{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KZQQCKJFHRSUE3SSN22F63ELZC","short_pith_number":"pith:KZQQCKJF","schema_version":"1.0","canonical_sha256":"56610129253c65426e526eb45f6c8bc8bc9ef88b766059856d30aeefb380e28f","source":{"kind":"arxiv","id":"2606.04503","version":1},"attestation_state":"computed","paper":{"title":"Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bowen Song, Gang Chen, Guangcheng Zhu, Haobo Wang, Shenzhi Yang, Weiqiang Wang, Xing Zheng, Xuening Feng, Yingfan Ma, Zhongqi Chen","submitted_at":"2026-06-03T06:34:42Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fully-annotated dataset. To this end, data-efficient RLVR methods have been widely studied from two perspectives: (i) data selection methods identify a small subset of \"golden\" samples that yield near-full-data performance, but they rely on a pre-existing pool of labeled data. (ii) unsupervised RLVR methods train the model using its own internal supervision signals on large-scale unlabeled data, yet they exhibit suboptimal performance. Accordingly,"},"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":"2606.04503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T06:34:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"217a71de6c679637937c0a0d2a32bc4594e8ecae863fb2179367c6df457fff4b","abstract_canon_sha256":"8c215743658009d4422620cfa0439d3d924ba6be0fad70858cf9b3917b9442e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:14.706071Z","signature_b64":"r+/cBPUpHhcAUZ+bLI4rN13cyhkOA5HTrl0RfAOqs9lu7l80fWnfBICDvrUK+iLg7co94xqxm7SVAPs/B739Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56610129253c65426e526eb45f6c8bc8bc9ef88b766059856d30aeefb380e28f","last_reissued_at":"2026-06-04T01:09:14.705423Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:14.705423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bowen Song, Gang Chen, Guangcheng Zhu, Haobo Wang, Shenzhi Yang, Weiqiang Wang, Xing Zheng, Xuening Feng, Yingfan Ma, Zhongqi Chen","submitted_at":"2026-06-03T06:34:42Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fully-annotated dataset. To this end, data-efficient RLVR methods have been widely studied from two perspectives: (i) data selection methods identify a small subset of \"golden\" samples that yield near-full-data performance, but they rely on a pre-existing pool of labeled data. (ii) unsupervised RLVR methods train the model using its own internal supervision signals on large-scale unlabeled data, yet they exhibit suboptimal performance. Accordingly,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04503","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/2606.04503/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":"2606.04503","created_at":"2026-06-04T01:09:14.705536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04503v1","created_at":"2026-06-04T01:09:14.705536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04503","created_at":"2026-06-04T01:09:14.705536+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZQQCKJFHRSU","created_at":"2026-06-04T01:09:14.705536+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZQQCKJFHRSUE3SS","created_at":"2026-06-04T01:09:14.705536+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZQQCKJF","created_at":"2026-06-04T01:09:14.705536+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/KZQQCKJFHRSUE3SSN22F63ELZC","json":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC.json","graph_json":"https://pith.science/api/pith-number/KZQQCKJFHRSUE3SSN22F63ELZC/graph.json","events_json":"https://pith.science/api/pith-number/KZQQCKJFHRSUE3SSN22F63ELZC/events.json","paper":"https://pith.science/paper/KZQQCKJF"},"agent_actions":{"view_html":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC","download_json":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC.json","view_paper":"https://pith.science/paper/KZQQCKJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04503&json=true","fetch_graph":"https://pith.science/api/pith-number/KZQQCKJFHRSUE3SSN22F63ELZC/graph.json","fetch_events":"https://pith.science/api/pith-number/KZQQCKJFHRSUE3SSN22F63ELZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC/action/storage_attestation","attest_author":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC/action/author_attestation","sign_citation":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC/action/citation_signature","submit_replication":"https://pith.science/pith/KZQQCKJFHRSUE3SSN22F63ELZC/action/replication_record"}},"created_at":"2026-06-04T01:09:14.705536+00:00","updated_at":"2026-06-04T01:09:14.705536+00:00"}