{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76D4Y36TSRHSVXGK45AWLZT6RH","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":"7094a3651824286953d6a8e786ac0de8c290a087ccbc8014449c068abacaac62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T16:30:19Z","title_canon_sha256":"ae078dee364b1fe5910c2b671736a1ee7474488a6f60a470b4b97ef47ebb2eb5"},"schema_version":"1.0","source":{"id":"2509.02479","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02479","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02479v2","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02479","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"76D4Y36TSRHS","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"76D4Y36TSRHSVXGK","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"76D4Y36T","created_at":"2026-07-05T12:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:35279abd9abbe719ccc5589d35029eb52dbe6d8c5a74068c850f7f303285e87b","target":"graph","created_at":"2026-07-05T12:04:19Z","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/2509.02479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn scenarios using Reinforcement Learning (RL) is often hindered by training instability and performance collapse. We identify that such instability is primarily caused by a distributional drift from external tool feedback, leading to the generation of low-probability tokens. This issue compounds over successive turns, causing catastrophic gradient norm explosions that derail the training p","authors_text":"Bo An, Longtao Zheng, Qian Liu, Xiaosen Zheng, Yingru Li, Zejun Ma, Zhenghai Xue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T16:30:19Z","title":"SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02479","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:a0c56e4fb62812fe2cc5bcfb6d823145fb7b355e9b71b740da395bed078cb737","target":"record","created_at":"2026-07-05T12:04:19Z","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":"7094a3651824286953d6a8e786ac0de8c290a087ccbc8014449c068abacaac62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T16:30:19Z","title_canon_sha256":"ae078dee364b1fe5910c2b671736a1ee7474488a6f60a470b4b97ef47ebb2eb5"},"schema_version":"1.0","source":{"id":"2509.02479","kind":"arxiv","version":2}},"canonical_sha256":"ff87cc6fd3944f2adccae74165e67e89c8d0d17fadcdbdb40fa4b93da5b0b0b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff87cc6fd3944f2adccae74165e67e89c8d0d17fadcdbdb40fa4b93da5b0b0b1","first_computed_at":"2026-07-05T12:04:19.345232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:19.345232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toxK2Pdne3duk5FrRj+n5xVYGtECN4bRIVISePgp7g9+u63Y+OBQKOBQgjQADe6hYDuST0Z6ryg91UhNZV9DCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:19.345759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02479","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0c56e4fb62812fe2cc5bcfb6d823145fb7b355e9b71b740da395bed078cb737","sha256:35279abd9abbe719ccc5589d35029eb52dbe6d8c5a74068c850f7f303285e87b"],"state_sha256":"2efd32ecdd872193547557f0b0cb416e7925dcc855dff02cd1cf9be70693d63f"}