{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NYLWGCIX6KUDIAKDBRMBW5CXYA","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":"034a83825d0962298fb22be8375c79501a808ddc0cd29f602d637d7a534aa26b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T12:25:57Z","title_canon_sha256":"a171ea4e8538f4e0c39ebfb85e107b69668b0719a288b8365497839de571b993"},"schema_version":"1.0","source":{"id":"2605.28388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28388","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28388v1","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28388","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"NYLWGCIX6KUD","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"NYLWGCIX6KUDIAKD","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"NYLWGCIX","created_at":"2026-05-28T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:87af40c77f93652bfa59ebef54d12971e9e7a48fe4d2d4299ef6fbc25c0f9ab8","target":"graph","created_at":"2026-05-28T01:05:16Z","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/2605.28388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Reward (RLVR) is empirically shown to notably enhance the reasoning performance of large language models (LLMs), particularly in mathematics and programming. However, the mechanistic role of Sample Difficulty in RLVR remains poorly understood. In this paper, we investigate RLVR through the lens of difficulty-wise and one-sample analysis. We find that sample difficulty has a non-monotonic effect on RLVR: easy and medium-difficulty problems yield the strongest and most stable reasoning improvements, whereas overly hard problems often provide weak learning s","authors_text":"Jiajun Zhang, Weiwei Xing, Xiaohui Gao, Yue Cheng, Zhanxing Zhu, Zheng Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T12:25:57Z","title":"Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28388","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":"sha256:963aa421f8c44282da6d77f7d5a4ac084eb300a909884357ffc1a2998bf57c17","target":"record","created_at":"2026-05-28T01:05:16Z","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":"034a83825d0962298fb22be8375c79501a808ddc0cd29f602d637d7a534aa26b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T12:25:57Z","title_canon_sha256":"a171ea4e8538f4e0c39ebfb85e107b69668b0719a288b8365497839de571b993"},"schema_version":"1.0","source":{"id":"2605.28388","kind":"arxiv","version":1}},"canonical_sha256":"6e17630917f2a83401430c581b7457c004c7ae8447f0590e270eb8e55584553d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e17630917f2a83401430c581b7457c004c7ae8447f0590e270eb8e55584553d","first_computed_at":"2026-05-28T01:05:16.806529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:16.806529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vjsW+EQ7D10624BxZZwYSFhlGerbEmphYO7FBqN+ULu01PDUnDBVyrHcmiC6zyvjn5BnTJ/pXGTPXHZFcXTFAA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:16.806932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:963aa421f8c44282da6d77f7d5a4ac084eb300a909884357ffc1a2998bf57c17","sha256:87af40c77f93652bfa59ebef54d12971e9e7a48fe4d2d4299ef6fbc25c0f9ab8"],"state_sha256":"84f36dc182580a6c6b4534996107b42d68ee9ea14959b381dcee8556dd99cea9"}