{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XYYSSUF2WJ4EJ3FOGN5B3DCEQI","short_pith_number":"pith:XYYSSUF2","schema_version":"1.0","canonical_sha256":"be312950bab27844ecae337a1d8c4482184967a3d8de3314b7a5a1dea250695a","source":{"kind":"arxiv","id":"2606.04516","version":1},"attestation_state":"computed","paper":{"title":"GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling","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, Kai Tang, Shenzhi Yang, Weiqiang Wang, Xing Zheng, Xuening Feng, Yingfan Ma, Zhengqing Zang, Zhongqi Chen","submitted_at":"2026-06-03T06:47:50Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse. Recent semi-supervised RLVR methods address this by using a small labeled set to guide unlabeled data, achieving a promising trade-off between training efficacy and annotation cost. However, they suffer from a severe data-efficiency bottleneck due to the reliance on coarse performance heuristics, leaving a vast majority of valuable instances underu"},"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":"2606.04516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T06:47:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f973271365b23b5f61c63cb257c4b05c3fb172130777d5f2219ba29a3fb01c16","abstract_canon_sha256":"62348edacdf824ec3db4e4deae04b5f8564325d2ad92547f57f5596cc62fa853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:15.644510Z","signature_b64":"EY3jU+gOQk6d/5y2HMhJQpR9DuMIm8WdI5TGrDjkcq1BEz0boCsbTeHsCjIVcWwlTuwmLvqwxmhSIej/RPdqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be312950bab27844ecae337a1d8c4482184967a3d8de3314b7a5a1dea250695a","last_reissued_at":"2026-06-04T01:09:15.643813Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:15.643813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling","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, Kai Tang, Shenzhi Yang, Weiqiang Wang, Xing Zheng, Xuening Feng, Yingfan Ma, Zhengqing Zang, Zhongqi Chen","submitted_at":"2026-06-03T06:47:50Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse. Recent semi-supervised RLVR methods address this by using a small labeled set to guide unlabeled data, achieving a promising trade-off between training efficacy and annotation cost. However, they suffer from a severe data-efficiency bottleneck due to the reliance on coarse performance heuristics, leaving a vast majority of valuable instances underu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04516","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/2606.04516/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":"2606.04516","created_at":"2026-06-04T01:09:15.643904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04516v1","created_at":"2026-06-04T01:09:15.643904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04516","created_at":"2026-06-04T01:09:15.643904+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYYSSUF2WJ4E","created_at":"2026-06-04T01:09:15.643904+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYYSSUF2WJ4EJ3FO","created_at":"2026-06-04T01:09:15.643904+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYYSSUF2","created_at":"2026-06-04T01:09:15.643904+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/XYYSSUF2WJ4EJ3FOGN5B3DCEQI","json":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI.json","graph_json":"https://pith.science/api/pith-number/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/graph.json","events_json":"https://pith.science/api/pith-number/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/events.json","paper":"https://pith.science/paper/XYYSSUF2"},"agent_actions":{"view_html":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI","download_json":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI.json","view_paper":"https://pith.science/paper/XYYSSUF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04516&json=true","fetch_graph":"https://pith.science/api/pith-number/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/graph.json","fetch_events":"https://pith.science/api/pith-number/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/action/storage_attestation","attest_author":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/action/author_attestation","sign_citation":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/action/citation_signature","submit_replication":"https://pith.science/pith/XYYSSUF2WJ4EJ3FOGN5B3DCEQI/action/replication_record"}},"created_at":"2026-06-04T01:09:15.643904+00:00","updated_at":"2026-06-04T01:09:15.643904+00:00"}