{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5VBEJZZ4X5MYTA4QPJG5PZPTPH","short_pith_number":"pith:5VBEJZZ4","schema_version":"1.0","canonical_sha256":"ed4244e73cbf598983907a4dd7e5f379db6f16259a093b1301cfebf73c4a5152","source":{"kind":"arxiv","id":"2505.17667","version":2},"attestation_state":"computed","paper":{"title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenliang Li, Fanqi Wan, Fei Huang, Jingren Zhou, Ji Zhang, Ming Yan, Shengyi Liao, Weizhou Shen, Yingcheng Shi, Ziyi Yang","submitted_at":"2025-05-23T09:31:55Z","abstract_excerpt":"Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs to effectively process and reason on long-context inputs via RL remains a critical unsolved challenge. To bridge this gap, we first formalize the paradigm of long-context reasoning RL, and identify key challenges in suboptimal training efficiency and unstable optimization process. To address these issues, we propose QwenLong-L1, a framework that adapts short"},"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":"2505.17667","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"927c9063d321d8800162a3bc6ba3ed261c95a8500ab9e7c7b012326d34fbac50","abstract_canon_sha256":"1d3a94d26a9b9410bff57a39d3a8b9d75dcbb7152ba2c82230908bc7ddb6dc8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:09.454614Z","signature_b64":"LD+ekJTGFiIAydBYeFUt6/A1UW597yCxuD1n7wbacMjbrHcnBfA50ZKy8aPDfYeJDRKVrMsQ+RTqNDkhDEoTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed4244e73cbf598983907a4dd7e5f379db6f16259a093b1301cfebf73c4a5152","last_reissued_at":"2026-07-05T11:10:09.453980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:09.453980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenliang Li, Fanqi Wan, Fei Huang, Jingren Zhou, Ji Zhang, Ming Yan, Shengyi Liao, Weizhou Shen, Yingcheng Shi, Ziyi Yang","submitted_at":"2025-05-23T09:31:55Z","abstract_excerpt":"Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs to effectively process and reason on long-context inputs via RL remains a critical unsolved challenge. To bridge this gap, we first formalize the paradigm of long-context reasoning RL, and identify key challenges in suboptimal training efficiency and unstable optimization process. To address these issues, we propose QwenLong-L1, a framework that adapts short"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17667","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/2505.17667/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":"2505.17667","created_at":"2026-07-05T11:10:09.454064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17667v2","created_at":"2026-07-05T11:10:09.454064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17667","created_at":"2026-07-05T11:10:09.454064+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VBEJZZ4X5MY","created_at":"2026-07-05T11:10:09.454064+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VBEJZZ4X5MYTA4Q","created_at":"2026-07-05T11:10:09.454064+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VBEJZZ4","created_at":"2026-07-05T11:10:09.454064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02073","citing_title":"Evidence-State Rewards for Long-Context Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02259","citing_title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02371","citing_title":"Internalized Reasoning for Long-Context Visual Document Understanding","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12227","citing_title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06471","citing_title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04831","citing_title":"StoryAlign: Evaluating and Training Reward Models for Story Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07981","citing_title":"A Decomposition Perspective to Long-context Reasoning for LLMs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14922","citing_title":"LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17535","citing_title":"OPSDL: On-Policy Self-Distillation for Long-Context Language Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH","json":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH.json","graph_json":"https://pith.science/api/pith-number/5VBEJZZ4X5MYTA4QPJG5PZPTPH/graph.json","events_json":"https://pith.science/api/pith-number/5VBEJZZ4X5MYTA4QPJG5PZPTPH/events.json","paper":"https://pith.science/paper/5VBEJZZ4"},"agent_actions":{"view_html":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH","download_json":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH.json","view_paper":"https://pith.science/paper/5VBEJZZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17667&json=true","fetch_graph":"https://pith.science/api/pith-number/5VBEJZZ4X5MYTA4QPJG5PZPTPH/graph.json","fetch_events":"https://pith.science/api/pith-number/5VBEJZZ4X5MYTA4QPJG5PZPTPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH/action/storage_attestation","attest_author":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH/action/author_attestation","sign_citation":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH/action/citation_signature","submit_replication":"https://pith.science/pith/5VBEJZZ4X5MYTA4QPJG5PZPTPH/action/replication_record"}},"created_at":"2026-07-05T11:10:09.454064+00:00","updated_at":"2026-07-05T11:10:09.454064+00:00"}