{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M3WLDAWYXA6CVUQWXQUFQJUXKD","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":"28891819b004197d9bcd47e44e5ac1eebeab7c306953cd2279f529ab9beba960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T05:56:26Z","title_canon_sha256":"767f6ae51e440ae2a72a010da32e165a839b0c5617cf86cfb6a1d044d8859276"},"schema_version":"1.0","source":{"id":"2501.07861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07861","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07861v1","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07861","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"M3WLDAWYXA6C","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"M3WLDAWYXA6CVUQW","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"M3WLDAWY","created_at":"2026-07-05T10:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:892b927c560104e55888473f759c6d5fa47593db2d943401f0eaec2bc52f899f","target":"graph","created_at":"2026-07-05T10:00:51Z","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/2501.07861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought reasoning or test-time search using Process Reward Models (PRMs), these approaches encounter challenges such as a lack of explanations, bias in PRM training data, early-step bias in PRM scores, and insufficient post-training optimization of reasoning potential. To address these issues, we propose Retrieval-Augmented Reasoning through Trustworthy Process Rewardi","authors_text":"Han Li, Jun Xu, Kai Zheng, Qipeng Wang, Song Yang, Weijie Yu, Xiaoxue Zang, Xiao Zhang, Zhongxiang Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T05:56:26Z","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07861","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":"sha256:5d5616fd2b2c890a27f88b99db27822e4cce016e1c6be4966180f13eeb723803","target":"record","created_at":"2026-07-05T10:00:51Z","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":"28891819b004197d9bcd47e44e5ac1eebeab7c306953cd2279f529ab9beba960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T05:56:26Z","title_canon_sha256":"767f6ae51e440ae2a72a010da32e165a839b0c5617cf86cfb6a1d044d8859276"},"schema_version":"1.0","source":{"id":"2501.07861","kind":"arxiv","version":1}},"canonical_sha256":"66ecb182d8b83c2ad216bc2858269750eb8859ee24a0fab7c40992a881376d25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66ecb182d8b83c2ad216bc2858269750eb8859ee24a0fab7c40992a881376d25","first_computed_at":"2026-07-05T10:00:51.523819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:51.523819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dkopqOSgWSMAYZgeYyWogS3FZ4MtSK5HrmK9nao5PB2JZZ1CsMJuWlM8eZtNkCxJSd49IRrlCODfZyH5P12FAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:51.524286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d5616fd2b2c890a27f88b99db27822e4cce016e1c6be4966180f13eeb723803","sha256:892b927c560104e55888473f759c6d5fa47593db2d943401f0eaec2bc52f899f"],"state_sha256":"a2fd64b48f89d8d2e36194fa8aa3f623069536634a48ba1787e9f9b4d33e3575"}