{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZEE7CCL5KRH3UMTVUB5YYDMKUF","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":"57e66cdfe3c4b1a0d870324b125612c48fc1023189e96a6f6ce24de77d7e919b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:51:28Z","title_canon_sha256":"a4c8e6ba6f75f4625b309e5303123f2bb8487dd612204dea1ae468bb6b1f9682"},"schema_version":"1.0","source":{"id":"2606.30406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30406","created_at":"2026-06-30T02:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30406v1","created_at":"2026-06-30T02:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30406","created_at":"2026-06-30T02:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZEE7CCL5KRH3","created_at":"2026-06-30T02:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZEE7CCL5KRH3UMTV","created_at":"2026-06-30T02:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZEE7CCL5","created_at":"2026-06-30T02:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:22bf85fdbcaea2c0f4ab019f9f29e34cfd55415c806bae662787c24d94ac873c","target":"graph","created_at":"2026-06-30T02:18:14Z","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/2606.30406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains hard. Existing methods, such as Off-Policy Finetune and Mix-RL, are either inefficient or lose performance. In this work, we propose Multi-teacher On-Policy Distillation (MOPD), a post-training paradigm for combining the capabilities of multiple domain RL teachers: we first run per-domain specialised RL to obtain a set of domain teachers, then distill these teachers into the student on its own rollouts. This eliminat","authors_text":"Bangjun Xiao, Bofei Gao, Fuli Luo, Hailin Zhang, Jianyu Wei, Jinhao Dong, Lei Li, Liang Zhao, Qibin Yang, Rang Li, Wenhan Ma, Yudong Wang, Zhifang Sui","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:51:28Z","title":"MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30406","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":"sha256:6413b2e8f33f9d94347ac80324feb75ac309d6fa5edb3e561f2666e671d58df3","target":"record","created_at":"2026-06-30T02:18:14Z","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":"57e66cdfe3c4b1a0d870324b125612c48fc1023189e96a6f6ce24de77d7e919b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:51:28Z","title_canon_sha256":"a4c8e6ba6f75f4625b309e5303123f2bb8487dd612204dea1ae468bb6b1f9682"},"schema_version":"1.0","source":{"id":"2606.30406","kind":"arxiv","version":1}},"canonical_sha256":"c909f1097d544fba3275a07b8c0d8aa14b168f10e7a92c6ff44dfa6a3a80b49a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c909f1097d544fba3275a07b8c0d8aa14b168f10e7a92c6ff44dfa6a3a80b49a","first_computed_at":"2026-06-30T02:18:14.065835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:14.065835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/cIaB0TQ7WDVL0uULYFyjyXtdPGiqjwBRJfgPI93b0VB+Po3BfxNU41QxbE2YeV/e4RD77O83x2A4eIHvC6KCA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:14.066347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6413b2e8f33f9d94347ac80324feb75ac309d6fa5edb3e561f2666e671d58df3","sha256:22bf85fdbcaea2c0f4ab019f9f29e34cfd55415c806bae662787c24d94ac873c"],"state_sha256":"76320a7eb42ecbebfe3f5582f842b8851a81a7c5bbb58a157093b83c552f06df"}