{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IK2E4IUYZFRU7LQF2Z6YTAY5HB","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":"a53f921cc329ac2f2be841fb905d25ce8c27eb79bfc2e82ac4837222be2f50a9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-31T16:47:31Z","title_canon_sha256":"fb6eb9e7fccb14f5af21b8c9da84492e1eb5450e864f72aaa4978d1c60bbfe4c"},"schema_version":"1.0","source":{"id":"2509.06980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06980","created_at":"2026-07-05T12:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06980v1","created_at":"2026-07-05T12:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06980","created_at":"2026-07-05T12:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"IK2E4IUYZFRU","created_at":"2026-07-05T12:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"IK2E4IUYZFRU7LQF","created_at":"2026-07-05T12:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"IK2E4IUY","created_at":"2026-07-05T12:07:13Z"}],"graph_snapshots":[{"event_id":"sha256:38f751f723c7f4cd9988f00f90c35adad96d233009a22ac096813aba4f7533a7","target":"graph","created_at":"2026-07-05T12:07:13Z","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/2509.06980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models excel at basic reasoning but struggle with tasks that require interaction with external tools. We present RLFactory, a plug-and-play reinforcement learning post-training framework for multi-round tool use. RLFactory tackles (i) tool-call stability and adaptability amid tool heterogeneity and interface issues via an asyncio-based asynchronous caller and a decoupled tool/training architecture, and (ii) diverse evaluation needs via a reward layer supporting rule-based, model-judgment, and tool-verification signals. It reconstructs the MDP by introducing observation markers f","authors_text":"Chengqi Dong, Chuhuai Yue, Guojun Yin, Hang He, Jiajun Chai, Jiwen Jiang, Siyu Xia, Wei Lin, Xiaoguang Li, Xiaohan Wang, Yi Jia, Zekun Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-31T16:47:31Z","title":"RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06980","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":"sha256:51b6d2e4e936e47f71e3b5cee242b7f1df374f836f4e2654c871005e2bdeb626","target":"record","created_at":"2026-07-05T12:07:13Z","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":"a53f921cc329ac2f2be841fb905d25ce8c27eb79bfc2e82ac4837222be2f50a9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-31T16:47:31Z","title_canon_sha256":"fb6eb9e7fccb14f5af21b8c9da84492e1eb5450e864f72aaa4978d1c60bbfe4c"},"schema_version":"1.0","source":{"id":"2509.06980","kind":"arxiv","version":1}},"canonical_sha256":"42b44e2298c9634fae05d67d89831d38484b2af37706825e93ffef3896928511","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42b44e2298c9634fae05d67d89831d38484b2af37706825e93ffef3896928511","first_computed_at":"2026-07-05T12:07:13.400928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:13.400928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qWIv611HrPKqEW7WnArKychAE5B/mFAJ7teFRiDsshxOW7uvih05qVjuwSIc3/jKlojxh32DF0D/ZMD9Yc54AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:13.401456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51b6d2e4e936e47f71e3b5cee242b7f1df374f836f4e2654c871005e2bdeb626","sha256:38f751f723c7f4cd9988f00f90c35adad96d233009a22ac096813aba4f7533a7"],"state_sha256":"9b30a6dcb944a6ca22b2d20b1f8f4a76be60e582c36d9cb0f50cd2ce5b081b7c"}