{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3PXB3R2ZY5KBLYI5MRDYREXU4H","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":"9846930a147ee1c6490c04bf169747c159a574faeaa7066fe83efe8659922c16","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T04:25:10Z","title_canon_sha256":"e207338cf67a0b619718b73a4e53226c36ec313b5cb811aa6a833f9f0ab2836a"},"schema_version":"1.0","source":{"id":"2505.17454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17454","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17454v1","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17454","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"3PXB3R2ZY5KB","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"3PXB3R2ZY5KBLYI5","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"3PXB3R2Z","created_at":"2026-07-05T11:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:d42bd5bb7710442eb045d9872fe2ece94c791fffd6e0eb6e0ffca6d829c7bc26","target":"graph","created_at":"2026-07-05T11:08:26Z","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/2505.17454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervision. To address this issue, recent studies have explored self-training methods that improve reasoning capabilities using pseudo-labels generated by the LLMs themselves. Among these, confidence-based self-training fine-tunes LLMs to prefer reasoning paths with high-confidence answers, where confidence is estimated via majority voting. However, such methods exclusively focus on the quality of the final answer and may i","authors_text":"Hyosoon Jang, Jungseul Ok, Sungjae Lee, Sungsoo Ahn, Yunhui Jang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T04:25:10Z","title":"Self-Training Large Language Models with Confident Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17454","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":"sha256:83ab0b650443a17c5911dc89452ae11ff72e3d5c002138a6dbf04661b725c201","target":"record","created_at":"2026-07-05T11:08:26Z","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":"9846930a147ee1c6490c04bf169747c159a574faeaa7066fe83efe8659922c16","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T04:25:10Z","title_canon_sha256":"e207338cf67a0b619718b73a4e53226c36ec313b5cb811aa6a833f9f0ab2836a"},"schema_version":"1.0","source":{"id":"2505.17454","kind":"arxiv","version":1}},"canonical_sha256":"dbee1dc759c75415e11d64478892f4e1f37ef2e83265c6ffafd302780323ef0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbee1dc759c75415e11d64478892f4e1f37ef2e83265c6ffafd302780323ef0e","first_computed_at":"2026-07-05T11:08:26.447149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:26.447149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Knrg6TeemApnoU5pd64lv3LTWCgruVBLdjQ734u7hySdnY7zFO3uVtrHjSt7VYnrC0HXZtmnItr73X04k4QgDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:26.447547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83ab0b650443a17c5911dc89452ae11ff72e3d5c002138a6dbf04661b725c201","sha256:d42bd5bb7710442eb045d9872fe2ece94c791fffd6e0eb6e0ffca6d829c7bc26"],"state_sha256":"22f63c41ee04b77a706665e1f869c29355d40c32f1dfb958a37fff3bb0525c10"}