{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VD3RWGRIYHL3YVUCMG2QGMEUGX","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":"4b3b3660441d1a6cc2afd28ec2db1e0066ff2cf45a0328caf3eab5e9477b218d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T21:25:47Z","title_canon_sha256":"9fd675b3dd572e9c9fcf842b91aec0056128902b90a3c89809340c6c5821559a"},"schema_version":"1.0","source":{"id":"2606.11209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11209","created_at":"2026-06-11T00:08:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11209v1","created_at":"2026-06-11T00:08:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11209","created_at":"2026-06-11T00:08:06Z"},{"alias_kind":"pith_short_12","alias_value":"VD3RWGRIYHL3","created_at":"2026-06-11T00:08:06Z"},{"alias_kind":"pith_short_16","alias_value":"VD3RWGRIYHL3YVUC","created_at":"2026-06-11T00:08:06Z"},{"alias_kind":"pith_short_8","alias_value":"VD3RWGRI","created_at":"2026-06-11T00:08:06Z"}],"graph_snapshots":[{"event_id":"sha256:26da7aee96e07bb8ebcb72f8afb6d8a5b578aeb91c5f0d868a4726e7b8c122fc","target":"graph","created_at":"2026-06-11T00:08:06Z","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/2606.11209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Optimization (GRPO) can improve multimodal reasoning, but most approaches rely on sparse outcome-only rewards. As a result, they struggle to tell whether an incorrect answer comes from a small mistake late in the reasoning or from an unhelpful trajectory from the start. A common solution is to train a process reward model (PRM) for step-level supervision, but this typically requires large-scale high-quality chain-of-tho","authors_text":"Boer Zhang, Jingpei Wu, Volker Tresp, Weixiang Shen, Xiao Han, Zifeng Ding","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T21:25:47Z","title":"ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11209","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":"sha256:9b33b18f66b749113139bba182160f387bf3f4cf95206e7158167797c6dd084c","target":"record","created_at":"2026-06-11T00:08:06Z","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":"4b3b3660441d1a6cc2afd28ec2db1e0066ff2cf45a0328caf3eab5e9477b218d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T21:25:47Z","title_canon_sha256":"9fd675b3dd572e9c9fcf842b91aec0056128902b90a3c89809340c6c5821559a"},"schema_version":"1.0","source":{"id":"2606.11209","kind":"arxiv","version":1}},"canonical_sha256":"a8f71b1a28c1d7bc568261b503309435e2cb88a17018ac01ce298279fee3d4b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8f71b1a28c1d7bc568261b503309435e2cb88a17018ac01ce298279fee3d4b3","first_computed_at":"2026-06-11T00:08:06.588599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T00:08:06.588599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iEIsCQgf93OEPj17q4gcuh1oUpX+pK7DNweHx8Yl1dQtlljOEHNxdmRksqcdiJYq0HZzCM4jmEbNUqdZnFtpAw==","signature_status":"signed_v1","signed_at":"2026-06-11T00:08:06.589719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b33b18f66b749113139bba182160f387bf3f4cf95206e7158167797c6dd084c","sha256:26da7aee96e07bb8ebcb72f8afb6d8a5b578aeb91c5f0d868a4726e7b8c122fc"],"state_sha256":"4ea5d520a9e4d0375a5105d477a767aff958c6e0fc80c77c500c6eabe39cc9c7"}