{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KZQQCKJFHRSUE3SSN22F63ELZC","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":"8c215743658009d4422620cfa0439d3d924ba6be0fad70858cf9b3917b9442e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T06:34:42Z","title_canon_sha256":"217a71de6c679637937c0a0d2a32bc4594e8ecae863fb2179367c6df457fff4b"},"schema_version":"1.0","source":{"id":"2606.04503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04503","created_at":"2026-06-04T01:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04503v1","created_at":"2026-06-04T01:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04503","created_at":"2026-06-04T01:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"KZQQCKJFHRSU","created_at":"2026-06-04T01:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"KZQQCKJFHRSUE3SS","created_at":"2026-06-04T01:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"KZQQCKJF","created_at":"2026-06-04T01:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:207f87309c9306cd62a110f836c942dca2157300b6673b22a159824327228140","target":"graph","created_at":"2026-06-04T01:09:14Z","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/2606.04503/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 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,","authors_text":"Bowen Song, Gang Chen, Guangcheng Zhu, Haobo Wang, Shenzhi Yang, Weiqiang Wang, Xing Zheng, Xuening Feng, Yingfan Ma, Zhongqi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T06:34:42Z","title":"Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04503","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:e794adcc354006d9023328a24b4e31e9b2bcd60738aff5bb94f75473e056a826","target":"record","created_at":"2026-06-04T01:09:14Z","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":"8c215743658009d4422620cfa0439d3d924ba6be0fad70858cf9b3917b9442e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T06:34:42Z","title_canon_sha256":"217a71de6c679637937c0a0d2a32bc4594e8ecae863fb2179367c6df457fff4b"},"schema_version":"1.0","source":{"id":"2606.04503","kind":"arxiv","version":1}},"canonical_sha256":"56610129253c65426e526eb45f6c8bc8bc9ef88b766059856d30aeefb380e28f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56610129253c65426e526eb45f6c8bc8bc9ef88b766059856d30aeefb380e28f","first_computed_at":"2026-06-04T01:09:14.705423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:14.705423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r+/cBPUpHhcAUZ+bLI4rN13cyhkOA5HTrl0RfAOqs9lu7l80fWnfBICDvrUK+iLg7co94xqxm7SVAPs/B739Dw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:14.706071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e794adcc354006d9023328a24b4e31e9b2bcd60738aff5bb94f75473e056a826","sha256:207f87309c9306cd62a110f836c942dca2157300b6673b22a159824327228140"],"state_sha256":"6b554c3e5a8f52e156bf20d3dfa5920e5eee8f269ed2631d7b7a0ebacf5b6863"}