{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QIY24QT3QV5EH4R6J6PSCH23UP","short_pith_number":"pith:QIY24QT3","schema_version":"1.0","canonical_sha256":"8231ae427b857a43f23e4f9f211f5ba3efb5561fa1465cfbf060f910afc4587d","source":{"kind":"arxiv","id":"2606.12634","version":1},"attestation_state":"computed","paper":{"title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianhong Xin, Juan Pablo De la Cruz Weinstein, Tianyu Ding","submitted_at":"2026-06-10T19:53:20Z","abstract_excerpt":"Long-horizon tool-use reinforcement learning can learn from outcome verification, but its\n  trajectory-level advantage is broadcast across many reasoning, API, and answer tokens.\n  Self-distillation promises a denser signal by reusing a policy's own rollouts or a privileged\n  teacher. We show, however, that direct token-level self-distillation can silently destroy tool use:\n  it rehearses teacher behavior without knowing which actions the verifier rewards, so useful skills\n  and harmful shortcuts are amplified together. We introduce Sibling-Guided Credit Distillation\n  (SGCD), which uses disti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.12634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:53:20Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a8e35800a2aae0b51eacdebd1248f489e3621e245e81dde571aba0cbde253318","abstract_canon_sha256":"e81fee06a71b0c0a441a538e5771eacac5a9ef7e75ad0f2bff1d4c736d68ae9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:41.779367Z","signature_b64":"6J+8aTYmZks2yistUoojwyKOqD5yuCULrH1pxC2YdudsafbHi0vimgh7DLCIkE3XZ0ej8hjcEuQGM+eR8B1lDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8231ae427b857a43f23e4f9f211f5ba3efb5561fa1465cfbf060f910afc4587d","last_reissued_at":"2026-06-12T01:08:41.778270Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:41.778270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianhong Xin, Juan Pablo De la Cruz Weinstein, Tianyu Ding","submitted_at":"2026-06-10T19:53:20Z","abstract_excerpt":"Long-horizon tool-use reinforcement learning can learn from outcome verification, but its\n  trajectory-level advantage is broadcast across many reasoning, API, and answer tokens.\n  Self-distillation promises a denser signal by reusing a policy's own rollouts or a privileged\n  teacher. We show, however, that direct token-level self-distillation can silently destroy tool use:\n  it rehearses teacher behavior without knowing which actions the verifier rewards, so useful skills\n  and harmful shortcuts are amplified together. We introduce Sibling-Guided Credit Distillation\n  (SGCD), which uses disti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12634","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.12634/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.12634","created_at":"2026-06-12T01:08:41.778430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12634v1","created_at":"2026-06-12T01:08:41.778430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12634","created_at":"2026-06-12T01:08:41.778430+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIY24QT3QV5E","created_at":"2026-06-12T01:08:41.778430+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIY24QT3QV5EH4R6","created_at":"2026-06-12T01:08:41.778430+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIY24QT3","created_at":"2026-06-12T01:08:41.778430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP","json":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP.json","graph_json":"https://pith.science/api/pith-number/QIY24QT3QV5EH4R6J6PSCH23UP/graph.json","events_json":"https://pith.science/api/pith-number/QIY24QT3QV5EH4R6J6PSCH23UP/events.json","paper":"https://pith.science/paper/QIY24QT3"},"agent_actions":{"view_html":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP","download_json":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP.json","view_paper":"https://pith.science/paper/QIY24QT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12634&json=true","fetch_graph":"https://pith.science/api/pith-number/QIY24QT3QV5EH4R6J6PSCH23UP/graph.json","fetch_events":"https://pith.science/api/pith-number/QIY24QT3QV5EH4R6J6PSCH23UP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP/action/storage_attestation","attest_author":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP/action/author_attestation","sign_citation":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP/action/citation_signature","submit_replication":"https://pith.science/pith/QIY24QT3QV5EH4R6J6PSCH23UP/action/replication_record"}},"created_at":"2026-06-12T01:08:41.778430+00:00","updated_at":"2026-06-12T01:08:41.778430+00:00"}