0f61b7f9ceb1dac7166f78bef6c41a9678393441912669ccaf34f5e4db4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e42db0f61b7f9ceb1dac7166f78bef6c41a9678393441912669ccaf34f5e4db4","first_computed_at":"2026-05-22T01:03:44.866933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:44.866933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JSfa8iT7tTIBk61Y6icoK99lSCMzGj1/TqRZ0h7U/HdVcOi7K+2Gstva3tpXc7V9IwPqpVrIU/NTdmalOZO6DA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:44.867945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03556","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5757b32e0f0c8200f3dcba62f06a0ae8222eb395dd1b176a33bb7acceaa45cce","sha256:7744cae41e628426a9d4d0c62e48f047d15712fba1e65e45a8cf7045c03c84f0"],"state_sha256":"9ec8aba830f732ee98fdbea515bb924fe39e4834eaf9ae0507a9237ac28224b6"}