{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QNWW6I6KN6RCOD5MMS5NY63QP6","short_pith_number":"pith:QNWW6I6K","canonical_record":{"source":{"id":"2607.22334","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T14:12:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"31fd4ed81a239a58be34981278531bfc69475eabe0983163c23fe0584fdef40e","abstract_canon_sha256":"18aaeb73cbf44f396ba06ab3b3ea5c82e02fe5251ddf4c0bda4d28a9336cfbfb"},"schema_version":"1.0"},"canonical_sha256":"836d6f23ca6fa2270fac64badc7b707fb82da0be6b532ef33ad8fe6bba4debc3","source":{"kind":"arxiv","id":"2607.22334","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22334","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22334v1","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22334","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"QNWW6I6KN6RC","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"QNWW6I6KN6RCOD5M","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"QNWW6I6K","created_at":"2026-07-27T01:21:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QNWW6I6KN6RCOD5MMS5NY63QP6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22334","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T14:12:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"31fd4ed81a239a58be34981278531bfc69475eabe0983163c23fe0584fdef40e","abstract_canon_sha256":"18aaeb73cbf44f396ba06ab3b3ea5c82e02fe5251ddf4c0bda4d28a9336cfbfb"},"schema_version":"1.0"},"canonical_sha256":"836d6f23ca6fa2270fac64badc7b707fb82da0be6b532ef33ad8fe6bba4debc3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:21:03.408560Z","signature_b64":"fkH3mZ7z8CgIR/jgyzdjANV6ND6HUlvTELlI1CT1F+Qpu41eg5MQmYcpTv9wDTiPNz1HmocyeLBQd6B/ZaEgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"836d6f23ca6fa2270fac64badc7b707fb82da0be6b532ef33ad8fe6bba4debc3","last_reissued_at":"2026-07-27T01:21:03.407701Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:21:03.407701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22334","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":"2026-07-27T01:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nqtt3xvH3eJcLPYHgxjXcXtu4mn0U0y4Gqb4KGPKTv2T9uuNNZqtOEc3WLe4Cjc8ZXZwaaaDu+XJXY3CthPbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:02:05.592366Z"},"content_sha256":"bc13c5b489266d32f3dce8c25c8518f1155cc0952aeb5d97b97c4d20259d89e1","schema_version":"1.0","event_id":"sha256:bc13c5b489266d32f3dce8c25c8518f1155cc0952aeb5d97b97c4d20259d89e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QNWW6I6KN6RCOD5MMS5NY63QP6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Han Xiao, Hao Wang, Honggang Qi, Kun Yuan, Minglei Zhang, Ming Sun, Wenlin Zhong","submitted_at":"2026-07-24T14:12:54Z","abstract_excerpt":"Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD). However, full-vocabulary OPD typically assumes a shared tokenizer, while existing cross-tokenizer methods may discard teacher probability mass or assign it to student tokens with unrelated content. We introduce Byte-Prefix Marginalization (BPM), which re-expresses the teacher's next-token distribution over the student vocabulary in a shared byte space. Specifically, BPM assigns each teacher token's probability to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22334","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/2607.22334/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":"2026-07-27T01:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/FWxCaIKT/kYFSuyZ5VZpDqvaxNZAi/rJd8eLO+6nRnAt7EPKQkzGYxmc7O0HVQJCPPHWKTw8zcTvPsseq0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:02:05.593362Z"},"content_sha256":"7536fdd0bcc78852e905f93df0ddb6c58d1cb691c824459e97716e342e226aa2","schema_version":"1.0","event_id":"sha256:7536fdd0bcc78852e905f93df0ddb6c58d1cb691c824459e97716e342e226aa2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNWW6I6KN6RCOD5MMS5NY63QP6/bundle.json","state_url":"https://pith.science/pith/QNWW6I6KN6RCOD5MMS5NY63QP6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNWW6I6KN6RCOD5MMS5NY63QP6/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":"2026-08-07T04:02:05Z","links":{"resolver":"https://pith.science/pith/QNWW6I6KN6RCOD5MMS5NY63QP6","bundle":"https://pith.science/pith/QNWW6I6KN6RCOD5MMS5NY63QP6/bundle.json","state":"https://pith.science/pith/QNWW6I6KN6RCOD5MMS5NY63QP6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNWW6I6KN6RCOD5MMS5NY63QP6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QNWW6I6KN6RCOD5MMS5NY63QP6","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":"18aaeb73cbf44f396ba06ab3b3ea5c82e02fe5251ddf4c0bda4d28a9336cfbfb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T14:12:54Z","title_canon_sha256":"31fd4ed81a239a58be34981278531bfc69475eabe0983163c23fe0584fdef40e"},"schema_version":"1.0","source":{"id":"2607.22334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22334","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22334v1","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22334","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"QNWW6I6KN6RC","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"QNWW6I6KN6RCOD5M","created_at":"2026-07-27T01:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"QNWW6I6K","created_at":"2026-07-27T01:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:7536fdd0bcc78852e905f93df0ddb6c58d1cb691c824459e97716e342e226aa2","target":"graph","created_at":"2026-07-27T01:21:03Z","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/2607.22334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD). However, full-vocabulary OPD typically assumes a shared tokenizer, while existing cross-tokenizer methods may discard teacher probability mass or assign it to student tokens with unrelated content. We introduce Byte-Prefix Marginalization (BPM), which re-expresses the teacher's next-token distribution over the student vocabulary in a shared byte space. Specifically, BPM assigns each teacher token's probability to the","authors_text":"Han Xiao, Hao Wang, Honggang Qi, Kun Yuan, Minglei Zhang, Ming Sun, Wenlin Zhong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T14:12:54Z","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22334","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:bc13c5b489266d32f3dce8c25c8518f1155cc0952aeb5d97b97c4d20259d89e1","target":"record","created_at":"2026-07-27T01:21:03Z","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":"18aaeb73cbf44f396ba06ab3b3ea5c82e02fe5251ddf4c0bda4d28a9336cfbfb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T14:12:54Z","title_canon_sha256":"31fd4ed81a239a58be34981278531bfc69475eabe0983163c23fe0584fdef40e"},"schema_version":"1.0","source":{"id":"2607.22334","kind":"arxiv","version":1}},"canonical_sha256":"836d6f23ca6fa2270fac64badc7b707fb82da0be6b532ef33ad8fe6bba4debc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"836d6f23ca6fa2270fac64badc7b707fb82da0be6b532ef33ad8fe6bba4debc3","first_computed_at":"2026-07-27T01:21:03.407701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:21:03.407701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fkH3mZ7z8CgIR/jgyzdjANV6ND6HUlvTELlI1CT1F+Qpu41eg5MQmYcpTv9wDTiPNz1HmocyeLBQd6B/ZaEgDw==","signature_status":"signed_v1","signed_at":"2026-07-27T01:21:03.408560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc13c5b489266d32f3dce8c25c8518f1155cc0952aeb5d97b97c4d20259d89e1","sha256:7536fdd0bcc78852e905f93df0ddb6c58d1cb691c824459e97716e342e226aa2"],"state_sha256":"120778bc98bcadca00059e11bcbeb6a0bf79918381b0e0f43f63bc7e4fb39d48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qkr/uGjwzQgUYgDBRE8Z5DDRz8W/JdHnA5R+EKZOLcV77EKi/jp1wKWkkRF/UFiRnwFB+UlpudrOhv3WHhlWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:02:05.601863Z","bundle_sha256":"1167ef699fb3942dbcf8ce931a12216085242bef6e73270f90d8288e77aedad1"}}