{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZEE7CCL5KRH3UMTVUB5YYDMKUF","short_pith_number":"pith:ZEE7CCL5","canonical_record":{"source":{"id":"2606.30406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:51:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4c8e6ba6f75f4625b309e5303123f2bb8487dd612204dea1ae468bb6b1f9682","abstract_canon_sha256":"57e66cdfe3c4b1a0d870324b125612c48fc1023189e96a6f6ce24de77d7e919b"},"schema_version":"1.0"},"canonical_sha256":"c909f1097d544fba3275a07b8c0d8aa14b168f10e7a92c6ff44dfa6a3a80b49a","source":{"kind":"arxiv","id":"2606.30406","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZEE7CCL5KRH3UMTVUB5YYDMKUF","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:51:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4c8e6ba6f75f4625b309e5303123f2bb8487dd612204dea1ae468bb6b1f9682","abstract_canon_sha256":"57e66cdfe3c4b1a0d870324b125612c48fc1023189e96a6f6ce24de77d7e919b"},"schema_version":"1.0"},"canonical_sha256":"c909f1097d544fba3275a07b8c0d8aa14b168f10e7a92c6ff44dfa6a3a80b49a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:14.066347Z","signature_b64":"/cIaB0TQ7WDVL0uULYFyjyXtdPGiqjwBRJfgPI93b0VB+Po3BfxNU41QxbE2YeV/e4RD77O83x2A4eIHvC6KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c909f1097d544fba3275a07b8c0d8aa14b168f10e7a92c6ff44dfa6a3a80b49a","last_reissued_at":"2026-06-30T02:18:14.065835Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:14.065835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30406","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BCdFlMiliNWXOFzmtaZ/BtwhJa+xn7X4QKL5UyMkE+pPwURsTbmGN3jCyy7j+KTJesUCH/D4QHVetyAyH/aXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:32:42.223818Z"},"content_sha256":"6413b2e8f33f9d94347ac80324feb75ac309d6fa5edb3e561f2666e671d58df3","schema_version":"1.0","event_id":"sha256:6413b2e8f33f9d94347ac80324feb75ac309d6fa5edb3e561f2666e671d58df3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZEE7CCL5KRH3UMTVUB5YYDMKUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","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","submitted_at":"2026-06-29T14:51:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30406","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/2606.30406/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RLNPkwnwG+v0I34/9z40KsMyvJwViDJLNV5YSD79AjkU9B8/7rJmlbXyrQWjI64YyaVG8W5ywXuVeTGlbEvDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:32:42.224343Z"},"content_sha256":"22bf85fdbcaea2c0f4ab019f9f29e34cfd55415c806bae662787c24d94ac873c","schema_version":"1.0","event_id":"sha256:22bf85fdbcaea2c0f4ab019f9f29e34cfd55415c806bae662787c24d94ac873c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF/bundle.json","state_url":"https://pith.science/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T02:32:42Z","links":{"resolver":"https://pith.science/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF","bundle":"https://pith.science/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF/bundle.json","state":"https://pith.science/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEE7CCL5KRH3UMTVUB5YYDMKUF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlf9DbkjWEzAdO6qHpAUthU6eFI7xPa7ItKmptzZ5ZnaTubSYyqTkjN9IP8xVrn3gogCT+X7VsWjuCBWsULDDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:32:42.229711Z","bundle_sha256":"01d26d50104d5195e3fc644ee3e4bccf6f2ec76a9791b1c1717ee64823e57471"}}