{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4VVT6V4I73KTDJOGVSHVAWEQIQ","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":"730816e7639183ff06fb2b29b392365d8b9d90cd7030f81801e9101e7d487631","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T12:21:41Z","title_canon_sha256":"2022df57695539a08401510975b6e2e2afff74a226bd01cdb18da5a0bfbe9928"},"schema_version":"1.0","source":{"id":"2605.22389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22389","created_at":"2026-05-22T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22389v1","created_at":"2026-05-22T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22389","created_at":"2026-05-22T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"4VVT6V4I73KT","created_at":"2026-05-22T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"4VVT6V4I73KTDJOG","created_at":"2026-05-22T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"4VVT6V4I","created_at":"2026-05-22T01:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:deafb3bfb9dfdb2e89c1901d616e31e2e837e89768f9b13f6e3f244d2e2901ae","target":"graph","created_at":"2026-05-22T01:04:41Z","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/2605.22389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effectively training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning data. Existing methods are either computationally expensive or fail to reliably distinguish high- from low-quality reasoning samples. To address this, we propose High-Entropy Sum (HES), a training-free metric that quantifies reasoning quality by summing only the entropy of the top (e.g., 0.5\\%) highest-entropy tokens in each reasoning sample. We validate HES across three mainstream training paradigms: Supervised Fine-tuning (SFT), Rejection Fine","authors_text":"Chengpeng Li, Dayiheng Liu, Fengbin Zhu, Fuli Feng, Keqin Bao, Wenjie Wang, Xiaoyuan Li, Yiyao Yu, Yubo Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T12:21:41Z","title":"Unified Data Selection for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22389","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":"sha256:6095a9a6a4f89c5c534caae1527c5936e16720634396d267e48cc4277f9e5781","target":"record","created_at":"2026-05-22T01:04:41Z","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":"730816e7639183ff06fb2b29b392365d8b9d90cd7030f81801e9101e7d487631","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T12:21:41Z","title_canon_sha256":"2022df57695539a08401510975b6e2e2afff74a226bd01cdb18da5a0bfbe9928"},"schema_version":"1.0","source":{"id":"2605.22389","kind":"arxiv","version":1}},"canonical_sha256":"e56b3f5788fed531a5c6ac8f50589044106850210315ff0931e4c2320d91bcc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56b3f5788fed531a5c6ac8f50589044106850210315ff0931e4c2320d91bcc1","first_computed_at":"2026-05-22T01:04:41.166088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:41.166088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rLvmrDmgo0QazLD5h0q3Bq5OvmM+UYoST4KwyKvm25kaJnCKcG82KlR58Fil6sFSmwIEGOlsheWAwdklyEdfCw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:41.166911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6095a9a6a4f89c5c534caae1527c5936e16720634396d267e48cc4277f9e5781","sha256:deafb3bfb9dfdb2e89c1901d616e31e2e837e89768f9b13f6e3f244d2e2901ae"],"state_sha256":"88b8f800e910afeb42d3492478ee9c77baddb1112c55da5c420fef593556e04c"}