{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FONSV7EPIOK7UWM7KPJ6P5DERA","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":"6e805c56e91f6018132d536c9fb24198d9d5a7f5bd080871ce69a098a6f4d28b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:20:30Z","title_canon_sha256":"d41c58607d364ccb8b17824f92b9ff72989aa5fa2408132aca09a3580bba7535"},"schema_version":"1.0","source":{"id":"2305.14201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14201","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14201v1","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14201","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"FONSV7EPIOK7","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"FONSV7EPIOK7UWM7","created_at":"2026-07-05T06:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"FONSV7EP","created_at":"2026-07-05T06:13:01Z"}],"graph_snapshots":[{"event_id":"sha256:4c2bff62032177933369b14db40fe8a44bf47bc550be578202e5ca1fbcc74c3a","target":"graph","created_at":"2026-07-05T06:13:01Z","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/2305.14201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Goat, a fine-tuned LLaMA model that significantly outperforms GPT-4 on a range of arithmetic tasks. Fine-tuned on a synthetically generated dataset, Goat achieves state-of-the-art performance on BIG-bench arithmetic sub-task. In particular, the zero-shot Goat-7B matches or even surpasses the accuracy achieved by the few-shot PaLM-540B. Surprisingly, Goat can achieve near-perfect accuracy on large-number addition and subtraction through supervised fine-tuning only, which is almost impossible with previous pretrained language models, such as Bloom, OPT, GPT-NeoX, etc. We attribute G","authors_text":"Bryan Kian Hsiang Low, Tiedong Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:20:30Z","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14201","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":"sha256:9ea0cb4d3675932d47a33d82ffb17d5e37650671d304387cfeb44d3c20efca3a","target":"record","created_at":"2026-07-05T06:13:01Z","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":"6e805c56e91f6018132d536c9fb24198d9d5a7f5bd080871ce69a098a6f4d28b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:20:30Z","title_canon_sha256":"d41c58607d364ccb8b17824f92b9ff72989aa5fa2408132aca09a3580bba7535"},"schema_version":"1.0","source":{"id":"2305.14201","kind":"arxiv","version":1}},"canonical_sha256":"2b9b2afc8f4395fa599f53d3e7f46488199b6fbd1736ad7d284d54612a577d44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b9b2afc8f4395fa599f53d3e7f46488199b6fbd1736ad7d284d54612a577d44","first_computed_at":"2026-07-05T06:13:01.967610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:01.967610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lHM4UxOk3JRFCMNbQQfaFqzttZUwNLj2KUG8ykU7sr6aB+ytltnpjNrPaRF7rLkK5fe4XBNKIQuzdYEdK5yfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:01.968055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ea0cb4d3675932d47a33d82ffb17d5e37650671d304387cfeb44d3c20efca3a","sha256:4c2bff62032177933369b14db40fe8a44bf47bc550be578202e5ca1fbcc74c3a"],"state_sha256":"642392b2b0141ee2388d34a25d4731e55bfa0460aacc0a3fd6535427127dbc3b"}