{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A325CT6LKQEKUFICPQKXH62WE3","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":"28db7998274c084c2582d78e4bfd8e69a38833d9ed59ff8cb5e9148af199833f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","title_canon_sha256":"3ebae9108e9356a8d9026e7d924f18ea579620e823b7b28b146b4231e52a65a9"},"schema_version":"1.0","source":{"id":"2606.27369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27369","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27369v1","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27369","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"A325CT6LKQEK","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"A325CT6LKQEKUFIC","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"A325CT6L","created_at":"2026-06-26T01:16:20Z"}],"graph_snapshots":[{"event_id":"sha256:9b1232fcfae7ac391d3480f7ca96e15044b08bc8fe3eb77fbe4003a1e54c7584","target":"graph","created_at":"2026-06-26T01:16:20Z","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/2606.27369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the ground-truth solution is unknown. We introduce a \\textbf{R}anking-\\textbf{i}nduced \\textbf{VER}ifiable framework (RiVER) that trains LLMs on score-based optimization tasks without ground-truth solutions, using deterministic execution feedback as continuous-valued supervision. When applying group-relative RL to such continuous rewards, we identify two key challenges: \\emph{scale dominance}, where uncalibrated score magn","authors_text":"Kun Zhou, Nikki Lijing Kuang, Qiyue Gao, Tongtong Liang, Xunpeng Huang, Yi-An Ma, Yingyu Lin, Yuxiong He, Zhewei Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27369","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":"sha256:2eeb637678863a6ec19ebd6ecd48b72d3d48babfe8de22c82c00a32daa785fc8","target":"record","created_at":"2026-06-26T01:16:20Z","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":"28db7998274c084c2582d78e4bfd8e69a38833d9ed59ff8cb5e9148af199833f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T17:59:36Z","title_canon_sha256":"3ebae9108e9356a8d9026e7d924f18ea579620e823b7b28b146b4231e52a65a9"},"schema_version":"1.0","source":{"id":"2606.27369","kind":"arxiv","version":1}},"canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06f5d14fcb5408aa15027c1573fb5626cc024c81436c7c7d7418ed1ef92b7cbc","first_computed_at":"2026-06-26T01:16:20.089000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:20.089000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zdkFbhdIxc8AkBBTIe8EQrPg82UHS0975S5FXClWUnwdjuvodlY0DJsVUxpbDzJ7cCXeHS49hYsABOJY82V6CA==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:20.089413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2eeb637678863a6ec19ebd6ecd48b72d3d48babfe8de22c82c00a32daa785fc8","sha256:9b1232fcfae7ac391d3480f7ca96e15044b08bc8fe3eb77fbe4003a1e54c7584"],"state_sha256":"dbede6db756e7c5c2c7f5b48fd06e89584bd93eb079387b1feb7d8e7adb5a57e"}