{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OKLSLVT4VHR5HMYKJK3QZXTYV6","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":"b0edf78ea82d42fbcec53138fedfb09279d97a90937ee087e14b0548d242ff3c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T15:53:55Z","title_canon_sha256":"d2b46bfd5c723c037c838aa073af8a12b7faa7f6844d7fd09b33eb8e5a75d6f8"},"schema_version":"1.0","source":{"id":"2602.02244","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02244","created_at":"2026-07-15T01:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02244v3","created_at":"2026-07-15T01:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02244","created_at":"2026-07-15T01:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"OKLSLVT4VHR5","created_at":"2026-07-15T01:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"OKLSLVT4VHR5HMYK","created_at":"2026-07-15T01:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"OKLSLVT4","created_at":"2026-07-15T01:21:49Z"}],"graph_snapshots":[{"event_id":"sha256:d6824ce1a2776aa7f25bda480d36a9d230febcedc63d20025dc9e99860021047","target":"graph","created_at":"2026-07-15T01:21:49Z","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/2602.02244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore. Adding entropy regularization during SFT is not a cure-all; it tends to flatten token distributions toward uniformity, increasing entropy without improving meaningful exploration capability. In this paper, we propose CurioSFT, an entropy-preserving SFT method desi","authors_text":"Dapeng Wu, Hao Gu, Hao Wang, Hongming Piao, Kaixiong Gong, Sirui Han, Xiangyu Yue, Yike Guo, Yuxiao Ye","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T15:53:55Z","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02244","kind":"arxiv","version":3},"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:c8dfdcb570fbcc73e82a0217784578ccb243f2368761f92eb4bdd6ab75acf95b","target":"record","created_at":"2026-07-15T01:21:49Z","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":"b0edf78ea82d42fbcec53138fedfb09279d97a90937ee087e14b0548d242ff3c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T15:53:55Z","title_canon_sha256":"d2b46bfd5c723c037c838aa073af8a12b7faa7f6844d7fd09b33eb8e5a75d6f8"},"schema_version":"1.0","source":{"id":"2602.02244","kind":"arxiv","version":3}},"canonical_sha256":"729725d67ca9e3d3b30a4ab70cde78afabe1291136e70c0098279d8872e1f2c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"729725d67ca9e3d3b30a4ab70cde78afabe1291136e70c0098279d8872e1f2c7","first_computed_at":"2026-07-15T01:21:49.971298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:21:49.971298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cPmvlVb3LEmCxNsSivT06pTuz86j0ArkH92ky/HRazqSB/ZcOHCUwwKOLz6WTsdYcsyTC8rml4izQ5abMYp4Bw==","signature_status":"signed_v1","signed_at":"2026-07-15T01:21:49.972152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.02244","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8dfdcb570fbcc73e82a0217784578ccb243f2368761f92eb4bdd6ab75acf95b","sha256:d6824ce1a2776aa7f25bda480d36a9d230febcedc63d20025dc9e99860021047"],"state_sha256":"9c8e84924baf2e2781b65b9047307eaaf1d801ac7f5b659037543ac104f042fd"}