{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M3WLDAWYXA6CVUQWXQUFQJUXKD","short_pith_number":"pith:M3WLDAWY","schema_version":"1.0","canonical_sha256":"66ecb182d8b83c2ad216bc2858269750eb8859ee24a0fab7c40992a881376d25","source":{"kind":"arxiv","id":"2501.07861","version":1},"attestation_state":"computed","paper":{"title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Li, Jun Xu, Kai Zheng, Qipeng Wang, Song Yang, Weijie Yu, Xiaoxue Zang, Xiao Zhang, Zhongxiang Sun","submitted_at":"2025-01-14T05:56:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.07861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T05:56:26Z","cross_cats_sorted":[],"title_canon_sha256":"767f6ae51e440ae2a72a010da32e165a839b0c5617cf86cfb6a1d044d8859276","abstract_canon_sha256":"28891819b004197d9bcd47e44e5ac1eebeab7c306953cd2279f529ab9beba960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:51.524286Z","signature_b64":"dkopqOSgWSMAYZgeYyWogS3FZ4MtSK5HrmK9nao5PB2JZZ1CsMJuWlM8eZtNkCxJSd49IRrlCODfZyH5P12FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ecb182d8b83c2ad216bc2858269750eb8859ee24a0fab7c40992a881376d25","last_reissued_at":"2026-07-05T10:00:51.523819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:51.523819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Li, Jun Xu, Kai Zheng, Qipeng Wang, Song Yang, Weijie Yu, Xiaoxue Zang, Xiao Zhang, Zhongxiang Sun","submitted_at":"2025-01-14T05:56:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07861","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/2501.07861/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.07861","created_at":"2026-07-05T10:00:51.523876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07861v1","created_at":"2026-07-05T10:00:51.523876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07861","created_at":"2026-07-05T10:00:51.523876+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3WLDAWYXA6C","created_at":"2026-07-05T10:00:51.523876+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3WLDAWYXA6CVUQW","created_at":"2026-07-05T10:00:51.523876+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3WLDAWY","created_at":"2026-07-05T10:00:51.523876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":175,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD","json":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD.json","graph_json":"https://pith.science/api/pith-number/M3WLDAWYXA6CVUQWXQUFQJUXKD/graph.json","events_json":"https://pith.science/api/pith-number/M3WLDAWYXA6CVUQWXQUFQJUXKD/events.json","paper":"https://pith.science/paper/M3WLDAWY"},"agent_actions":{"view_html":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD","download_json":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD.json","view_paper":"https://pith.science/paper/M3WLDAWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07861&json=true","fetch_graph":"https://pith.science/api/pith-number/M3WLDAWYXA6CVUQWXQUFQJUXKD/graph.json","fetch_events":"https://pith.science/api/pith-number/M3WLDAWYXA6CVUQWXQUFQJUXKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD/action/storage_attestation","attest_author":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD/action/author_attestation","sign_citation":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD/action/citation_signature","submit_replication":"https://pith.science/pith/M3WLDAWYXA6CVUQWXQUFQJUXKD/action/replication_record"}},"created_at":"2026-07-05T10:00:51.523876+00:00","updated_at":"2026-07-05T10:00:51.523876+00:00"}