{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:75O3ODZLFB3DF7ZYYBMOXBJOAT","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":"0a5424fc7e33c507184ec7b9bc936624f568c9ef5ad2425d5596f29b2083a869","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T12:12:37Z","title_canon_sha256":"79e566e8993b52e6e594a800df820605b565b14300fdc30b4ad3341ee01b4571"},"schema_version":"1.0","source":{"id":"2607.13753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13753","created_at":"2026-07-16T01:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13753v1","created_at":"2026-07-16T01:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13753","created_at":"2026-07-16T01:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"75O3ODZLFB3D","created_at":"2026-07-16T01:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"75O3ODZLFB3DF7ZY","created_at":"2026-07-16T01:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"75O3ODZL","created_at":"2026-07-16T01:23:04Z"}],"graph_snapshots":[{"event_id":"sha256:3718b2bd84ce0a417403bb485d9fae069ef84e40c484e79f11e3f8f64c2260fd","target":"graph","created_at":"2026-07-16T01:23:04Z","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/2607.13753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have made strong reasoning gains through supervised fine-tuning, reinforcement learning, and on-policy distillation, yet these post-training methods are usually evaluated only by final-answer accuracy. We study how they reshape confidence during reasoning. We introduce a three-stage calibration framework that evaluates confidence before, during, and after chain-of-thought generation, corresponding to difficulty estimation, early termination, and answer aggregation. Through a controlled comparison on mathematical reasoning benchmarks, we find that OPD provides the most use","authors_text":"Anhao Zhao, Guodong Du, Shuhao Li, Tianyu Yuan, Wanyu Lin, Xiaoyu Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T12:12:37Z","title":"Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13753","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":"sha256:40655a4f444fa6317a12968fd21848ef0673fa5c6858263f84cf0a17118ec6cd","target":"record","created_at":"2026-07-16T01:23:04Z","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":"0a5424fc7e33c507184ec7b9bc936624f568c9ef5ad2425d5596f29b2083a869","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T12:12:37Z","title_canon_sha256":"79e566e8993b52e6e594a800df820605b565b14300fdc30b4ad3341ee01b4571"},"schema_version":"1.0","source":{"id":"2607.13753","kind":"arxiv","version":1}},"canonical_sha256":"ff5db70f2b287632ff38c058eb852e04f18d6da20043ddb5098e580e757cdf47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff5db70f2b287632ff38c058eb852e04f18d6da20043ddb5098e580e757cdf47","first_computed_at":"2026-07-16T01:23:04.296005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:23:04.296005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HzBnC8RBNQY40uhykMnbXzNwPuRINEN5vC3FPCnwATbyw73N4en5h6/Sn9/1w/afrEOUPmRgQr9Xor+HyYNkAQ==","signature_status":"signed_v1","signed_at":"2026-07-16T01:23:04.297351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40655a4f444fa6317a12968fd21848ef0673fa5c6858263f84cf0a17118ec6cd","sha256:3718b2bd84ce0a417403bb485d9fae069ef84e40c484e79f11e3f8f64c2260fd"],"state_sha256":"80a27e5273aa51cfdc737bc79b0248b87553bae514e1cf373938d000c0e5b9cd"}