{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6HJIVK6VETFLOS3PLOG75AIKBJ","short_pith_number":"pith:6HJIVK6V","schema_version":"1.0","canonical_sha256":"f1d28aabd524cab74b6f5b8dfe810a0a58dc7ec1dd5b82ed0b3615116e35f759","source":{"kind":"arxiv","id":"2006.09265","version":2},"attestation_state":"computed","paper":{"title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.PL","stat.ML"],"primary_cat":"cs.LO","authors_text":"Lawrence C. Paulson, Lei Yu, Wenda Li, Yuhuai Wu","submitted_at":"2020-06-13T21:09:23Z","abstract_excerpt":"A well-defined benchmark is essential for measuring and accelerating research progress of machine learning models. In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models. We build a non-synthetic dataset from the largest repository of proofs written by human experts in a theorem prover. The dataset has a broad coverage of undergraduate and research-level mathematical and computer science theorems. In our defined task, a model is required to fill in a missing intermediate proposition given surroundin"},"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":"2006.09265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2020-06-13T21:09:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.PL","stat.ML"],"title_canon_sha256":"d8cdc7392146e3e96d8927373332e19e88b4ff2fbc82cb91af638cebd31e2957","abstract_canon_sha256":"df51dd7d8e684a6b5e26e3e4b83f66f6f02229068ad628f29ee55f659e2cb74d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:00.210194Z","signature_b64":"omdhIpXOcJOmj2OZLomfB26mUssajknTk7e+Ji+JVtOxOMQIlFBGzGN/gUq5lh1QqqtOirx+hHkB+sywCTTjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d28aabd524cab74b6f5b8dfe810a0a58dc7ec1dd5b82ed0b3615116e35f759","last_reissued_at":"2026-07-05T02:26:00.209691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:00.209691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.PL","stat.ML"],"primary_cat":"cs.LO","authors_text":"Lawrence C. Paulson, Lei Yu, Wenda Li, Yuhuai Wu","submitted_at":"2020-06-13T21:09:23Z","abstract_excerpt":"A well-defined benchmark is essential for measuring and accelerating research progress of machine learning models. In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models. We build a non-synthetic dataset from the largest repository of proofs written by human experts in a theorem prover. The dataset has a broad coverage of undergraduate and research-level mathematical and computer science theorems. In our defined task, a model is required to fill in a missing intermediate proposition given surroundin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09265","kind":"arxiv","version":2},"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/2006.09265/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":"2006.09265","created_at":"2026-07-05T02:26:00.209754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09265v2","created_at":"2026-07-05T02:26:00.209754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09265","created_at":"2026-07-05T02:26:00.209754+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HJIVK6VETFL","created_at":"2026-07-05T02:26:00.209754+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HJIVK6VETFLOS3P","created_at":"2026-07-05T02:26:00.209754+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HJIVK6V","created_at":"2026-07-05T02:26:00.209754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18098","citing_title":"IsabeLLM: Automated Theorem Proving Applied to Formally Verifying Consensus","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25155","citing_title":"Rethinking Wireless Communications through Formal Mathematical AI Reasoning","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ","json":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ.json","graph_json":"https://pith.science/api/pith-number/6HJIVK6VETFLOS3PLOG75AIKBJ/graph.json","events_json":"https://pith.science/api/pith-number/6HJIVK6VETFLOS3PLOG75AIKBJ/events.json","paper":"https://pith.science/paper/6HJIVK6V"},"agent_actions":{"view_html":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ","download_json":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ.json","view_paper":"https://pith.science/paper/6HJIVK6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09265&json=true","fetch_graph":"https://pith.science/api/pith-number/6HJIVK6VETFLOS3PLOG75AIKBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6HJIVK6VETFLOS3PLOG75AIKBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ/action/storage_attestation","attest_author":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ/action/author_attestation","sign_citation":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ/action/citation_signature","submit_replication":"https://pith.science/pith/6HJIVK6VETFLOS3PLOG75AIKBJ/action/replication_record"}},"created_at":"2026-07-05T02:26:00.209754+00:00","updated_at":"2026-07-05T02:26:00.209754+00:00"}