{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CXF2UOE4ICSZ3NTYQT3OVSZHFN","short_pith_number":"pith:CXF2UOE4","schema_version":"1.0","canonical_sha256":"15cbaa389c40a59db67884f6eacb272b7a720a3074bc4a53d4405e23e47c127c","source":{"kind":"arxiv","id":"2404.02078","version":1},"attestation_state":"computed","paper":{"title":"Advancing LLM Reasoning Generalists with Preference Trees","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Boji Shan, Bowen Zhou, Ganqu Cui, Hanbin Wang, Hao Peng, Huimin Chen, Jia Deng, Lifan Yuan, Maosong Sun, Ning Ding, Ruobing Xie, Xingyao Wang, Yankai Lin, Zhenghao Liu, Zhiyuan Liu","submitted_at":"2024-04-02T16:25:30Z","abstract_excerpt":"We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Finetuned from Mistral-7B and CodeLlama-70B, Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks covering mathematics, code generation, and logical reasoning problems. Notably, Eurus-70B beats GPT-3.5 Turbo in reasoning through a comprehensive benchmarking across 12 tests covering five tasks, and achieves a 33.3% pass@1 accuracy on LeetCode and 32.6% on TheoremQA, two challenging benchmarks, substantially outperforming existing open-source models by margins mor"},"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":"2404.02078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-02T16:25:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"06e333b56dcdce41646f771783e69423bec30827e63a22f03c765e532fb514df","abstract_canon_sha256":"d679b68550a6ee2cb74746a3c0ae0fcfd877c996218ed1cad16adf0c7ce1e14c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:35.635934Z","signature_b64":"/jy7g2qoYS7CrZcuXAvBUb0g/d/ntaA/9fiUTzhpZR3z31n0DBSUzxyxl4RtQe656Gz3CY/V8xPReWq6o+igBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15cbaa389c40a59db67884f6eacb272b7a720a3074bc4a53d4405e23e47c127c","last_reissued_at":"2026-07-05T08:03:35.635441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:35.635441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing LLM Reasoning Generalists with Preference Trees","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Boji Shan, Bowen Zhou, Ganqu Cui, Hanbin Wang, Hao Peng, Huimin Chen, Jia Deng, Lifan Yuan, Maosong Sun, Ning Ding, Ruobing Xie, Xingyao Wang, Yankai Lin, Zhenghao Liu, Zhiyuan Liu","submitted_at":"2024-04-02T16:25:30Z","abstract_excerpt":"We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Finetuned from Mistral-7B and CodeLlama-70B, Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks covering mathematics, code generation, and logical reasoning problems. Notably, Eurus-70B beats GPT-3.5 Turbo in reasoning through a comprehensive benchmarking across 12 tests covering five tasks, and achieves a 33.3% pass@1 accuracy on LeetCode and 32.6% on TheoremQA, two challenging benchmarks, substantially outperforming existing open-source models by margins mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02078","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/2404.02078/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":"2404.02078","created_at":"2026-07-05T08:03:35.635497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02078v1","created_at":"2026-07-05T08:03:35.635497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02078","created_at":"2026-07-05T08:03:35.635497+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXF2UOE4ICSZ","created_at":"2026-07-05T08:03:35.635497+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXF2UOE4ICSZ3NTY","created_at":"2026-07-05T08:03:35.635497+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXF2UOE4","created_at":"2026-07-05T08:03:35.635497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11634","citing_title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10528","citing_title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05434","citing_title":"Selective-Advantage Entropy-Adaptive Horizon GRPO: Asymmetric Token-Level Discounting for Efficient Reinforcement Learning of Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12058","citing_title":"Holder Policy Optimisation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.21139","citing_title":"Training Software Engineering Agents and Verifiers with SWE-Gym","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.24235","citing_title":"PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2410.18451","citing_title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","ref_index":25,"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":66,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02737","citing_title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12058","citing_title":"Holder Policy Optimisation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21776","citing_title":"Video-R1: Reinforcing Video Reasoning in MLLMs","ref_index":42,"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":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12312","citing_title":"CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN","json":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN.json","graph_json":"https://pith.science/api/pith-number/CXF2UOE4ICSZ3NTYQT3OVSZHFN/graph.json","events_json":"https://pith.science/api/pith-number/CXF2UOE4ICSZ3NTYQT3OVSZHFN/events.json","paper":"https://pith.science/paper/CXF2UOE4"},"agent_actions":{"view_html":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN","download_json":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN.json","view_paper":"https://pith.science/paper/CXF2UOE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02078&json=true","fetch_graph":"https://pith.science/api/pith-number/CXF2UOE4ICSZ3NTYQT3OVSZHFN/graph.json","fetch_events":"https://pith.science/api/pith-number/CXF2UOE4ICSZ3NTYQT3OVSZHFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN/action/storage_attestation","attest_author":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN/action/author_attestation","sign_citation":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN/action/citation_signature","submit_replication":"https://pith.science/pith/CXF2UOE4ICSZ3NTYQT3OVSZHFN/action/replication_record"}},"created_at":"2026-07-05T08:03:35.635497+00:00","updated_at":"2026-07-05T08:03:35.635497+00:00"}