{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SUQX6L7CL4KGODCAJ5RZN2PIDF","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":"25e063ea992fc30a8f55c19f4b195f97b0b41372d1072154912222e20d25f838","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T03:10:47Z","title_canon_sha256":"7e132d2705964b63c1be48a6ad81d7f6e4120cd5e19ea24e5912c3208b197c25"},"schema_version":"1.0","source":{"id":"2603.18444","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.18444","created_at":"2026-05-26T01:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2603.18444v2","created_at":"2026-05-26T01:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.18444","created_at":"2026-05-26T01:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"SUQX6L7CL4KG","created_at":"2026-05-26T01:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"SUQX6L7CL4KGODCA","created_at":"2026-05-26T01:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"SUQX6L7C","created_at":"2026-05-26T01:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:ba4d833db474a25ceb45e0977594479e92584dd4b6a3ba9517fef09d6f2091b2","target":"graph","created_at":"2026-05-26T01:03:28Z","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/2603.18444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large language models. However, existing group-based RLVR methods often suffer from severe sample inefficiency. This inefficiency stems from reliance on point estimation of rewards from a small number of rollouts, leading to high estimation variance, variance collapse, and ineffective utilization of generated responses. In this work, we reformulate RLVR from a statistical estimation perspective by modeling rewards as samples drawn from a policy-in","authors_text":"Doohyuk Jang, Eunho Yang, Gyouk Chu, Haechan Kim, Soohyun Ryu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T03:10:47Z","title":"Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.18444","kind":"arxiv","version":2},"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":"sha256:52625a4e507e95181f3956c0b7d64aa99ed0a3d78cc178a5da8edb18d14345f4","target":"record","created_at":"2026-05-26T01:03:28Z","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":"25e063ea992fc30a8f55c19f4b195f97b0b41372d1072154912222e20d25f838","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T03:10:47Z","title_canon_sha256":"7e132d2705964b63c1be48a6ad81d7f6e4120cd5e19ea24e5912c3208b197c25"},"schema_version":"1.0","source":{"id":"2603.18444","kind":"arxiv","version":2}},"canonical_sha256":"95217f2fe25f14670c404f6396e9e81972f035c10ed2e347359b7e73eaa481ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95217f2fe25f14670c404f6396e9e81972f035c10ed2e347359b7e73eaa481ad","first_computed_at":"2026-05-26T01:03:28.375177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:28.375177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y5vsWw260IMZCwVUXgCxDgotqpMN+OhNUl1dOjA9XkasC5JDwzCM+84accc5YPl7vWtnDdIYcQr513WZUyA+BA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:28.376092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.18444","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52625a4e507e95181f3956c0b7d64aa99ed0a3d78cc178a5da8edb18d14345f4","sha256:ba4d833db474a25ceb45e0977594479e92584dd4b6a3ba9517fef09d6f2091b2"],"state_sha256":"33d44db03e6e1f6f599d9f20fb31b3d5b04c3e9acdce33438a7edc3e6e9b057e"}