{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W4XKIS4GRYQ5BEYZ324UBCLOOU","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":"1c1fd0b98ae7fd62987b513642f7ea0b39f4692d31d52748c30e310cfa20c989","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:04:05Z","title_canon_sha256":"38b7762885e350d5ffacb0bdf77bd609086a1806b68f6f4fb94641cd132135b6"},"schema_version":"1.0","source":{"id":"2505.17447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17447","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17447v1","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17447","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"W4XKIS4GRYQ5","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"W4XKIS4GRYQ5BEYZ","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"W4XKIS4G","created_at":"2026-07-05T11:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:5168996f28c4ec5d02ae1438a7f475f3c83883e4928decb22e20af8c243d62fb","target":"graph","created_at":"2026-07-05T11:08:26Z","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/2505.17447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Bo Zheng, Haobo Wang, Hao Chen, Jiexiang Wang, Jinglei Chen, Junbo Zhao, Lirong Gao, Qi Zhang, Sheng Guo, Shouqing Yang, Xiaomeng Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:04:05Z","title":"LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17447","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":"sha256:666ff01fc0803b233ec7f1160aa275dd4c5a3a964f152f1cb7617b50578f7173","target":"record","created_at":"2026-07-05T11:08:26Z","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":"1c1fd0b98ae7fd62987b513642f7ea0b39f4692d31d52748c30e310cfa20c989","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:04:05Z","title_canon_sha256":"38b7762885e350d5ffacb0bdf77bd609086a1806b68f6f4fb94641cd132135b6"},"schema_version":"1.0","source":{"id":"2505.17447","kind":"arxiv","version":1}},"canonical_sha256":"b72ea44b868e21d09319deb940896e7506ea06bc8eb466b4580723fbccae10b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b72ea44b868e21d09319deb940896e7506ea06bc8eb466b4580723fbccae10b3","first_computed_at":"2026-07-05T11:08:26.372677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:26.372677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8yfebLNcMw7JvgieBnMIMxkEtZe0fGrUr/4UxWIPKr/LERMCEmCrIjOUeadDjaRzwOxcLPd1GV50GaD+TgoZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:26.373087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:666ff01fc0803b233ec7f1160aa275dd4c5a3a964f152f1cb7617b50578f7173","sha256:5168996f28c4ec5d02ae1438a7f475f3c83883e4928decb22e20af8c243d62fb"],"state_sha256":"c42e4e861ea1dcc492f2ce21bfa22e1f473e5f4c205b31daebe51335a019043e"}