{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UOXHR7CDY5CDUNSNZV6OL7IOHP","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":"dd2eb8c61f4e798e8bbdbdd68d0b62868d5e91ae1207b918d99931447f3da060","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T06:26:13Z","title_canon_sha256":"b63d5e1d3f87835ed76d7dfc9a19967050a7911466a8ee622863b1d187e744fc"},"schema_version":"1.0","source":{"id":"2607.07050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07050","created_at":"2026-07-09T01:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07050v1","created_at":"2026-07-09T01:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07050","created_at":"2026-07-09T01:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"UOXHR7CDY5CD","created_at":"2026-07-09T01:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"UOXHR7CDY5CDUNSN","created_at":"2026-07-09T01:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"UOXHR7CD","created_at":"2026-07-09T01:20:13Z"}],"graph_snapshots":[{"event_id":"sha256:087a01dc22c01a7c21819b154b91871b36665fadf6794207ad956379de17aae7","target":"graph","created_at":"2026-07-09T01:20:13Z","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/2607.07050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on\n  its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teacher tool-use setting, vanilla generalized knowledge distillation improves tool-call recall but also moves the model toward over-calling, where it ca","authors_text":"Chengjun Mao, Guang Chen, Jiabin Shen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T06:26:13Z","title":"Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07050","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:fb800f46365399312a6b3818d2ec2ed35c7994e44f2efe06407401039d61dd0e","target":"record","created_at":"2026-07-09T01:20:13Z","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":"dd2eb8c61f4e798e8bbdbdd68d0b62868d5e91ae1207b918d99931447f3da060","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T06:26:13Z","title_canon_sha256":"b63d5e1d3f87835ed76d7dfc9a19967050a7911466a8ee622863b1d187e744fc"},"schema_version":"1.0","source":{"id":"2607.07050","kind":"arxiv","version":1}},"canonical_sha256":"a3ae78fc43c7443a364dcd7ce5fd0e3bef90646adf40fd07c18bfcc2ef3cf01e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3ae78fc43c7443a364dcd7ce5fd0e3bef90646adf40fd07c18bfcc2ef3cf01e","first_computed_at":"2026-07-09T01:20:13.287621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:13.287621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Njz7mh+1rFU81ZDyVhFv8X6CCAwPp9Sy5+Tuae+mdkSGt1vn5rLH+9LW2L9ftZtPWt5nygKBbwbGnCz9JrMuDw==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:13.287974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb800f46365399312a6b3818d2ec2ed35c7994e44f2efe06407401039d61dd0e","sha256:087a01dc22c01a7c21819b154b91871b36665fadf6794207ad956379de17aae7"],"state_sha256":"d7831827e18cb1871f0b9f9f5535fa9ef7fd63dae0ac3727eda7d7784ade4333"}