{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YNNPUD75L4ASNNICVPP2HYFMVK","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":"f969a3ab71dbd6eaed20b2c2ffd61492f98bb36267a76ceef9c6c59473784d42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T08:57:54Z","title_canon_sha256":"2b8d07b5d994911afdcf71e463aefab2b8126fa339e352b4db2b46e81e4eb4f7"},"schema_version":"1.0","source":{"id":"2509.00125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00125","created_at":"2026-07-05T12:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00125v1","created_at":"2026-07-05T12:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00125","created_at":"2026-07-05T12:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"YNNPUD75L4AS","created_at":"2026-07-05T12:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"YNNPUD75L4ASNNIC","created_at":"2026-07-05T12:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"YNNPUD75","created_at":"2026-07-05T12:02:09Z"}],"graph_snapshots":[{"event_id":"sha256:75c7467f2f99d67881aba04054eb68412f3b4b87d05c33ea2a2d2c31403cfebd","target":"graph","created_at":"2026-07-05T12:02:09Z","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/2509.00125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Feedback (RLVF) has become a key technique for enhancing the reasoning abilities of Large Language Models (LLMs). However, its reliance on sparse, outcome based rewards, which only indicate if a final answer is correct or not, fails to provide granular guidance on the reasoning process itself. This limitation hinders efficient learning, as the model cannot distinguish between high quality and inefficient solutions, nor can it learn effectively from different types of failures. To address this, we observe that an LLMs self-certainty often correlates with t","authors_text":"Ang Li, Shouda Liu, Yang Zhang, Yisen Wang, Zhihang Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T08:57:54Z","title":"Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00125","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:ff0fd903154a7253917e26e0faf353dafc1e1ea0cb229869bafc41f211c32fc1","target":"record","created_at":"2026-07-05T12:02:09Z","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":"f969a3ab71dbd6eaed20b2c2ffd61492f98bb36267a76ceef9c6c59473784d42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T08:57:54Z","title_canon_sha256":"2b8d07b5d994911afdcf71e463aefab2b8126fa339e352b4db2b46e81e4eb4f7"},"schema_version":"1.0","source":{"id":"2509.00125","kind":"arxiv","version":1}},"canonical_sha256":"c35afa0ffd5f0126b502abdfa3e0acaaa677f6705217314a19fc5c87d631d8a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c35afa0ffd5f0126b502abdfa3e0acaaa677f6705217314a19fc5c87d631d8a0","first_computed_at":"2026-07-05T12:02:09.743594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:09.743594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fooLMeys5gnjRtUVNyNBZyBzItby/okboX6d+Wr/4DzI47FWYAP3LQpv7nmJfHM6C9Os9WzdMmdD4CqvrEblDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:09.744398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff0fd903154a7253917e26e0faf353dafc1e1ea0cb229869bafc41f211c32fc1","sha256:75c7467f2f99d67881aba04054eb68412f3b4b87d05c33ea2a2d2c31403cfebd"],"state_sha256":"39c1bc5e820e2d349504e5a84f7c20d92cf4a78a42f64959cfe7f7ff6552d468"}