{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QMMK7OFV7YO55SL6QAVEMG2NNV","short_pith_number":"pith:QMMK7OFV","canonical_record":{"source":{"id":"2607.28449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T16:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"05f7126edf7bfac00599b669ebba943fcc02d82a7b25dba6cf6ab4555f2af893","abstract_canon_sha256":"0fe6c8a6210aa0609ca949604496f24f4a767f8f1288254c962acb41f17bbf17"},"schema_version":"1.0"},"canonical_sha256":"8318afb8b5fe1ddec97e802a461b4d6d4d9e688416f4bdf33e86e0a062d0ca1e","source":{"kind":"arxiv","id":"2607.28449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28449","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28449v1","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28449","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"QMMK7OFV7YO5","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"QMMK7OFV7YO55SL6","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"QMMK7OFV","created_at":"2026-07-31T01:37:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QMMK7OFV7YO55SL6QAVEMG2NNV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T16:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"05f7126edf7bfac00599b669ebba943fcc02d82a7b25dba6cf6ab4555f2af893","abstract_canon_sha256":"0fe6c8a6210aa0609ca949604496f24f4a767f8f1288254c962acb41f17bbf17"},"schema_version":"1.0"},"canonical_sha256":"8318afb8b5fe1ddec97e802a461b4d6d4d9e688416f4bdf33e86e0a062d0ca1e","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8318afb8b5fe1ddec97e802a461b4d6d4d9e688416f4bdf33e86e0a062d0ca1e","last_reissued_at":"2026-07-31T01:37:39.896847Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:39.896847Z"},"source_kind":"arxiv","source_id":"2607.28449","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":"2026-07-31T01:37:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUuP+1qzkNvMLqmktNXW1sFLr3cWey5igeuoc0ZwLQY71wkuH9MQ5t3EvdKaqduFj6mv3NLy5RrrmzCw87qyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:19:59.573476Z"},"content_sha256":"4a61896b24a857b2fcc958b9c8df1cfa56964ef614c5d7ce076b55b691631d00","schema_version":"1.0","event_id":"sha256:4a61896b24a857b2fcc958b9c8df1cfa56964ef614c5d7ce076b55b691631d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QMMK7OFV7YO55SL6QAVEMG2NNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Cai, Song Han, Yecheng Wu","submitted_at":"2026-07-30T16:17:15Z","abstract_excerpt":"On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD supervision should also have generated the demonstrations used to train the supervised fine-tuning (SFT) reference. However, this condition is frequently violated in practice when SFT data have mixed or unknown provenance or when different models are preferred for SFT data generation and subsequent distillation. In such cross-teacher settings, even a stronger OPD teacher can yield little improvement over the SFT refere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28449","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/2607.28449/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":"2026-07-31T01:37:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2m5jpoGj7rOpqc7Eqg/Ni2OjNpHXNaH6+1a59BhWNPqmXlx19znag0FVXIYIAKJjE8eCK64/ICW7hiTiPwBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:19:59.573986Z"},"content_sha256":"e597bbacad709ace842c528207a45dcec8ab63f8d81d415303f701c216f4314e","schema_version":"1.0","event_id":"sha256:e597bbacad709ace842c528207a45dcec8ab63f8d81d415303f701c216f4314e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMMK7OFV7YO55SL6QAVEMG2NNV/bundle.json","state_url":"https://pith.science/pith/QMMK7OFV7YO55SL6QAVEMG2NNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMMK7OFV7YO55SL6QAVEMG2NNV/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":"2026-08-01T01:19:59Z","links":{"resolver":"https://pith.science/pith/QMMK7OFV7YO55SL6QAVEMG2NNV","bundle":"https://pith.science/pith/QMMK7OFV7YO55SL6QAVEMG2NNV/bundle.json","state":"https://pith.science/pith/QMMK7OFV7YO55SL6QAVEMG2NNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMMK7OFV7YO55SL6QAVEMG2NNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QMMK7OFV7YO55SL6QAVEMG2NNV","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":"0fe6c8a6210aa0609ca949604496f24f4a767f8f1288254c962acb41f17bbf17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T16:17:15Z","title_canon_sha256":"05f7126edf7bfac00599b669ebba943fcc02d82a7b25dba6cf6ab4555f2af893"},"schema_version":"1.0","source":{"id":"2607.28449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28449","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28449v1","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28449","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"QMMK7OFV7YO5","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"QMMK7OFV7YO55SL6","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"QMMK7OFV","created_at":"2026-07-31T01:37:39Z"}],"graph_snapshots":[{"event_id":"sha256:e597bbacad709ace842c528207a45dcec8ab63f8d81d415303f701c216f4314e","target":"graph","created_at":"2026-07-31T01:37:39Z","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/2607.28449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD supervision should also have generated the demonstrations used to train the supervised fine-tuning (SFT) reference. However, this condition is frequently violated in practice when SFT data have mixed or unknown provenance or when different models are preferred for SFT data generation and subsequent distillation. In such cross-teacher settings, even a stronger OPD teacher can yield little improvement over the SFT refere","authors_text":"Han Cai, Song Han, Yecheng Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T16:17:15Z","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28449","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":"sha256:4a61896b24a857b2fcc958b9c8df1cfa56964ef614c5d7ce076b55b691631d00","target":"record","created_at":"2026-07-31T01:37:39Z","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":"0fe6c8a6210aa0609ca949604496f24f4a767f8f1288254c962acb41f17bbf17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T16:17:15Z","title_canon_sha256":"05f7126edf7bfac00599b669ebba943fcc02d82a7b25dba6cf6ab4555f2af893"},"schema_version":"1.0","source":{"id":"2607.28449","kind":"arxiv","version":1}},"canonical_sha256":"8318afb8b5fe1ddec97e802a461b4d6d4d9e688416f4bdf33e86e0a062d0ca1e","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8318afb8b5fe1ddec97e802a461b4d6d4d9e688416f4bdf33e86e0a062d0ca1e","first_computed_at":"2026-07-31T01:37:39.896847Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:39.896847Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a61896b24a857b2fcc958b9c8df1cfa56964ef614c5d7ce076b55b691631d00","sha256:e597bbacad709ace842c528207a45dcec8ab63f8d81d415303f701c216f4314e"],"state_sha256":"826e9789a4cb9e06b6e56ebc6efb70c639453aa38a15150d74c958f91267e04d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iUJTvjnJEiiGsDBv105Ht87TYeUpIgR8oQR4WuVDlctfdkcDoPkLj59OQW92JiyWcDEWKAnrnwPTO8K7i0dnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T01:19:59.578840Z","bundle_sha256":"934961bee5a41ab49de04cd7b06f11c1783c146f55b05a74da124415cb8f7861"}}