{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HBBWPG6DRQYAPR7CAMCKSJHRA4","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":"3607e5e98d8bec6ce90a5a8699454013ea83146fb5381426eadbb64488046564","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T07:52:40Z","title_canon_sha256":"27e00b93e8d485d3e6f838496472ea78aa3a0cb4b9514e526a4319445ce75cd2"},"schema_version":"1.0","source":{"id":"2606.07006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07006","created_at":"2026-06-08T01:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07006v1","created_at":"2026-06-08T01:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07006","created_at":"2026-06-08T01:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"HBBWPG6DRQYA","created_at":"2026-06-08T01:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"HBBWPG6DRQYAPR7C","created_at":"2026-06-08T01:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"HBBWPG6D","created_at":"2026-06-08T01:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:d6587e7cd6bf5c670d5acb9ab7a3d7d0e8f88bec27663779b9bdad373830039d","target":"graph","created_at":"2026-06-08T01:04:40Z","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/2606.07006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior. However, reasoning is not simple path imitation: rigidly following one demonstrated solution may overfit to surface forms and suppress the model's own reasoning distribution. We propose Rollout-Adaptive Supervised Fine-Tuning (RASFT), a policy-aware SFT framework that calibrates expert supervision according to problem-level solvability estimated from verified on-policy rollouts. Fo","authors_text":"Fei Sun, Fengyuan Liu, Mengnan Du, Na Zou, Wei Shi, Yanguang Liu, Yongliang Miao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T07:52:40Z","title":"RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07006","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:f292a989048ddb8c616b840478ba4066785da2d8acf63066b2359b8dcd35d251","target":"record","created_at":"2026-06-08T01:04:40Z","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":"3607e5e98d8bec6ce90a5a8699454013ea83146fb5381426eadbb64488046564","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T07:52:40Z","title_canon_sha256":"27e00b93e8d485d3e6f838496472ea78aa3a0cb4b9514e526a4319445ce75cd2"},"schema_version":"1.0","source":{"id":"2606.07006","kind":"arxiv","version":1}},"canonical_sha256":"3843679bc38c3007c7e20304a924f1073c65710c41ea8c89574dd0d2d38fc2c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3843679bc38c3007c7e20304a924f1073c65710c41ea8c89574dd0d2d38fc2c2","first_computed_at":"2026-06-08T01:04:40.839829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:40.839829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lG11HvcjPwVfLE2JQzT5ZugEYYWW7eCrIbCwsSNiAxAU0HOUbkIvBAPdbbX3IjWu+Jfgs71dljM1DAxyfB6TAw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:40.840677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f292a989048ddb8c616b840478ba4066785da2d8acf63066b2359b8dcd35d251","sha256:d6587e7cd6bf5c670d5acb9ab7a3d7d0e8f88bec27663779b9bdad373830039d"],"state_sha256":"d25c92ead2fc337bdf9f47e9ef8cbc2507f64cdabca8b5c04c410d4dd5ebf230"}