{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W4XKIS4GRYQ5BEYZ324UBCLOOU","short_pith_number":"pith:W4XKIS4G","schema_version":"1.0","canonical_sha256":"b72ea44b868e21d09319deb940896e7506ea06bc8eb466b4580723fbccae10b3","source":{"kind":"arxiv","id":"2505.17447","version":1},"attestation_state":"computed","paper":{"title":"LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Haobo Wang, Hao Chen, Jiexiang Wang, Jinglei Chen, Junbo Zhao, Lirong Gao, Qi Zhang, Sheng Guo, Shouqing Yang, Xiaomeng Hu","submitted_at":"2025-05-23T04:04:05Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches, while the correctness of intermediate think-and-search steps is usually neglected. To address this issue, we design a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation."},"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":"2505.17447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:04:05Z","cross_cats_sorted":[],"title_canon_sha256":"38b7762885e350d5ffacb0bdf77bd609086a1806b68f6f4fb94641cd132135b6","abstract_canon_sha256":"1c1fd0b98ae7fd62987b513642f7ea0b39f4692d31d52748c30e310cfa20c989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:26.373087Z","signature_b64":"8yfebLNcMw7JvgieBnMIMxkEtZe0fGrUr/4UxWIPKr/LERMCEmCrIjOUeadDjaRzwOxcLPd1GV50GaD+TgoZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72ea44b868e21d09319deb940896e7506ea06bc8eb466b4580723fbccae10b3","last_reissued_at":"2026-07-05T11:08:26.372677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:26.372677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Haobo Wang, Hao Chen, Jiexiang Wang, Jinglei Chen, Junbo Zhao, Lirong Gao, Qi Zhang, Sheng Guo, Shouqing Yang, Xiaomeng Hu","submitted_at":"2025-05-23T04:04:05Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches, while the correctness of intermediate think-and-search steps is usually neglected. To address this issue, we design a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17447","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/2505.17447/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":"2505.17447","created_at":"2026-07-05T11:08:26.372733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17447v1","created_at":"2026-07-05T11:08:26.372733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17447","created_at":"2026-07-05T11:08:26.372733+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4XKIS4GRYQ5","created_at":"2026-07-05T11:08:26.372733+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4XKIS4GRYQ5BEYZ","created_at":"2026-07-05T11:08:26.372733+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4XKIS4G","created_at":"2026-07-05T11:08:26.372733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU","json":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU.json","graph_json":"https://pith.science/api/pith-number/W4XKIS4GRYQ5BEYZ324UBCLOOU/graph.json","events_json":"https://pith.science/api/pith-number/W4XKIS4GRYQ5BEYZ324UBCLOOU/events.json","paper":"https://pith.science/paper/W4XKIS4G"},"agent_actions":{"view_html":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU","download_json":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU.json","view_paper":"https://pith.science/paper/W4XKIS4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17447&json=true","fetch_graph":"https://pith.science/api/pith-number/W4XKIS4GRYQ5BEYZ324UBCLOOU/graph.json","fetch_events":"https://pith.science/api/pith-number/W4XKIS4GRYQ5BEYZ324UBCLOOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU/action/storage_attestation","attest_author":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU/action/author_attestation","sign_citation":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU/action/citation_signature","submit_replication":"https://pith.science/pith/W4XKIS4GRYQ5BEYZ324UBCLOOU/action/replication_record"}},"created_at":"2026-07-05T11:08:26.372733+00:00","updated_at":"2026-07-05T11:08:26.372733+00:00"}