{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QIY24QT3QV5EH4R6J6PSCH23UP","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":"e81fee06a71b0c0a441a538e5771eacac5a9ef7e75ad0f2bff1d4c736d68ae9a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:53:20Z","title_canon_sha256":"a8e35800a2aae0b51eacdebd1248f489e3621e245e81dde571aba0cbde253318"},"schema_version":"1.0","source":{"id":"2606.12634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12634","created_at":"2026-06-12T01:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12634v1","created_at":"2026-06-12T01:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12634","created_at":"2026-06-12T01:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"QIY24QT3QV5E","created_at":"2026-06-12T01:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"QIY24QT3QV5EH4R6","created_at":"2026-06-12T01:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"QIY24QT3","created_at":"2026-06-12T01:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:f5dda86940d867f40ddad2f270571526184fec4d0dfe7d594ff48e30bdd61ed4","target":"graph","created_at":"2026-06-12T01:08:41Z","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/2606.12634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianhong Xin, Juan Pablo De la Cruz Weinstein, Tianyu Ding","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:53:20Z","title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12634","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":"sha256:7567b006125c718ef03edf3c321e96e752556590bd935f906157795bd7334bf7","target":"record","created_at":"2026-06-12T01:08:41Z","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":"e81fee06a71b0c0a441a538e5771eacac5a9ef7e75ad0f2bff1d4c736d68ae9a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:53:20Z","title_canon_sha256":"a8e35800a2aae0b51eacdebd1248f489e3621e245e81dde571aba0cbde253318"},"schema_version":"1.0","source":{"id":"2606.12634","kind":"arxiv","version":1}},"canonical_sha256":"8231ae427b857a43f23e4f9f211f5ba3efb5561fa1465cfbf060f910afc4587d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8231ae427b857a43f23e4f9f211f5ba3efb5561fa1465cfbf060f910afc4587d","first_computed_at":"2026-06-12T01:08:41.778270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:41.778270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6J+8aTYmZks2yistUoojwyKOqD5yuCULrH1pxC2YdudsafbHi0vimgh7DLCIkE3XZ0ej8hjcEuQGM+eR8B1lDg==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:41.779367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7567b006125c718ef03edf3c321e96e752556590bd935f906157795bd7334bf7","sha256:f5dda86940d867f40ddad2f270571526184fec4d0dfe7d594ff48e30bdd61ed4"],"state_sha256":"e5bb78b299f3c8e83af85261f4dff33ab64c1f150c59e4a8e33d028fefc89044"}