{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KFDYI7UA7ZVAX5F4G64AVTK6GS","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":"d4f42f67a434e4c832b74bad58836c3080335f945c3ddf14e015bdfb8310ac09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:42:52Z","title_canon_sha256":"c9c32a45ee559d0424672e281902b8a676831d1994df7cc9962083d1bbbb313a"},"schema_version":"1.0","source":{"id":"2605.19433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19433","created_at":"2026-05-20T01:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19433v1","created_at":"2026-05-20T01:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19433","created_at":"2026-05-20T01:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"KFDYI7UA7ZVA","created_at":"2026-05-20T01:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"KFDYI7UA7ZVAX5F4","created_at":"2026-05-20T01:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"KFDYI7UA","created_at":"2026-05-20T01:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:b65a2920c8060bc909a7dcd4528e7d0798e4e1061e2c99e1abdbfe2f092dd302","target":"graph","created_at":"2026-05-20T01:05:45Z","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/2605.19433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computational overhead hinders real-world deployment. LLM reasoning distillation addresses this by transferring reasoning capabilities from formidable teacher models to compact student models. However, existing distillation paradigms face a fundamental dilemma. Typical off-policy distillation strictly utilizes teacher-generated golden trajectories, suffering from an exposure bias due to the mismatch between training distributions and student-generated infe","authors_text":"Bing Wang, Chen Shen, Jieping Ye, Kaiyuan Liu, Rui Miao, Shaotian Yan, Sinan Fan, Xiaosong Yuan, Ximing Li, Zhanming Shen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:42:52Z","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19433","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:e8585e72e5a7cfa632c6a80e52bd1e99f65a519b3405aabb649e141ba2edaa99","target":"record","created_at":"2026-05-20T01:05:45Z","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":"d4f42f67a434e4c832b74bad58836c3080335f945c3ddf14e015bdfb8310ac09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T06:42:52Z","title_canon_sha256":"c9c32a45ee559d0424672e281902b8a676831d1994df7cc9962083d1bbbb313a"},"schema_version":"1.0","source":{"id":"2605.19433","kind":"arxiv","version":1}},"canonical_sha256":"5147847e80fe6a0bf4bc37b80acd5e349122412773e3fb40b1acd28c4a66b52a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5147847e80fe6a0bf4bc37b80acd5e349122412773e3fb40b1acd28c4a66b52a","first_computed_at":"2026-05-20T01:05:45.630143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:45.630143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"murOO/b+Efmm07qY1E4rJGDR1gEt4MM24iHm5Bt4Kmq7RCliQkzm3Y+IUAOsWUd1xPQzazOM8EBG+wR975RCDg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:45.631101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8585e72e5a7cfa632c6a80e52bd1e99f65a519b3405aabb649e141ba2edaa99","sha256:b65a2920c8060bc909a7dcd4528e7d0798e4e1061e2c99e1abdbfe2f092dd302"],"state_sha256":"5776d2ffc3a5b15ba0ffb2d34b7054860c7a27c9360e18c55351126fee91f38d"}