{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4KTDL4BXCGPQJ6EGG42BRGAGJ7","short_pith_number":"pith:4KTDL4BX","schema_version":"1.0","canonical_sha256":"e2a635f037119f04f88637341898064fe64c03758735b945878e1f9cab62182d","source":{"kind":"arxiv","id":"2605.25864","version":1},"attestation_state":"computed","paper":{"title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guojun Yin, Jiajun Chai, Li Wang, Tianhao Peng, Wei Lin, Xiaodong Lu, Xiaohan Wang, Yikun Ban","submitted_at":"2026-05-25T13:55:12Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward computation, the acquisition of which is often prohibitively expensive in real-world scenarios. While unsupervised RLVR paradigms attempt to circumvent this by training on pseudo-labels, they are notoriously susceptible to training collapse. Moreover, different samples often exhibit varying annotation values. In this paper, we propose Reinforcement Learning with A"},"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":"2605.25864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T13:55:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5efd9fca538955c35f85596ac4a4f2bfd63569929779464c5daa1dc429e9e390","abstract_canon_sha256":"05486c7d26905390b028aff76179474152663d53ee0c0cb9920c826715a455de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:15.871649Z","signature_b64":"G9jxIhTx9yBWjHP1T1yejiJTIDxkTm6fxRPp2TR0Zvngi8XSGqoBc3ttYIzN02g2ua8+TO3ocoJNrlEauBUjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2a635f037119f04f88637341898064fe64c03758735b945878e1f9cab62182d","last_reissued_at":"2026-05-26T02:05:15.871106Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:15.871106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guojun Yin, Jiajun Chai, Li Wang, Tianhao Peng, Wei Lin, Xiaodong Lu, Xiaohan Wang, Yikun Ban","submitted_at":"2026-05-25T13:55:12Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward computation, the acquisition of which is often prohibitively expensive in real-world scenarios. While unsupervised RLVR paradigms attempt to circumvent this by training on pseudo-labels, they are notoriously susceptible to training collapse. Moreover, different samples often exhibit varying annotation values. In this paper, we propose Reinforcement Learning with A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25864","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/2605.25864/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":"2605.25864","created_at":"2026-05-26T02:05:15.871189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25864v1","created_at":"2026-05-26T02:05:15.871189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25864","created_at":"2026-05-26T02:05:15.871189+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KTDL4BXCGPQ","created_at":"2026-05-26T02:05:15.871189+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KTDL4BXCGPQJ6EG","created_at":"2026-05-26T02:05:15.871189+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KTDL4BX","created_at":"2026-05-26T02:05:15.871189+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/4KTDL4BXCGPQJ6EGG42BRGAGJ7","json":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7.json","graph_json":"https://pith.science/api/pith-number/4KTDL4BXCGPQJ6EGG42BRGAGJ7/graph.json","events_json":"https://pith.science/api/pith-number/4KTDL4BXCGPQJ6EGG42BRGAGJ7/events.json","paper":"https://pith.science/paper/4KTDL4BX"},"agent_actions":{"view_html":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7","download_json":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7.json","view_paper":"https://pith.science/paper/4KTDL4BX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25864&json=true","fetch_graph":"https://pith.science/api/pith-number/4KTDL4BXCGPQJ6EGG42BRGAGJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/4KTDL4BXCGPQJ6EGG42BRGAGJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7/action/storage_attestation","attest_author":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7/action/author_attestation","sign_citation":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7/action/citation_signature","submit_replication":"https://pith.science/pith/4KTDL4BXCGPQJ6EGG42BRGAGJ7/action/replication_record"}},"created_at":"2026-05-26T02:05:15.871189+00:00","updated_at":"2026-05-26T02:05:15.871189+00:00"}