{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TOLPITQ7Q7YLKGUREKV6NCCM5L","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":"5c10fdb82643636c62f218dc863aaf0c55b84bb39ad238f5078b9e6fabe5dca3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:06:38Z","title_canon_sha256":"483cfcdae28f1d4aa2a39937ef7e9d9f83d1be27732246496a5562c15b2e248d"},"schema_version":"1.0","source":{"id":"2606.01281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01281","created_at":"2026-06-02T02:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01281v1","created_at":"2026-06-02T02:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01281","created_at":"2026-06-02T02:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"TOLPITQ7Q7YL","created_at":"2026-06-02T02:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"TOLPITQ7Q7YLKGUR","created_at":"2026-06-02T02:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"TOLPITQ7","created_at":"2026-06-02T02:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:febf5326ab3b72bba96515969a9c1c46c200db54e625a8dcacfcea50e0481943","target":"graph","created_at":"2026-06-02T02:04:28Z","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/2606.01281/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 a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, its effectiveness is substantially hindered by the prevalence of ineffective training data: many sampled prompts yield response groups that are either entirely correct or entirely incorrect, resulting in zero-variance rewards and limited learning signals. Recent state-of-the-art methods address this issue through extensive LLM rollouts to filter ineffective samples, but at the cost of considerable computational overhead. Alt","authors_text":"Heming Zou, Qi Wang, Xiangyang Ji, Yixiu Mao, Yun Qu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:06:38Z","title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01281","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:c63d56712147712a931db50dd1cf8440ca20535bdf711a9e9646c99c681156d9","target":"record","created_at":"2026-06-02T02:04:28Z","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":"5c10fdb82643636c62f218dc863aaf0c55b84bb39ad238f5078b9e6fabe5dca3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:06:38Z","title_canon_sha256":"483cfcdae28f1d4aa2a39937ef7e9d9f83d1be27732246496a5562c15b2e248d"},"schema_version":"1.0","source":{"id":"2606.01281","kind":"arxiv","version":1}},"canonical_sha256":"9b96f44e1f87f0b51a9122abe6884ceaf0d02dbfb94ffe711278c1db09e5f6c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b96f44e1f87f0b51a9122abe6884ceaf0d02dbfb94ffe711278c1db09e5f6c6","first_computed_at":"2026-06-02T02:04:28.751515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:28.751515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aXpecmm4MuXqNF/My9ML897iW7e43h/H0WE+TTwaf5m6IiSUXRzecWHQDBRkDSkmVhH5Z8Gj8I+HuypyuzwZDA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:28.751910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c63d56712147712a931db50dd1cf8440ca20535bdf711a9e9646c99c681156d9","sha256:febf5326ab3b72bba96515969a9c1c46c200db54e625a8dcacfcea50e0481943"],"state_sha256":"8a20b1ff37922c72370a5939dd22919fbf2a73929418904d746c0aca23314bab"}