{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V27JMQSD7PWO2J5RFKFQ75LP7T","short_pith_number":"pith:V27JMQSD","schema_version":"1.0","canonical_sha256":"aebe964243fbeced27b12a8b0ff56ffcf4da7e5ac090a8094f776525329c3d8e","source":{"kind":"arxiv","id":"2410.09671","version":1},"attestation_state":"computed","paper":{"title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anjie Liu, Jiachen Zhu, Jun Wang, Lei Chen, Linyi Yang, Lionel M. Ni, Meng Fang, Muning Wen, Weinan Zhang, Yan Song, Ying Wen, Ziqin Gong, Ziyu Wan","submitted_at":"2024-10-12T23:42:16Z","abstract_excerpt":"In this technical report, we introduce OpenR, an open-source framework designed to integrate key components for enhancing the reasoning capabilities of large language models (LLMs). OpenR unifies data acquisition, reinforcement learning training (both online and offline), and non-autoregressive decoding into a cohesive software platform. Our goal is to establish an open-source platform and community to accelerate the development of LLM reasoning. Inspired by the success of OpenAI's o1 model, which demonstrated improved reasoning abilities through step-by-step reasoning and reinforcement learni"},"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":"2410.09671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-12T23:42:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b596df0d01c79be3f42453b59e77880ead160af9661045f997365d948394a761","abstract_canon_sha256":"55e9b31bd451c6866f7e364df9b70612d8db5610dfaaeb2530d8dcfd688f2b79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:42.394235Z","signature_b64":"SHu7vJKMtAt/nr7e0Sw3uo3ifF2PhFqYPwnIzvToFvLJ7brgs6nWbO060XgY5KhK8ob2hmwdiijjopap24KsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aebe964243fbeced27b12a8b0ff56ffcf4da7e5ac090a8094f776525329c3d8e","last_reissued_at":"2026-07-05T09:19:42.393615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:42.393615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anjie Liu, Jiachen Zhu, Jun Wang, Lei Chen, Linyi Yang, Lionel M. Ni, Meng Fang, Muning Wen, Weinan Zhang, Yan Song, Ying Wen, Ziqin Gong, Ziyu Wan","submitted_at":"2024-10-12T23:42:16Z","abstract_excerpt":"In this technical report, we introduce OpenR, an open-source framework designed to integrate key components for enhancing the reasoning capabilities of large language models (LLMs). OpenR unifies data acquisition, reinforcement learning training (both online and offline), and non-autoregressive decoding into a cohesive software platform. Our goal is to establish an open-source platform and community to accelerate the development of LLM reasoning. Inspired by the success of OpenAI's o1 model, which demonstrated improved reasoning abilities through step-by-step reasoning and reinforcement learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09671","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/2410.09671/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":"2410.09671","created_at":"2026-07-05T09:19:42.393677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09671v1","created_at":"2026-07-05T09:19:42.393677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09671","created_at":"2026-07-05T09:19:42.393677+00:00"},{"alias_kind":"pith_short_12","alias_value":"V27JMQSD7PWO","created_at":"2026-07-05T09:19:42.393677+00:00"},{"alias_kind":"pith_short_16","alias_value":"V27JMQSD7PWO2J5R","created_at":"2026-07-05T09:19:42.393677+00:00"},{"alias_kind":"pith_short_8","alias_value":"V27JMQSD","created_at":"2026-07-05T09:19:42.393677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09932","citing_title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30898","citing_title":"UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15721","citing_title":"Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15529","citing_title":"Process Rewards with Learned Reliability","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10195","citing_title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10195","citing_title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07851","citing_title":"ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17957","citing_title":"Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T","json":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T.json","graph_json":"https://pith.science/api/pith-number/V27JMQSD7PWO2J5RFKFQ75LP7T/graph.json","events_json":"https://pith.science/api/pith-number/V27JMQSD7PWO2J5RFKFQ75LP7T/events.json","paper":"https://pith.science/paper/V27JMQSD"},"agent_actions":{"view_html":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T","download_json":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T.json","view_paper":"https://pith.science/paper/V27JMQSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09671&json=true","fetch_graph":"https://pith.science/api/pith-number/V27JMQSD7PWO2J5RFKFQ75LP7T/graph.json","fetch_events":"https://pith.science/api/pith-number/V27JMQSD7PWO2J5RFKFQ75LP7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T/action/storage_attestation","attest_author":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T/action/author_attestation","sign_citation":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T/action/citation_signature","submit_replication":"https://pith.science/pith/V27JMQSD7PWO2J5RFKFQ75LP7T/action/replication_record"}},"created_at":"2026-07-05T09:19:42.393677+00:00","updated_at":"2026-07-05T09:19:42.393677+00:00"}