{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TOLPITQ7Q7YLKGUREKV6NCCM5L","short_pith_number":"pith:TOLPITQ7","schema_version":"1.0","canonical_sha256":"9b96f44e1f87f0b51a9122abe6884ceaf0d02dbfb94ffe711278c1db09e5f6c6","source":{"kind":"arxiv","id":"2606.01281","version":1},"attestation_state":"computed","paper":{"title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heming Zou, Qi Wang, Xiangyang Ji, Yixiu Mao, Yun Qu","submitted_at":"2026-05-31T15:06:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:06:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"483cfcdae28f1d4aa2a39937ef7e9d9f83d1be27732246496a5562c15b2e248d","abstract_canon_sha256":"5c10fdb82643636c62f218dc863aaf0c55b84bb39ad238f5078b9e6fabe5dca3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:28.751910Z","signature_b64":"aXpecmm4MuXqNF/My9ML897iW7e43h/H0WE+TTwaf5m6IiSUXRzecWHQDBRkDSkmVhH5Z8Gj8I+HuypyuzwZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b96f44e1f87f0b51a9122abe6884ceaf0d02dbfb94ffe711278c1db09e5f6c6","last_reissued_at":"2026-06-02T02:04:28.751515Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:28.751515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heming Zou, Qi Wang, Xiangyang Ji, Yixiu Mao, Yun Qu","submitted_at":"2026-05-31T15:06:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01281","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01281/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01281","created_at":"2026-06-02T02:04:28.751576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01281v1","created_at":"2026-06-02T02:04:28.751576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01281","created_at":"2026-06-02T02:04:28.751576+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOLPITQ7Q7YL","created_at":"2026-06-02T02:04:28.751576+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOLPITQ7Q7YLKGUR","created_at":"2026-06-02T02:04:28.751576+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOLPITQ7","created_at":"2026-06-02T02:04:28.751576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L","json":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L.json","graph_json":"https://pith.science/api/pith-number/TOLPITQ7Q7YLKGUREKV6NCCM5L/graph.json","events_json":"https://pith.science/api/pith-number/TOLPITQ7Q7YLKGUREKV6NCCM5L/events.json","paper":"https://pith.science/paper/TOLPITQ7"},"agent_actions":{"view_html":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L","download_json":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L.json","view_paper":"https://pith.science/paper/TOLPITQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01281&json=true","fetch_graph":"https://pith.science/api/pith-number/TOLPITQ7Q7YLKGUREKV6NCCM5L/graph.json","fetch_events":"https://pith.science/api/pith-number/TOLPITQ7Q7YLKGUREKV6NCCM5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L/action/storage_attestation","attest_author":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L/action/author_attestation","sign_citation":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L/action/citation_signature","submit_replication":"https://pith.science/pith/TOLPITQ7Q7YLKGUREKV6NCCM5L/action/replication_record"}},"created_at":"2026-06-02T02:04:28.751576+00:00","updated_at":"2026-06-02T02:04:28.751576+00:00"}