{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AOZJ4KMLULKVUY6WUFPB7CJ4A2","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":"533ab721c982e7dcd399537c8fb5b9fa436c4a3f450b1b4cbe257e17503e391e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T17:55:36Z","title_canon_sha256":"343c909bc6387a3e7b7ade2224bf7cc7eb8e04d9a9222361ad233e92349c5d42"},"schema_version":"1.0","source":{"id":"2407.21009","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21009","created_at":"2026-07-05T10:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21009v4","created_at":"2026-07-05T10:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21009","created_at":"2026-07-05T10:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"AOZJ4KMLULKV","created_at":"2026-07-05T10:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"AOZJ4KMLULKVUY6W","created_at":"2026-07-05T10:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"AOZJ4KML","created_at":"2026-07-05T10:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:05feffcd144bfbbd4d822f5500e856ed655371a53359de3328d297928d26c03c","target":"graph","created_at":"2026-07-05T10:08:19Z","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/2407.21009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current LLM training positions mathematical reasoning as a core capability. With publicly available sources fully tapped, there is unmet demand for diverse and challenging math questions. Relying solely on human experts is both time-consuming and costly, while LLM-generated questions often lack the requisite diversity and difficulty. We present a design framework that combines the strengths of LLMs with a human-in-the-loop approach to generate a diverse array of challenging math questions. We leverage LLM metacognition skills [Didolkar et al., 2024] of a strong LLM to extract core \"skills\" fro","authors_text":"Anirudh Goyal, Dingli Yu, Jiatong Yu, Kaifeng Lyu, Michael Mozer, Nan Rosemary Ke, Sanjeev Arora, Simon Park, Vedant Shah, Yinghui He, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T17:55:36Z","title":"AI-Assisted Generation of Difficult Math Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21009","kind":"arxiv","version":4},"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":"sha256:591d9e0a15c1a7ec45649f2bad08454e0e27b7df511b7f94b8f24f2e9a1cf36b","target":"record","created_at":"2026-07-05T10:08:19Z","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":"533ab721c982e7dcd399537c8fb5b9fa436c4a3f450b1b4cbe257e17503e391e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T17:55:36Z","title_canon_sha256":"343c909bc6387a3e7b7ade2224bf7cc7eb8e04d9a9222361ad233e92349c5d42"},"schema_version":"1.0","source":{"id":"2407.21009","kind":"arxiv","version":4}},"canonical_sha256":"03b29e298ba2d55a63d6a15e1f893c0683b6cc32cbe4acfa784e6a6160d4ae61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03b29e298ba2d55a63d6a15e1f893c0683b6cc32cbe4acfa784e6a6160d4ae61","first_computed_at":"2026-07-05T10:08:19.786053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:19.786053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGRowunD4KQiaCBArV/003b2kiyE4c4DsuZUrIE7ZGlpRu1m3jCdHPrQ53YCdKVZco+75XF/Vr+VJ6uPvXvdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:19.786622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21009","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:591d9e0a15c1a7ec45649f2bad08454e0e27b7df511b7f94b8f24f2e9a1cf36b","sha256:05feffcd144bfbbd4d822f5500e856ed655371a53359de3328d297928d26c03c"],"state_sha256":"c684d07c70bff33bf3334c3339c03f1f9ceb73b9e1472b777739d723211d2057"}