{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZSAUSYXJMYX6XGIFZKQ47RAETC","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":"f363462ff70e141480636bccdeb7347c9cf542b23ee8e5b9a245cc7fdcb3a422","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T08:30:37Z","title_canon_sha256":"7a5271cb14b83b0df971b770c70d8b87d7d40f2f7a2c04178b6564582724a7b6"},"schema_version":"1.0","source":{"id":"2406.02100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02100","created_at":"2026-07-05T08:27:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02100v1","created_at":"2026-07-05T08:27:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02100","created_at":"2026-07-05T08:27:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZSAUSYXJMYX6","created_at":"2026-07-05T08:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZSAUSYXJMYX6XGIF","created_at":"2026-07-05T08:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZSAUSYXJ","created_at":"2026-07-05T08:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:1e35aa0f74e3c7f4c43be8da397a3761d23f38744ebdd1468bbad7dc51f465bb","target":"graph","created_at":"2026-07-05T08:27:14Z","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/2406.02100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown excellent performance in language understanding, text generation, code synthesis, and many other tasks, while they still struggle in complex multi-step reasoning problems, such as mathematical reasoning. In this paper, through a newly proposed arithmetical puzzle problem, we show that the model can perform well on multi-step reasoning tasks via fine-tuning on high-quality synthetic data. Experimental results with the open-llama-3B model on three different test datasets show that not only the model can reach a zero-shot pass@1 at 0.44 on the in-domain dat","authors_text":"Chen Ye, Haolong Li, Jie Chen, Yinqi Zhang, Yu Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T08:30:37Z","title":"Exploring Mathematical Extrapolation of Large Language Models with Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02100","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":"sha256:380c3f970cda8cd415948490ba6f0bfa3b0ac20f17fc7fd97bf5ed447098c33b","target":"record","created_at":"2026-07-05T08:27:14Z","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":"f363462ff70e141480636bccdeb7347c9cf542b23ee8e5b9a245cc7fdcb3a422","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T08:30:37Z","title_canon_sha256":"7a5271cb14b83b0df971b770c70d8b87d7d40f2f7a2c04178b6564582724a7b6"},"schema_version":"1.0","source":{"id":"2406.02100","kind":"arxiv","version":1}},"canonical_sha256":"cc814962e9662feb9905caa1cfc40498b887c337fd6eec07d610396140a362cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc814962e9662feb9905caa1cfc40498b887c337fd6eec07d610396140a362cc","first_computed_at":"2026-07-05T08:27:14.674074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:14.674074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kvyJsry1u3m0ZCqbmvdUUM+naIQQw656KJk0OEIhHvdOibZu5uQMxk2fafc4dIHgOoHvbigR7avcBEuOn85ABg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:14.674482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:380c3f970cda8cd415948490ba6f0bfa3b0ac20f17fc7fd97bf5ed447098c33b","sha256:1e35aa0f74e3c7f4c43be8da397a3761d23f38744ebdd1468bbad7dc51f465bb"],"state_sha256":"6eec5d0ef036b4338f53f737e0a1943570e9f61a83ec660ce0f02434a2c7f235"}