{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6HJIVK6VETFLOS3PLOG75AIKBJ","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":"df51dd7d8e684a6b5e26e3e4b83f66f6f02229068ad628f29ee55f659e2cb74d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.PL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2020-06-13T21:09:23Z","title_canon_sha256":"d8cdc7392146e3e96d8927373332e19e88b4ff2fbc82cb91af638cebd31e2957"},"schema_version":"1.0","source":{"id":"2006.09265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09265","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09265v2","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09265","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"pith_short_12","alias_value":"6HJIVK6VETFL","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"6HJIVK6VETFLOS3P","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"6HJIVK6V","created_at":"2026-07-05T02:26:00Z"}],"graph_snapshots":[{"event_id":"sha256:c7e79d28a8502ddac17f39547f5a44c34fe5fcf060e1bc169c6da7a08aafd8ec","target":"graph","created_at":"2026-07-05T02:26:00Z","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/2006.09265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lawrence C. Paulson, Lei Yu, Wenda Li, Yuhuai Wu","cross_cats":["cs.AI","cs.CL","cs.LG","cs.PL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2020-06-13T21:09:23Z","title":"IsarStep: a Benchmark for High-level Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09265","kind":"arxiv","version":2},"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:e762e95a3f88f60b0e9fa6282f1170894e95c4ae4eab8e88035ebff4b8ca1329","target":"record","created_at":"2026-07-05T02:26:00Z","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":"df51dd7d8e684a6b5e26e3e4b83f66f6f02229068ad628f29ee55f659e2cb74d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.PL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2020-06-13T21:09:23Z","title_canon_sha256":"d8cdc7392146e3e96d8927373332e19e88b4ff2fbc82cb91af638cebd31e2957"},"schema_version":"1.0","source":{"id":"2006.09265","kind":"arxiv","version":2}},"canonical_sha256":"f1d28aabd524cab74b6f5b8dfe810a0a58dc7ec1dd5b82ed0b3615116e35f759","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d28aabd524cab74b6f5b8dfe810a0a58dc7ec1dd5b82ed0b3615116e35f759","first_computed_at":"2026-07-05T02:26:00.209691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:00.209691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"omdhIpXOcJOmj2OZLomfB26mUssajknTk7e+Ji+JVtOxOMQIlFBGzGN/gUq5lh1QqqtOirx+hHkB+sywCTTjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:00.210194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e762e95a3f88f60b0e9fa6282f1170894e95c4ae4eab8e88035ebff4b8ca1329","sha256:c7e79d28a8502ddac17f39547f5a44c34fe5fcf060e1bc169c6da7a08aafd8ec"],"state_sha256":"6b95861a48763a2ca413057035b10161e52ee9cf3116f31b8f573d0abe20ec47"}