{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:662WEKGVOMNVXXRV3DXT54XNS3","short_pith_number":"pith:662WEKGV","schema_version":"1.0","canonical_sha256":"f7b56228d5731b5bde35d8ef3ef2ed96e22d7d8de273daa6f1e3ba8d416c5f73","source":{"kind":"arxiv","id":"2406.06555","version":1},"attestation_state":"computed","paper":{"title":"An Evaluation Benchmark for Autoformalization in Lean4","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.LG","authors_text":"Aryan Gulati, Brando Miranda, Devanshu Ladsaria, Jasdeep Sidhu, Shubhra Mishra","submitted_at":"2024-06-01T07:06:57Z","abstract_excerpt":"Large Language Models (LLMs) hold the potential to revolutionize autoformalization. The introduction of Lean4, a mathematical programming language, presents an unprecedented opportunity to rigorously assess the autoformalization capabilities of LLMs. This paper introduces a novel evaluation benchmark designed for Lean4, applying it to test the abilities of state-of-the-art LLMs, including GPT-3.5, GPT-4, and Gemini Pro. Our comprehensive analysis reveals that, despite recent advancements, these LLMs still exhibit limitations in autoformalization, particularly in more complex areas of mathemati"},"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":"2406.06555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T07:06:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.PL"],"title_canon_sha256":"46e39aa9c4a890055e2c52ce3da1271871c1f3f8ba4d42b5a4fbd04195a494d0","abstract_canon_sha256":"a3c38d355ed63b7f654d112388b63bdf5001a466e6309b01a7b3cd3441169dac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:47.188189Z","signature_b64":"aonEVm5zs7m8grhIBUaY5cmmDWCZ0YMrpKTxpgdwHau4cKEwiXuGloG2kvbOt5vkHmJXxw141ylL0KLBuETkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7b56228d5731b5bde35d8ef3ef2ed96e22d7d8de273daa6f1e3ba8d416c5f73","last_reissued_at":"2026-07-05T08:29:47.187718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:47.187718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Evaluation Benchmark for Autoformalization in Lean4","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.LG","authors_text":"Aryan Gulati, Brando Miranda, Devanshu Ladsaria, Jasdeep Sidhu, Shubhra Mishra","submitted_at":"2024-06-01T07:06:57Z","abstract_excerpt":"Large Language Models (LLMs) hold the potential to revolutionize autoformalization. The introduction of Lean4, a mathematical programming language, presents an unprecedented opportunity to rigorously assess the autoformalization capabilities of LLMs. This paper introduces a novel evaluation benchmark designed for Lean4, applying it to test the abilities of state-of-the-art LLMs, including GPT-3.5, GPT-4, and Gemini Pro. Our comprehensive analysis reveals that, despite recent advancements, these LLMs still exhibit limitations in autoformalization, particularly in more complex areas of mathemati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06555","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/2406.06555/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":"2406.06555","created_at":"2026-07-05T08:29:47.187774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06555v1","created_at":"2026-07-05T08:29:47.187774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06555","created_at":"2026-07-05T08:29:47.187774+00:00"},{"alias_kind":"pith_short_12","alias_value":"662WEKGVOMNV","created_at":"2026-07-05T08:29:47.187774+00:00"},{"alias_kind":"pith_short_16","alias_value":"662WEKGVOMNVXXRV","created_at":"2026-07-05T08:29:47.187774+00:00"},{"alias_kind":"pith_short_8","alias_value":"662WEKGV","created_at":"2026-07-05T08:29:47.187774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3","json":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3.json","graph_json":"https://pith.science/api/pith-number/662WEKGVOMNVXXRV3DXT54XNS3/graph.json","events_json":"https://pith.science/api/pith-number/662WEKGVOMNVXXRV3DXT54XNS3/events.json","paper":"https://pith.science/paper/662WEKGV"},"agent_actions":{"view_html":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3","download_json":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3.json","view_paper":"https://pith.science/paper/662WEKGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06555&json=true","fetch_graph":"https://pith.science/api/pith-number/662WEKGVOMNVXXRV3DXT54XNS3/graph.json","fetch_events":"https://pith.science/api/pith-number/662WEKGVOMNVXXRV3DXT54XNS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3/action/storage_attestation","attest_author":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3/action/author_attestation","sign_citation":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3/action/citation_signature","submit_replication":"https://pith.science/pith/662WEKGVOMNVXXRV3DXT54XNS3/action/replication_record"}},"created_at":"2026-07-05T08:29:47.187774+00:00","updated_at":"2026-07-05T08:29:47.187774+00:00"}