{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JI6SBHLA6UXLZQH6NPA7VGAZES","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":"07351398b2d24a6f5dfb134260ecf994d8998571417777320c767d738ca9c148","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:39:20Z","title_canon_sha256":"3a52b31f26808bfe9ac38b260aeb0ff40e67165a55e85bc0dd86e272468d1651"},"schema_version":"1.0","source":{"id":"2605.30833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30833","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30833v1","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30833","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"JI6SBHLA6UXL","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"JI6SBHLA6UXLZQH6","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"JI6SBHLA","created_at":"2026-06-01T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:b4768fe769218add346019b6b3cc1967bdf6c66b5929e7cf8e5917bdec945c06","target":"graph","created_at":"2026-06-01T01:03:19Z","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/2605.30833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identify a critical bottleneck, \\textbf{Supervision Fidelity Decay (SFD)}: as student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative. Consequently, the teacher-dependent corrective signal in reverse-KL distillation weakens, causing student drift to compound across long reasoning chains. To mitigate SFD, we introduce \\textbf{Lookahead Group Reward (\\ours{})}.","authors_text":"Ben He, Hongyu Lin, Jie Lou, Le Sun, Xianpei Han, Xing Yu, Xinyan Guan, Yanjiang Liu, Yaojie Lu, Yuqiu Ji","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:39:20Z","title":"Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30833","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":"sha256:8113d6a4a9db4b4755e14e4f660fb62b770b0bea6a77ce7a4d4b41610fc402ae","target":"record","created_at":"2026-06-01T01:03:19Z","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":"07351398b2d24a6f5dfb134260ecf994d8998571417777320c767d738ca9c148","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:39:20Z","title_canon_sha256":"3a52b31f26808bfe9ac38b260aeb0ff40e67165a55e85bc0dd86e272468d1651"},"schema_version":"1.0","source":{"id":"2605.30833","kind":"arxiv","version":1}},"canonical_sha256":"4a3d209d60f52ebcc0fe6bc1fa98192497463b3e756d837c0a64bbcfeea62c3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a3d209d60f52ebcc0fe6bc1fa98192497463b3e756d837c0a64bbcfeea62c3a","first_computed_at":"2026-06-01T01:03:19.916927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:19.916927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ribJdYsxo3y53kCY0LDAD6F9XtIc0jmOtmkGcAHFaEfIB5SHjgFrLdyL6fo5hGGZnA21KwsvKOmte8yD6ffDw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:19.917922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8113d6a4a9db4b4755e14e4f660fb62b770b0bea6a77ce7a4d4b41610fc402ae","sha256:b4768fe769218add346019b6b3cc1967bdf6c66b5929e7cf8e5917bdec945c06"],"state_sha256":"cc06973624fd38b437bf196630f64169f63d563457d69131f0276234bd1dd996"}