{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QBNBTLIKTH5GZZRDZWBNKZBK7G","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":"d4bfe3ef0f201e3c89d150ecc343a295cb4c526a9ed0a97506291959a5bd1ef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T10:30:53Z","title_canon_sha256":"46f355d52e1e5a59b9d063d2750f073c1712a00d3375d7fb7768363403138010"},"schema_version":"1.0","source":{"id":"2605.10325","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10325","created_at":"2026-05-28T02:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10325v2","created_at":"2026-05-28T02:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10325","created_at":"2026-05-28T02:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"QBNBTLIKTH5G","created_at":"2026-05-28T02:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"QBNBTLIKTH5GZZRD","created_at":"2026-05-28T02:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"QBNBTLIK","created_at":"2026-05-28T02:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:35cd9299a0e5c530541541237d7ccbea7d045c39c179cde90d088b4bee17ce99","target":"graph","created_at":"2026-05-28T02:04:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"dense verifier-grounded rewards can improve long-horizon credit assignment by providing more localized learning signals, with the benefit depending on the reliability of the verifier. Empirically, VPR outperforms outcome-level reward and rollout-based process reward baselines across controlled environments, and more importantly, transfers to both general and agentic reasoning benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That reliable symbolic, algorithmic, or posterior-based oracles exist for verifying intermediate actions in the studied densely-verifiable agentic reasoning problems, and that the learned skills transfer meaningfully beyond the specific training environments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Verifiable Process Rewards (VPR) converts symbolic oracles into dense turn-level supervision for reinforcement learning in agentic reasoning, outperforming outcome-only rewards and transferring to general benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Converting oracles into dense turn-level rewards improves credit assignment for long-horizon LLM agent reasoning."}],"snapshot_sha256":"5a80f2e6b22834041601d60e6a06411bcac1561c146f1d549fb15dd32f872c33"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ab14a2bba61a9cf04afef2acb9fb54b785580336a47c1a077436088b88f1d0c8"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:02:01.181511Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:35:52.703771Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:18.913231Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:28:02.357747Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10325/integrity.json","findings":[],"snapshot_sha256":"6af5b09c74a15e3f5f3775966c56be195131b94fa01518981aacabe99cfc8cb5","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of large language models (LLMs), but most existing approaches rely on sparse outcome-level feedback. This sparsity creates a credit assignment challenge in long-horizon agentic reasoning: a trajectory may fail despite containing many correct intermediate decisions, or succeed despite containing flawed ones. In this work, we study a class of densely-verifiable agentic reasoning problems, where intermediate actions can be objectively checked by symbolic or algorithmic oracles. We propose Verifiable Process","authors_text":"Chao Yu, Huaijie Wang, Huining Yuan, Jiaxuan Gao, Xiangmin Yi, Xiao-Ping Zhang, Yi Wu, Yu Wang, Zelai Xu","cross_cats":[],"headline":"Converting oracles into dense turn-level rewards improves credit assignment for long-horizon LLM agent reasoning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T10:30:53Z","title":"Verifiable Process Rewards for Agentic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10325","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T04:54:42.341354Z","id":"dffaaed6-739f-4f55-a565-297817bdf206","model_set":{"reader":"grok-4.3"},"one_line_summary":"Verifiable Process Rewards (VPR) converts symbolic oracles into dense turn-level supervision for reinforcement learning in agentic reasoning, outperforming outcome-only rewards and transferring to general benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Converting oracles into dense turn-level rewards improves credit assignment for long-horizon LLM agent reasoning.","strongest_claim":"dense verifier-grounded rewards can improve long-horizon credit assignment by providing more localized learning signals, with the benefit depending on the reliability of the verifier. Empirically, VPR outperforms outcome-level reward and rollout-based process reward baselines across controlled environments, and more importantly, transfers to both general and agentic reasoning benchmarks.","weakest_assumption":"That reliable symbolic, algorithmic, or posterior-based oracles exist for verifying intermediate actions in the studied densely-verifiable agentic reasoning problems, and that the learned skills transfer meaningfully beyond the specific training environments."}},"verdict_id":"dffaaed6-739f-4f55-a565-297817bdf206"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b677f786adac74a9f82fd78d2e035d618fd497231ce17090bb22b5b881fbc0f5","target":"record","created_at":"2026-05-28T02:04:49Z","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":"d4bfe3ef0f201e3c89d150ecc343a295cb4c526a9ed0a97506291959a5bd1ef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T10:30:53Z","title_canon_sha256":"46f355d52e1e5a59b9d063d2750f073c1712a00d3375d7fb7768363403138010"},"schema_version":"1.0","source":{"id":"2605.10325","kind":"arxiv","version":2}},"canonical_sha256":"805a19ad0a99fa6ce623cd82d5642af9ba0424bf4f31a4787edca92ca4459fb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"805a19ad0a99fa6ce623cd82d5642af9ba0424bf4f31a4787edca92ca4459fb0","first_computed_at":"2026-05-28T02:04:49.287358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:49.287358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNRxAIzbndZBg+qoGenU9Wry/QT2cvY/KCgK0muiny9OSwtwOuYjLkMvphYkjh6HKz5LJNPQcVrSg3PcOnLeAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:49.287885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10325","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b677f786adac74a9f82fd78d2e035d618fd497231ce17090bb22b5b881fbc0f5","sha256:35cd9299a0e5c530541541237d7ccbea7d045c39c179cde90d088b4bee17ce99"],"state_sha256":"5bf0fe2fd4f4d9657af8b6f8e94d7d1561e06bd0c56bf2648490b9ac5bafafee"}