{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2N3GJTI6LAQ4MQICLWOGUOEE5J","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":"18f7ffcf58720d3499b852a2ae3a5bea4751c042e0094252898047a5c9945462","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T08:03:14Z","title_canon_sha256":"eff2a52967e69fbdd5718bd88c715f51afdd918b4616b73e57e01d056750717b"},"schema_version":"1.0","source":{"id":"2510.18383","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.18383","created_at":"2026-06-19T16:12:15Z"},{"alias_kind":"arxiv_version","alias_value":"2510.18383v3","created_at":"2026-06-19T16:12:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18383","created_at":"2026-06-19T16:12:15Z"},{"alias_kind":"pith_short_12","alias_value":"2N3GJTI6LAQ4","created_at":"2026-06-19T16:12:15Z"},{"alias_kind":"pith_short_16","alias_value":"2N3GJTI6LAQ4MQIC","created_at":"2026-06-19T16:12:15Z"},{"alias_kind":"pith_short_8","alias_value":"2N3GJTI6","created_at":"2026-06-19T16:12:15Z"}],"graph_snapshots":[{"event_id":"sha256:6affb473ddef7879cee0784c7df5460e847871ac1b4e7b9e643abc5a427e5669","target":"graph","created_at":"2026-06-19T16:12:15Z","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/2510.18383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), suffers from poor out-of-domain (OOD) generalization due to its rigid alignment with static teacher trajectories. While reinforcement learning (RL) offers an alternative, the capacity limitations of SLMs pose a severe dilemma: sparse outcome rewards provide insufficient guidance, whereas strict trajectory matching imposes overly restrictive constraints. To bridge this capacity-driven gap, we ","authors_text":"Changsu Choi, Dongyeon Kim, Hoyun Song, KyungTae Lim, MinKyung Cho, NohHyeob Bae, Seona Yu, Sunjin Park, WooHyeon Jung","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T08:03:14Z","title":"MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18383","kind":"arxiv","version":3},"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:d3eb0ff1697a450afc64a340c025f985df4bf9ee5be78a597c9859d3b576a37d","target":"record","created_at":"2026-06-19T16:12:15Z","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":"18f7ffcf58720d3499b852a2ae3a5bea4751c042e0094252898047a5c9945462","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T08:03:14Z","title_canon_sha256":"eff2a52967e69fbdd5718bd88c715f51afdd918b4616b73e57e01d056750717b"},"schema_version":"1.0","source":{"id":"2510.18383","kind":"arxiv","version":3}},"canonical_sha256":"d37664cd1e5821c641025d9c6a3884ea42ee0e5134d3ab8da5742898319726ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d37664cd1e5821c641025d9c6a3884ea42ee0e5134d3ab8da5742898319726ad","first_computed_at":"2026-06-19T16:12:15.766756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:15.766756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOmZlxxOSA6WrWMQJQ+xhMYbD90W0HgHr8TYajDY4sfrnU7CFilsb0cFVcVRSxORPcECuzBBCZh8kNWTr0nHBw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:15.767203Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.18383","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3eb0ff1697a450afc64a340c025f985df4bf9ee5be78a597c9859d3b576a37d","sha256:6affb473ddef7879cee0784c7df5460e847871ac1b4e7b9e643abc5a427e5669"],"state_sha256":"38a34f01ed1395672edccc60623681d5235b12ed2ab17b080efacb9145467062"}