{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBWDFESSL7WNDK3QAUAJ25JCCL","short_pith_number":"pith:MBWDFESS","schema_version":"1.0","canonical_sha256":"606c3292525fecd1ab7005009d752212f7685f34729661181cc7563037c4b256","source":{"kind":"arxiv","id":"2511.07317","version":2},"attestation_state":"computed","paper":{"title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenyang Zhao, Hamish Ivison, Hannaneh Hajishirzi, Hao Peng, Jacqueline He, Lifan Yuan, Natasha Jaques, Pang Wei Koh, Runlong Zhou, Shuyue Stella Li, Simon Shaolei Du, Siting Li, Tong Chen, Yiping Wang, Yulia Tsvetkov, Zhiyuan Zeng, Zhuorui Ye","submitted_at":"2025-11-10T17:18:35Z","abstract_excerpt":"We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). RLVE enables each verifiable environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses. In contrast, static data distributions often lead to vanishing learning signals when problems are either too easy or too hard for the policy. To implement RLVE, we create RLVE-Gym, a large"},"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":"2511.07317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-10T17:18:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5221e73bfb4279b156ce611fe2787980d048e37900da2c0caccb69fbc50ffa24","abstract_canon_sha256":"4ab8ae6dbf4088c78bae5c270d24486e1ca156f63a8dacfef0e5429f6da64863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:10.480738Z","signature_b64":"3yoj+N6V/1/H4KiXBqQBkga8OH8v7qoJ7qkeG+BQBVeaRE9JKx0YDRCWOssOiS71A/ziBthk3Epve/uaGCCqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606c3292525fecd1ab7005009d752212f7685f34729661181cc7563037c4b256","last_reissued_at":"2026-06-09T01:05:10.480235Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:10.480235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenyang Zhao, Hamish Ivison, Hannaneh Hajishirzi, Hao Peng, Jacqueline He, Lifan Yuan, Natasha Jaques, Pang Wei Koh, Runlong Zhou, Shuyue Stella Li, Simon Shaolei Du, Siting Li, Tong Chen, Yiping Wang, Yulia Tsvetkov, Zhiyuan Zeng, Zhuorui Ye","submitted_at":"2025-11-10T17:18:35Z","abstract_excerpt":"We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). RLVE enables each verifiable environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses. In contrast, static data distributions often lead to vanishing learning signals when problems are either too easy or too hard for the policy. To implement RLVE, we create RLVE-Gym, a large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07317","kind":"arxiv","version":2},"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/2511.07317/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":"2511.07317","created_at":"2026-06-09T01:05:10.480295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07317v2","created_at":"2026-06-09T01:05:10.480295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07317","created_at":"2026-06-09T01:05:10.480295+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBWDFESSL7WN","created_at":"2026-06-09T01:05:10.480295+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBWDFESSL7WNDK3Q","created_at":"2026-06-09T01:05:10.480295+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBWDFESS","created_at":"2026-06-09T01:05:10.480295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2601.04809","citing_title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15432","citing_title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11680","citing_title":"ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05365","citing_title":"ZAYA1-8B Technical Report","ref_index":222,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01248","citing_title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL","json":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL.json","graph_json":"https://pith.science/api/pith-number/MBWDFESSL7WNDK3QAUAJ25JCCL/graph.json","events_json":"https://pith.science/api/pith-number/MBWDFESSL7WNDK3QAUAJ25JCCL/events.json","paper":"https://pith.science/paper/MBWDFESS"},"agent_actions":{"view_html":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL","download_json":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL.json","view_paper":"https://pith.science/paper/MBWDFESS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07317&json=true","fetch_graph":"https://pith.science/api/pith-number/MBWDFESSL7WNDK3QAUAJ25JCCL/graph.json","fetch_events":"https://pith.science/api/pith-number/MBWDFESSL7WNDK3QAUAJ25JCCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL/action/storage_attestation","attest_author":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL/action/author_attestation","sign_citation":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL/action/citation_signature","submit_replication":"https://pith.science/pith/MBWDFESSL7WNDK3QAUAJ25JCCL/action/replication_record"}},"created_at":"2026-06-09T01:05:10.480295+00:00","updated_at":"2026-06-09T01:05:10.480295+00:00"}