{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FHK2SA2WL3NSCBN3HO2QLTJWUB","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":"1106e155db072c9f1615361e92c37976eefc2ce8dc71326ea051d390cf320109","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T05:01:31Z","title_canon_sha256":"d977de914fec6043096b22434bdc2c9db0be522f32507455d9040f7719f0fa1e"},"schema_version":"1.0","source":{"id":"2505.15107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15107","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15107v2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15107","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"FHK2SA2WL3NS","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"FHK2SA2WL3NSCBN3","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"FHK2SA2W","created_at":"2026-07-05T11:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:f703a14b3f415bdd7ad47af3f6a64db95c744a285da20520775378399368a70b","target":"graph","created_at":"2026-07-05T11:09:14Z","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/2505.15107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document retrieval, achieving notable improvements in QA performance, but underperform on complex, multi-hop QA resulting from the sparse rewards from global signal only. To address this gap in existing research, we introduce StepSearch, a framework for search LLMs that trained with step-wise proximal policy optimization method. It consists of richer and more detailed i","authors_text":"Cijun Ouyang, Jialu Cai, Kang An, Xuhui Zheng, Yichao Wu, Yuhang Wang, Ziliang Wang","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T05:01:31Z","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15107","kind":"arxiv","version":2},"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":"sha256:25cfe2d0f69f12fc12e5e1e99b557773d56986d0adb8a6c32df68ac4a29af675","target":"record","created_at":"2026-07-05T11:09:14Z","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":"1106e155db072c9f1615361e92c37976eefc2ce8dc71326ea051d390cf320109","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T05:01:31Z","title_canon_sha256":"d977de914fec6043096b22434bdc2c9db0be522f32507455d9040f7719f0fa1e"},"schema_version":"1.0","source":{"id":"2505.15107","kind":"arxiv","version":2}},"canonical_sha256":"29d5a903565edb2105bb3bb505cd36a06ff5d2690d62f52bcb5b9f5cdcb17098","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29d5a903565edb2105bb3bb505cd36a06ff5d2690d62f52bcb5b9f5cdcb17098","first_computed_at":"2026-07-05T11:09:14.529272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:14.529272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2S3g7jjQbSIqb+kpDrj638srKXO6sRX3+DGlX3dJ1ApJMOy14TeSPE9/9jafiMQB/cbon+n/7LRQGdm68VCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:14.529783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25cfe2d0f69f12fc12e5e1e99b557773d56986d0adb8a6c32df68ac4a29af675","sha256:f703a14b3f415bdd7ad47af3f6a64db95c744a285da20520775378399368a70b"],"state_sha256":"91e9d0dd98c87619fb168a45672c59b96bc32695e478abad892ce64f5b5ef3bf"}