{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RJNX5HCIXEUNXMZS6OYE5HQY6P","short_pith_number":"pith:RJNX5HCI","canonical_record":{"source":{"id":"2606.24143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"5b8defd260538f044924cd712cbb0e15ed296c399fad07fa4a4d9ff66bd528d3","abstract_canon_sha256":"df85aa1d7a6d7c463a41a0e33742f94de8ac53d3008eef711681426aeff4bcb9"},"schema_version":"1.0"},"canonical_sha256":"8a5b7e9c48b928dbb332f3b04e9e18f3c95b6d4e983aa796bec021ce94cdda44","source":{"kind":"arxiv","id":"2606.24143","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24143","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24143v1","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24143","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"RJNX5HCIXEUN","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"RJNX5HCIXEUNXMZS","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"RJNX5HCI","created_at":"2026-06-24T01:14:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RJNX5HCIXEUNXMZS6OYE5HQY6P","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"5b8defd260538f044924cd712cbb0e15ed296c399fad07fa4a4d9ff66bd528d3","abstract_canon_sha256":"df85aa1d7a6d7c463a41a0e33742f94de8ac53d3008eef711681426aeff4bcb9"},"schema_version":"1.0"},"canonical_sha256":"8a5b7e9c48b928dbb332f3b04e9e18f3c95b6d4e983aa796bec021ce94cdda44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:42.334505Z","signature_b64":"lKCPC5L/0WM97HCeTkBP2LccmXIQjamYUtjP76k+bAckRFGGX5ErpgrkxTX/0nWBHPzs79C+G+ephhTVv1jWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a5b7e9c48b928dbb332f3b04e9e18f3c95b6d4e983aa796bec021ce94cdda44","last_reissued_at":"2026-06-24T01:14:42.333618Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:42.333618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24143","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":"2026-06-24T01:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XheuCXHg3KmaFF5IHMPBYRNG0xEd02LBljf1pdtqbAvZQPgQwTy46dzMyOVA5q4A8u9KD9PbFicMNAJIjw9PAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T07:26:46.344603Z"},"content_sha256":"b4470ba7c72977a49ec4f98df217c51d5fb5b2970cd43c2f028b95cd8890108e","schema_version":"1.0","event_id":"sha256:b4470ba7c72977a49ec4f98df217c51d5fb5b2970cd43c2f028b95cd8890108e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RJNX5HCIXEUNXMZS6OYE5HQY6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AsyncOPD: How Stale Can On-Policy Distillation Be?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donghoon Kim, Hyung Il Koo, Kangwook Lee, Kevin Galim, Minjae Lee, Minjun Kang, Minseo Kim, Rishabh Tiwari, Sanghyun Park, Seunghyuk Oh, Wonjun Kang, Yuchen Zeng","submitted_at":"2026-06-23T04:50:49Z","abstract_excerpt":"On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24143","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/2606.24143/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":"2026-06-24T01:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KH6L7qA7t0Z4ATyrOzCSWIjswkljIGshbwqN7Y07wsAeHaLZdIfzesgsgPJpCV+/IQKKyrKGYptpnzgmSpghCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T07:26:46.344971Z"},"content_sha256":"bc77a614cf4f00ddd0a699591aa3478017e4d106e39693b61090452756f363fd","schema_version":"1.0","event_id":"sha256:bc77a614cf4f00ddd0a699591aa3478017e4d106e39693b61090452756f363fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P/bundle.json","state_url":"https://pith.science/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P/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":"2026-06-28T07:26:46Z","links":{"resolver":"https://pith.science/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P","bundle":"https://pith.science/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P/bundle.json","state":"https://pith.science/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJNX5HCIXEUNXMZS6OYE5HQY6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RJNX5HCIXEUNXMZS6OYE5HQY6P","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":"df85aa1d7a6d7c463a41a0e33742f94de8ac53d3008eef711681426aeff4bcb9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:50:49Z","title_canon_sha256":"5b8defd260538f044924cd712cbb0e15ed296c399fad07fa4a4d9ff66bd528d3"},"schema_version":"1.0","source":{"id":"2606.24143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24143","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24143v1","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24143","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"RJNX5HCIXEUN","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"RJNX5HCIXEUNXMZS","created_at":"2026-06-24T01:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"RJNX5HCI","created_at":"2026-06-24T01:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:bc77a614cf4f00ddd0a699591aa3478017e4d106e39693b61090452756f363fd","target":"graph","created_at":"2026-06-24T01:14:42Z","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/2606.24143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present ","authors_text":"Donghoon Kim, Hyung Il Koo, Kangwook Lee, Kevin Galim, Minjae Lee, Minjun Kang, Minseo Kim, Rishabh Tiwari, Sanghyun Park, Seunghyuk Oh, Wonjun Kang, Yuchen Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:50:49Z","title":"AsyncOPD: How Stale Can On-Policy Distillation Be?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24143","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:b4470ba7c72977a49ec4f98df217c51d5fb5b2970cd43c2f028b95cd8890108e","target":"record","created_at":"2026-06-24T01:14:42Z","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":"df85aa1d7a6d7c463a41a0e33742f94de8ac53d3008eef711681426aeff4bcb9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:50:49Z","title_canon_sha256":"5b8defd260538f044924cd712cbb0e15ed296c399fad07fa4a4d9ff66bd528d3"},"schema_version":"1.0","source":{"id":"2606.24143","kind":"arxiv","version":1}},"canonical_sha256":"8a5b7e9c48b928dbb332f3b04e9e18f3c95b6d4e983aa796bec021ce94cdda44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a5b7e9c48b928dbb332f3b04e9e18f3c95b6d4e983aa796bec021ce94cdda44","first_computed_at":"2026-06-24T01:14:42.333618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:42.333618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lKCPC5L/0WM97HCeTkBP2LccmXIQjamYUtjP76k+bAckRFGGX5ErpgrkxTX/0nWBHPzs79C+G+ephhTVv1jWBg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:42.334505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4470ba7c72977a49ec4f98df217c51d5fb5b2970cd43c2f028b95cd8890108e","sha256:bc77a614cf4f00ddd0a699591aa3478017e4d106e39693b61090452756f363fd"],"state_sha256":"b1001849163b35310adee9d3d5452d512f27f4c99a4dc8d58e4b112d0826460f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0W73YeW2/KBA/x4KFYEeiofKVXL6S4ImqxD4R1ntiFdvJkWqlNaz0e5vvN2Esvser5wHKgd9OlerUxIAqbqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T07:26:46.346958Z","bundle_sha256":"de2d363a4e1bcac062c1f2d41fff2fe0b6a2d6870f83314d336db92ca570b6f1"}}