{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YKXUJOTDTYHYI6H6ODHQARX5PE","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":"9d68883ef58c08318c52870944a04c19e8934cbf36e88a70e86728d06b22f019","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:55:06Z","title_canon_sha256":"93f00146825d16300a8e49a81e752ec99d14af185f4ee98ddadc87cbcde1a3ff"},"schema_version":"1.0","source":{"id":"2607.18260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18260","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18260v1","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18260","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"YKXUJOTDTYHY","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"YKXUJOTDTYHYI6H6","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"YKXUJOTD","created_at":"2026-07-22T00:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:a9ea18ae24572b8d5a6c52734b673755eab6c0cfef07db1df59794a2a31fe7f9","target":"graph","created_at":"2026-07-22T00:22:39Z","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/2607.18260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce FindStatBench, an execution benchmark for evaluating large language models on combinatorial code synthesis. Built from FindStat, it contains 2,329 tasks across 24 collections and 5.52M hidden instances, covering statistic synthesis, which maps objects to integers, and map synthesis, which maps objects to objects. Each task gives a mathematical description and at most five public input-output examples; a model must emit one Python solve function with no retrieval, tool use, execution feedback, voting, or reranking. Submissions are scored by exact sandboxed execution on held-out com","authors_text":"Soham Dan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:55:06Z","title":"FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18260","kind":"arxiv","version":1},"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:c52366522fe3db7b037034abea31aa6d1598b2497277dd12b6c23ef9d55d299c","target":"record","created_at":"2026-07-22T00:22:39Z","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":"9d68883ef58c08318c52870944a04c19e8934cbf36e88a70e86728d06b22f019","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T02:55:06Z","title_canon_sha256":"93f00146825d16300a8e49a81e752ec99d14af185f4ee98ddadc87cbcde1a3ff"},"schema_version":"1.0","source":{"id":"2607.18260","kind":"arxiv","version":1}},"canonical_sha256":"c2af44ba639e0f8478fe70cf0046fd792d37156efde3fbc200f75666bed29c74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2af44ba639e0f8478fe70cf0046fd792d37156efde3fbc200f75666bed29c74","first_computed_at":"2026-07-22T00:22:39.051621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:39.051621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x8ahveC/lmPpmWMZGHKSBpbcpnprIrmuKgSS7QwKO4WQaI3Yq/M5di0r7XZqssIAwozE/n7SMjVWoqjozP0PDA==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:39.052513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c52366522fe3db7b037034abea31aa6d1598b2497277dd12b6c23ef9d55d299c","sha256:a9ea18ae24572b8d5a6c52734b673755eab6c0cfef07db1df59794a2a31fe7f9"],"state_sha256":"291e7d4ef147d8ec6dc03ff4c954747a26762330527090f7a856f6b7a9f3ff86"}