{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CXF2UOE4ICSZ3NTYQT3OVSZHFN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d679b68550a6ee2cb74746a3c0ae0fcfd877c996218ed1cad16adf0c7ce1e14c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-02T16:25:30Z","title_canon_sha256":"06e333b56dcdce41646f771783e69423bec30827e63a22f03c765e532fb514df"},"schema_version":"1.0","source":{"id":"2404.02078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02078","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02078v1","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02078","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"CXF2UOE4ICSZ","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"CXF2UOE4ICSZ3NTY","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"CXF2UOE4","created_at":"2026-07-05T08:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:fbdcaf8a36903005a74a668830ddb1a4fbff745901fd63083272b60f7e04b595","target":"graph","created_at":"2026-07-05T08:03:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.02078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-02T16:25:30Z","title":"Advancing LLM Reasoning Generalists with Preference Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02078","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c50906fa7ebc93f5f9196794273ec0a7f57a02ac817532e7efbb16fcac29ead","target":"record","created_at":"2026-07-05T08:03:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d679b68550a6ee2cb74746a3c0ae0fcfd877c996218ed1cad16adf0c7ce1e14c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-02T16:25:30Z","title_canon_sha256":"06e333b56dcdce41646f771783e69423bec30827e63a22f03c765e532fb514df"},"schema_version":"1.0","source":{"id":"2404.02078","kind":"arxiv","version":1}},"canonical_sha256":"15cbaa389c40a59db67884f6eacb272b7a720a3074bc4a53d4405e23e47c127c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15cbaa389c40a59db67884f6eacb272b7a720a3074bc4a53d4405e23e47c127c","first_computed_at":"2026-07-05T08:03:35.635441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:35.635441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/jy7g2qoYS7CrZcuXAvBUb0g/d/ntaA/9fiUTzhpZR3z31n0DBSUzxyxl4RtQe656Gz3CY/V8xPReWq6o+igBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:35.635934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c50906fa7ebc93f5f9196794273ec0a7f57a02ac817532e7efbb16fcac29ead","sha256:fbdcaf8a36903005a74a668830ddb1a4fbff745901fd63083272b60f7e04b595"],"state_sha256":"7abc7464107fd301a72bbf0cd716db31af1ea1d9f3b1daebda30e15d2f8c3fed"}