{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AXSUKHBAPYKBYGUUUUHPSQVID5","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":"9a7d60e0fb60e975e70bad85814ba0d500d9a61993d69a939bac5bb3b2d3fc40","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T06:31:59Z","title_canon_sha256":"697a6e83abd1b09b1ccf04a610f4cda7d2ca9ec810661defe4a360cb9bf60e6e"},"schema_version":"1.0","source":{"id":"2606.11709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11709","created_at":"2026-06-11T01:10:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11709v1","created_at":"2026-06-11T01:10:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11709","created_at":"2026-06-11T01:10:04Z"},{"alias_kind":"pith_short_12","alias_value":"AXSUKHBAPYKB","created_at":"2026-06-11T01:10:04Z"},{"alias_kind":"pith_short_16","alias_value":"AXSUKHBAPYKBYGUU","created_at":"2026-06-11T01:10:04Z"},{"alias_kind":"pith_short_8","alias_value":"AXSUKHBA","created_at":"2026-06-11T01:10:04Z"}],"graph_snapshots":[{"event_id":"sha256:62ec9428f66d18aad9dec6d3ef20414ba79c8ea234c884fb57f7e1c658789a2e","target":"graph","created_at":"2026-06-11T01:10:04Z","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/2606.11709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs. We term this pathology \\emph{privilege-induced style drift}, which destabilizes training or causes response length to shrink. To address this, we propose \\textbf{RLCSD} (","authors_text":"Aiwei Liu, Bolin Ding, Leyi Pan, Lijie Wen, Lingzhe Zhang, Shuchang Tao, Yunpeng Zhai, Zhaoyang Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T06:31:59Z","title":"RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11709","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":"sha256:64f6c640321caa22cb20baa22e34cd4e193a95a08ac969ff7a3be5ff2b594243","target":"record","created_at":"2026-06-11T01:10:04Z","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":"9a7d60e0fb60e975e70bad85814ba0d500d9a61993d69a939bac5bb3b2d3fc40","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T06:31:59Z","title_canon_sha256":"697a6e83abd1b09b1ccf04a610f4cda7d2ca9ec810661defe4a360cb9bf60e6e"},"schema_version":"1.0","source":{"id":"2606.11709","kind":"arxiv","version":1}},"canonical_sha256":"05e5451c207e141c1a94a50ef942a81f6e538b7d015e09e3827a428d36320a10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05e5451c207e141c1a94a50ef942a81f6e538b7d015e09e3827a428d36320a10","first_computed_at":"2026-06-11T01:10:04.171674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:04.171674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GSG0u81BhXIXAVb+O3BicY40Von0PVQN3Czrk8ty6sGjfre1YFr+BHp0b9etrtqoPcZZps9G/cdQnyCU1xAjDQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:04.172533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64f6c640321caa22cb20baa22e34cd4e193a95a08ac969ff7a3be5ff2b594243","sha256:62ec9428f66d18aad9dec6d3ef20414ba79c8ea234c884fb57f7e1c658789a2e"],"state_sha256":"3313cd3e3f6bd6ba8e960082e2645e75ca4fd3f607c224471f3d5e719e69a3aa"}