{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ETOL6PWBPMYF25QP4IK7BDGLH5","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":"264f7b115a358f53f7507348959998a77310c4b6ff588c7eddd4ae008ff2882d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:29:22Z","title_canon_sha256":"bd3bec7636cf126b563a6226e2ec4fd55c345ac07d8e65f4e6c49c6a9c4a8eeb"},"schema_version":"1.0","source":{"id":"2506.04185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04185","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04185v1","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04185","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"ETOL6PWBPMYF","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"ETOL6PWBPMYF25QP","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"ETOL6PWB","created_at":"2026-07-05T11:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:c6ad3db3138cbf0d580484bb93d59144e1fe3a127d5e94e51501f0f1e8f8586f","target":"graph","created_at":"2026-07-05T11:15:58Z","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/2506.04185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to identify optimal reasoning-search interaction trajectories, resulting in suboptimal responses. We propose R-Search, a novel reinforcement learning framework for Reasoning-Search integration, designed to enable LLMs to autonomously execute multi-step reasoning with deep search interaction, and learn optimal reasoning search interaction trajectories via multi","authors_text":"Daren Zha, Dingling Xu, Limin Liu, Qingfei Zhao, Ruobing Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:29:22Z","title":"R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04185","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:b904d7fad4c600faa926fbc0f292cdc7c003877cc73e2209e5e251b8407a1926","target":"record","created_at":"2026-07-05T11:15:58Z","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":"264f7b115a358f53f7507348959998a77310c4b6ff588c7eddd4ae008ff2882d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:29:22Z","title_canon_sha256":"bd3bec7636cf126b563a6226e2ec4fd55c345ac07d8e65f4e6c49c6a9c4a8eeb"},"schema_version":"1.0","source":{"id":"2506.04185","kind":"arxiv","version":1}},"canonical_sha256":"24dcbf3ec17b305d760fe215f08ccb3f571ff59eb7ec63e3cfcb3f94dbfe9374","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24dcbf3ec17b305d760fe215f08ccb3f571ff59eb7ec63e3cfcb3f94dbfe9374","first_computed_at":"2026-07-05T11:15:58.564096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:58.564096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5M4NjzN+LCcGUE6jdOEkt8WalFqG7Ei+u+2aMKlneWJJmM3Fi0BlaX3fhIFTFHpswYTh7h4MsR6cV6w0sZDgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:58.564640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b904d7fad4c600faa926fbc0f292cdc7c003877cc73e2209e5e251b8407a1926","sha256:c6ad3db3138cbf0d580484bb93d59144e1fe3a127d5e94e51501f0f1e8f8586f"],"state_sha256":"f2f12977f2baefbb3010906c847317351291e5919cdd7abb8a5fb88a803f98a7"}