{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7HG5I3ZN5UBBZEUGEC6F3WJ7DF","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":"3f2de4cd88610c732db5556ff3b675f96feb066149d70b28b115ad57e565e1fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T15:14:24Z","title_canon_sha256":"2b4b1df7070041c5f7f3535dca478d946c8f1d386e6ab08bf1ac4ecdd2abbc4f"},"schema_version":"1.0","source":{"id":"2605.17497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17497","created_at":"2026-05-20T00:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17497v1","created_at":"2026-05-20T00:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17497","created_at":"2026-05-20T00:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"7HG5I3ZN5UBB","created_at":"2026-05-20T00:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"7HG5I3ZN5UBBZEUG","created_at":"2026-05-20T00:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"7HG5I3ZN","created_at":"2026-05-20T00:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:c403faab5fe2c55a47a08daedaa378f8e0813843ac7d307a6e577f823e60b1a3","target":"graph","created_at":"2026-05-20T00:04:42Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.673272Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.638878Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17497/integrity.json","findings":[],"snapshot_sha256":"bbab3aa14c8eba6e9c48f6abbe4e2a86c28a901c45f5634ee7d1593713cf38a8","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We show that a mixed group contains a richer process signal: a correct completion is a self-generated witness of how the current policy can solve the problem, while a wrong completion provides on-policy prefixes where the policy needs correction. We introduce \\emph{Self-Supervised On-Policy Distillation} (SSOPD), which distills a teacher distribution conditioned on the shortest correct completion into prefixes of the longest wrong completion. Thi","authors_text":"Yinrong Hong, Zhiquan Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T15:14:24Z","title":"Self-Supervised On-Policy Distillation for Reasoning Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17497","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":"sha256:3b391553c1a2e88df1993a1297423cdabdfe281b89c119be8286fb4187835487","target":"record","created_at":"2026-05-20T00:04:42Z","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":"3f2de4cd88610c732db5556ff3b675f96feb066149d70b28b115ad57e565e1fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T15:14:24Z","title_canon_sha256":"2b4b1df7070041c5f7f3535dca478d946c8f1d386e6ab08bf1ac4ecdd2abbc4f"},"schema_version":"1.0","source":{"id":"2605.17497","kind":"arxiv","version":1}},"canonical_sha256":"f9cdd46f2ded021c928620bc5dd93f1960db15b8557032eb8cb6bad172965fbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9cdd46f2ded021c928620bc5dd93f1960db15b8557032eb8cb6bad172965fbd","first_computed_at":"2026-05-20T00:04:42.251132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:42.251132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wZRbcwuiyLCxPNab7E95+imojssHN8/tDZegGPEMgtyMz1Y6UqKIS7J3gGjsIpUWjeOexjbSXxOdoi0wFD2NBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:42.251976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b391553c1a2e88df1993a1297423cdabdfe281b89c119be8286fb4187835487","sha256:c403faab5fe2c55a47a08daedaa378f8e0813843ac7d307a6e577f823e60b1a3"],"state_sha256":"b70ae3d39790be58055bffd1e809d58101fad95f07f49c2559c18f381e2f9760"}