{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GSE6ZYYPR5AGNUFKNUBNAKKWHG","short_pith_number":"pith:GSE6ZYYP","schema_version":"1.0","canonical_sha256":"3489ece30f8f4066d0aa6d02d0295639b3d151178c052845f2b77a8593419d12","source":{"kind":"arxiv","id":"2606.02588","version":1},"attestation_state":"computed","paper":{"title":"Lean-GAP: A Dataset of Formalized Graduate Algebra Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LO","authors_text":"Byung-Hak Hwang, Chul-hee Lee, Hyojae Lim, Hyukpyo Hong, Hyungryul Baik, Ilkyoo Choi, Jaeseong Heo, Jihoon Hyun, Jineon Baek, Keewoo Lee, Kyu-Hwan Lee, Seewoo Lee, Yeachan Park","submitted_at":"2026-05-20T08:15:43Z","abstract_excerpt":"We present Lean-GAP (Lean-Graduate Agebra Problems), 430 formalized graduate-level algebra problems from the textbook Abstract Algebra by Dummit and Foote. We develop a scalable pipeline consisting of PDF-to-LaTeX preprocessing, autoformalization into Lean 4, and verification of informal-formal correspondence. While the preprocessing and autoformalization stages can be largely automated, we find that verification remains the most subtle and labor-intensive component, requiring careful human oversight. Our contributions include (i) the construction of a structured dataset of formalized exercise"},"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":"2606.02588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2026-05-20T08:15:43Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"520dd7c4b7fb7661051aa6b54032cf4858359858e6eda2537248403b892bafb9","abstract_canon_sha256":"7abd06df0de208bb45bffc467ee5667a2eae064fdaaa4d2e87694a308f27436d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T00:05:03.946870Z","signature_b64":"sUG4C4SjFA9oBo1w8p34PxU6zE0hYQ570aflZg9eC/sRVOEBLNtsK3Kp/fyPOUzDTXK0yF4nSBdNunweH2y0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3489ece30f8f4066d0aa6d02d0295639b3d151178c052845f2b77a8593419d12","last_reissued_at":"2026-06-03T00:05:03.946369Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T00:05:03.946369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lean-GAP: A Dataset of Formalized Graduate Algebra Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LO","authors_text":"Byung-Hak Hwang, Chul-hee Lee, Hyojae Lim, Hyukpyo Hong, Hyungryul Baik, Ilkyoo Choi, Jaeseong Heo, Jihoon Hyun, Jineon Baek, Keewoo Lee, Kyu-Hwan Lee, Seewoo Lee, Yeachan Park","submitted_at":"2026-05-20T08:15:43Z","abstract_excerpt":"We present Lean-GAP (Lean-Graduate Agebra Problems), 430 formalized graduate-level algebra problems from the textbook Abstract Algebra by Dummit and Foote. We develop a scalable pipeline consisting of PDF-to-LaTeX preprocessing, autoformalization into Lean 4, and verification of informal-formal correspondence. While the preprocessing and autoformalization stages can be largely automated, we find that verification remains the most subtle and labor-intensive component, requiring careful human oversight. Our contributions include (i) the construction of a structured dataset of formalized exercise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02588","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/2606.02588/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":"2606.02588","created_at":"2026-06-03T00:05:03.946430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02588v1","created_at":"2026-06-03T00:05:03.946430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02588","created_at":"2026-06-03T00:05:03.946430+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSE6ZYYPR5AG","created_at":"2026-06-03T00:05:03.946430+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSE6ZYYPR5AGNUFK","created_at":"2026-06-03T00:05:03.946430+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSE6ZYYP","created_at":"2026-06-03T00:05:03.946430+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/GSE6ZYYPR5AGNUFKNUBNAKKWHG","json":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG.json","graph_json":"https://pith.science/api/pith-number/GSE6ZYYPR5AGNUFKNUBNAKKWHG/graph.json","events_json":"https://pith.science/api/pith-number/GSE6ZYYPR5AGNUFKNUBNAKKWHG/events.json","paper":"https://pith.science/paper/GSE6ZYYP"},"agent_actions":{"view_html":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG","download_json":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG.json","view_paper":"https://pith.science/paper/GSE6ZYYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02588&json=true","fetch_graph":"https://pith.science/api/pith-number/GSE6ZYYPR5AGNUFKNUBNAKKWHG/graph.json","fetch_events":"https://pith.science/api/pith-number/GSE6ZYYPR5AGNUFKNUBNAKKWHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG/action/storage_attestation","attest_author":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG/action/author_attestation","sign_citation":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG/action/citation_signature","submit_replication":"https://pith.science/pith/GSE6ZYYPR5AGNUFKNUBNAKKWHG/action/replication_record"}},"created_at":"2026-06-03T00:05:03.946430+00:00","updated_at":"2026-06-03T00:05:03.946430+00:00"}