{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AKZMNMFYBI6L6LXPZZFOGVXLS5","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":"8404f8fe96a6d16fd9389ea7f27628a80a84c7337d0bcb61947e6f72262d841e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T11:30:18Z","title_canon_sha256":"184121070caa72a462732f9f13ca946dcfa60d60e8820c7b7b569f34907e8ef4"},"schema_version":"1.0","source":{"id":"2505.24480","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24480","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24480v1","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24480","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"AKZMNMFYBI6L","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"AKZMNMFYBI6L6LXP","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"AKZMNMFY","created_at":"2026-07-05T11:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:f6046bdddae1e2ea532ca7d799055b68299943798299daf8d78ae8d04ddcea7f","target":"graph","created_at":"2026-07-05T11:12:50Z","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/2505.24480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external code tools effectively, which is supported by tool-augmented reinforcement learning (RL) through interactive learning. Despite its benefits, tool-augmented RL can still suffer from potential instability in the learning dynamics. In light of this challenge, we present a systematic approach to improving the training effectiveness and stability of tool-augment","authors_text":"Beichen Zhang, Fei Bai, Ji-Rong Wen, Lei Fang, Wayne Xin Zhao, Yingqian Min, Zheng Liu, Zhipeng Chen, Zhongyuan Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T11:30:18Z","title":"Towards Effective Code-Integrated Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24480","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:b2ac57215105d41d35fff25d111e46c2dc0779da991e2b71921ae19076c95053","target":"record","created_at":"2026-07-05T11:12:50Z","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":"8404f8fe96a6d16fd9389ea7f27628a80a84c7337d0bcb61947e6f72262d841e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T11:30:18Z","title_canon_sha256":"184121070caa72a462732f9f13ca946dcfa60d60e8820c7b7b569f34907e8ef4"},"schema_version":"1.0","source":{"id":"2505.24480","kind":"arxiv","version":1}},"canonical_sha256":"02b2c6b0b80a3cbf2eefce4ae356eb975e9ff609d40075f06adf3e5c682b4aba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02b2c6b0b80a3cbf2eefce4ae356eb975e9ff609d40075f06adf3e5c682b4aba","first_computed_at":"2026-07-05T11:12:50.764128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:50.764128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JtWTuwLYzQ27IkGXhcAlSusiLceI+USlumwdP8aAfarJiaQ/GmXX4tH5YY4xKfxPGho6rFTxk5Vy7/RgIl2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:50.764654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24480","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2ac57215105d41d35fff25d111e46c2dc0779da991e2b71921ae19076c95053","sha256:f6046bdddae1e2ea532ca7d799055b68299943798299daf8d78ae8d04ddcea7f"],"state_sha256":"0b6b5f2684a74a486d5fc5227504f2b32cf9ef9d08e72ae4f7b134a0e4b89cc2"}