{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XKBBPEUZTOUWEEZKX5CIEXZJ7I","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":"c3d68c6c6e4ea0d94fdc097c0b307d8aa120260fb558e1c198477e485b245f7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T04:47:38Z","title_canon_sha256":"97918a5dd7ee1078f987bb0f4abd02934256ed43a7c8c7ceddc71b23f626bc35"},"schema_version":"1.0","source":{"id":"2608.06802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06802","created_at":"2026-08-10T01:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06802v1","created_at":"2026-08-10T01:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06802","created_at":"2026-08-10T01:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"XKBBPEUZTOUW","created_at":"2026-08-10T01:12:08Z"},{"alias_kind":"pith_short_16","alias_value":"XKBBPEUZTOUWEEZK","created_at":"2026-08-10T01:12:08Z"},{"alias_kind":"pith_short_8","alias_value":"XKBBPEUZ","created_at":"2026-08-10T01:12:08Z"}],"graph_snapshots":[{"event_id":"sha256:43c9518ab5241165b6e4e731bf77d7b0573ce903a76647ffcbba0704847f86a7","target":"graph","created_at":"2026-08-10T01:12:08Z","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/2608.06802/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 with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage before OPD. In this paper, we demystify warm-up for OPD from both data and training perspectives. For data, we find that effective warm-up relies on teacher-compatible chain-of-thought supervision, and that even incorrect teacher rollouts can provide comparable benefits to correct ones. This suggests that warm-up primarily transfers a teacher-compatible thinking pattern rather than merely correct answers. For training","authors_text":"Junjie Wang, Mao Zheng, Runming Yang, Taiqiang Wu, Tao Liu, Xuan Luo, Xuewei Yang, Yujiu Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T04:47:38Z","title":"Simple-OPD: Demystifying Warm-up for On-policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06802","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":"sha256:0b6e7b938ad694ef900ed8a04a4857cc8490e0d6d90831575e7e8e97e4ac212a","target":"record","created_at":"2026-08-10T01:12:08Z","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":"c3d68c6c6e4ea0d94fdc097c0b307d8aa120260fb558e1c198477e485b245f7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T04:47:38Z","title_canon_sha256":"97918a5dd7ee1078f987bb0f4abd02934256ed43a7c8c7ceddc71b23f626bc35"},"schema_version":"1.0","source":{"id":"2608.06802","kind":"arxiv","version":1}},"canonical_sha256":"ba821792999ba962132abf44825f29fa0aab8ad2d0d6056e32b535efa22be22f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba821792999ba962132abf44825f29fa0aab8ad2d0d6056e32b535efa22be22f","first_computed_at":"2026-08-10T01:12:08.084918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:12:08.084918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M+8HqrcJYYdwvfAuJx6mys8kz4e7VapGe8pTRVZK+8dR2riBJQqEftiYwBtl12QsQGk8EGFvf9lXHS97gJGjAA==","signature_status":"signed_v1","signed_at":"2026-08-10T01:12:08.088314Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b6e7b938ad694ef900ed8a04a4857cc8490e0d6d90831575e7e8e97e4ac212a","sha256:43c9518ab5241165b6e4e731bf77d7b0573ce903a76647ffcbba0704847f86a7"],"state_sha256":"21a3e4ec6997ab3d1e90749a7dee39ffbe4157cf7cb41b60b3ef0815db23f6b3"}