{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:THL3IADC74CYF5ZSQXY3ORERSQ","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":"5aa2795da28901d5ee29638f3ed9defe894e926628f86c2c6822539b59ae26b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T20:31:48Z","title_canon_sha256":"25e009a3814537c00d8a9c380633a0a3c99ce7e76b335314ec3d8178daca8452"},"schema_version":"1.0","source":{"id":"2607.26246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26246","created_at":"2026-07-30T01:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26246v1","created_at":"2026-07-30T01:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26246","created_at":"2026-07-30T01:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"THL3IADC74CY","created_at":"2026-07-30T01:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"THL3IADC74CYF5ZS","created_at":"2026-07-30T01:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"THL3IADC","created_at":"2026-07-30T01:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:d6b8cb7c4b47ada965458f1eb3a51f0ae76dff3193381d8d12e23564c2491419","target":"graph","created_at":"2026-07-30T01:17:48Z","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/2607.26246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs. Prevailing approaches assume a teacher at least as capable as the student: they either distill a larger model into a smaller one, which fails at the frontier where no larger teacher exists, or consolidate multiple domain experts trained from a shared base, which requires costly training at the student's scale. We introduce Weak-to-Strong On-Policy Distillation (W2S-OPD), a simple yet effective OPD fra","authors_text":"Fangxu Yu, Jianfeng Gao, Michael Xu, Tianyi Zhou, Weijia Xu, XiaoDong Liu, Zinan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T20:31:48Z","title":"Weak-to-Strong On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26246","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":"sha256:177a459bd2ddd79303aa6f0191f8615043d44b74d14a61844c1652773b35e721","target":"record","created_at":"2026-07-30T01:17:48Z","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":"5aa2795da28901d5ee29638f3ed9defe894e926628f86c2c6822539b59ae26b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T20:31:48Z","title_canon_sha256":"25e009a3814537c00d8a9c380633a0a3c99ce7e76b335314ec3d8178daca8452"},"schema_version":"1.0","source":{"id":"2607.26246","kind":"arxiv","version":1}},"canonical_sha256":"99d7b40062ff0582f73285f1b74491942eeda9fc48254501c438aebf9f3bb307","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99d7b40062ff0582f73285f1b74491942eeda9fc48254501c438aebf9f3bb307","first_computed_at":"2026-07-30T01:17:48.961817Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:17:48.961817Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:177a459bd2ddd79303aa6f0191f8615043d44b74d14a61844c1652773b35e721","sha256:d6b8cb7c4b47ada965458f1eb3a51f0ae76dff3193381d8d12e23564c2491419"],"state_sha256":"3a713e8e2bab13ff4e1cb1a330df4d5f8e537947aff28c124f248f524e511290"}