{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZVDHXWBK6V5ZTWDHVF5BQWTO3O","short_pith_number":"pith:ZVDHXWBK","canonical_record":{"source":{"id":"2608.05802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T09:37:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1acf91eaeefa6eeae72446db8f67a2768446c15feab5ca51eda0588b6ac38218","abstract_canon_sha256":"cedef610dbb3a86f3ea9f68f5dd8aa0ca7dab2615e6c107f24ad2fa5acaf1b4d"},"schema_version":"1.0"},"canonical_sha256":"cd467bd82af57b99d867a97a185a6edb887387e0c09efc3d60da8c29872409b0","source":{"kind":"arxiv","id":"2608.05802","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05802","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05802v1","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05802","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZVDHXWBK6V5Z","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"ZVDHXWBK6V5ZTWDH","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"ZVDHXWBK","created_at":"2026-08-07T00:52:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZVDHXWBK6V5ZTWDHVF5BQWTO3O","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T09:37:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1acf91eaeefa6eeae72446db8f67a2768446c15feab5ca51eda0588b6ac38218","abstract_canon_sha256":"cedef610dbb3a86f3ea9f68f5dd8aa0ca7dab2615e6c107f24ad2fa5acaf1b4d"},"schema_version":"1.0"},"canonical_sha256":"cd467bd82af57b99d867a97a185a6edb887387e0c09efc3d60da8c29872409b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:46.863217Z","signature_b64":"SbxFPTf8vOJGUrphlM+ZYVwJRODi7fq7XtSVZlOQTm2CjhFfUjq68guZPo7AcnX36KHxBu6F2cEN3PykejuRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd467bd82af57b99d867a97a185a6edb887387e0c09efc3d60da8c29872409b0","last_reissued_at":"2026-08-07T00:52:46.861800Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:46.861800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05802","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":"2026-08-07T00:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9e11tJ4kQc4iNzySGx89ciYgvdTfHhgplDJd9ANKyEB9yrLfDdUzV0nKW4RhSge58V26jyMUScVJWcR+q8CACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:08:46.178451Z"},"content_sha256":"2186a6c1a27ca875d1318effbf8feef361feee8b69996fa08dbef318bc277fb1","schema_version":"1.0","event_id":"sha256:2186a6c1a27ca875d1318effbf8feef361feee8b69996fa08dbef318bc277fb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZVDHXWBK6V5ZTWDHVF5BQWTO3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On-Policy Delta Distillation for Multilingual Math Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Byeongho Heo, Dongyoon Han, Jaehui Hwang, Sangdoo Yun","submitted_at":"2026-08-06T09:37:49Z","abstract_excerpt":"On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored. We study OPD and its advanced variant, On-Policy Delta Distillation (OPD$^2$), for mathematical reasoning in English, Korean, and Japanese. OPD$^2$ improves OPD by using the probability gap between a post-trained teacher and its base model as the learning signal. Experiments with Qwen3 show that OPD$^2$ consistently outperforms the original OPD, with particularly strong improvements in Korean and Japanese, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05802","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/2608.05802/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":"2026-08-07T00:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Niu2IBSpb92pE9zHfJt8KMOdc2e0xB2351rYV+3eiTRRqp02Ra9XYSHYha6bxoCXCAF7OJi/nZapPdOCZQUbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:08:46.179524Z"},"content_sha256":"45ee5e8cad9c0413ef560760556e1b265456fa8a398880f287768bf05dd08580","schema_version":"1.0","event_id":"sha256:45ee5e8cad9c0413ef560760556e1b265456fa8a398880f287768bf05dd08580"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O/bundle.json","state_url":"https://pith.science/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O/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":"2026-08-09T13:08:46Z","links":{"resolver":"https://pith.science/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O","bundle":"https://pith.science/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O/bundle.json","state":"https://pith.science/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVDHXWBK6V5ZTWDHVF5BQWTO3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZVDHXWBK6V5ZTWDHVF5BQWTO3O","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":"cedef610dbb3a86f3ea9f68f5dd8aa0ca7dab2615e6c107f24ad2fa5acaf1b4d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T09:37:49Z","title_canon_sha256":"1acf91eaeefa6eeae72446db8f67a2768446c15feab5ca51eda0588b6ac38218"},"schema_version":"1.0","source":{"id":"2608.05802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05802","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05802v1","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05802","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZVDHXWBK6V5Z","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"ZVDHXWBK6V5ZTWDH","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"ZVDHXWBK","created_at":"2026-08-07T00:52:46Z"}],"graph_snapshots":[{"event_id":"sha256:45ee5e8cad9c0413ef560760556e1b265456fa8a398880f287768bf05dd08580","target":"graph","created_at":"2026-08-07T00:52:46Z","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/2608.05802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored. We study OPD and its advanced variant, On-Policy Delta Distillation (OPD$^2$), for mathematical reasoning in English, Korean, and Japanese. OPD$^2$ improves OPD by using the probability gap between a post-trained teacher and its base model as the learning signal. Experiments with Qwen3 show that OPD$^2$ consistently outperforms the original OPD, with particularly strong improvements in Korean and Japanese, and","authors_text":"Byeongho Heo, Dongyoon Han, Jaehui Hwang, Sangdoo Yun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T09:37:49Z","title":"On-Policy Delta Distillation for Multilingual Math Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05802","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":"sha256:2186a6c1a27ca875d1318effbf8feef361feee8b69996fa08dbef318bc277fb1","target":"record","created_at":"2026-08-07T00:52:46Z","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":"cedef610dbb3a86f3ea9f68f5dd8aa0ca7dab2615e6c107f24ad2fa5acaf1b4d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T09:37:49Z","title_canon_sha256":"1acf91eaeefa6eeae72446db8f67a2768446c15feab5ca51eda0588b6ac38218"},"schema_version":"1.0","source":{"id":"2608.05802","kind":"arxiv","version":1}},"canonical_sha256":"cd467bd82af57b99d867a97a185a6edb887387e0c09efc3d60da8c29872409b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd467bd82af57b99d867a97a185a6edb887387e0c09efc3d60da8c29872409b0","first_computed_at":"2026-08-07T00:52:46.861800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:52:46.861800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SbxFPTf8vOJGUrphlM+ZYVwJRODi7fq7XtSVZlOQTm2CjhFfUjq68guZPo7AcnX36KHxBu6F2cEN3PykejuRCA==","signature_status":"signed_v1","signed_at":"2026-08-07T00:52:46.863217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2186a6c1a27ca875d1318effbf8feef361feee8b69996fa08dbef318bc277fb1","sha256:45ee5e8cad9c0413ef560760556e1b265456fa8a398880f287768bf05dd08580"],"state_sha256":"193d4adc7ec6d01acb959ead5bbb94427722f135971f572645130b9f2f8d0652"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eqn5/szxYSpCrFCW1YQjcfi/AfsR4zSy7HWYPdgiLqgBnUvl28oI2Y1rG7ozgJbwV6x+i9FivsG1zgNmgscVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:08:46.186704Z","bundle_sha256":"d21e736ed3d85f048ca9177ab8c8ca1a2c1fbef1d4d92bd1ba9ffc08d677dccd"}}