{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:456F6KSNSL5OPDRJNF2JUICSJG","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":"1091f49d455e8fa9266f5d0db9892c0f60266819d6e1e9c60b09be25d9fc6116","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T01:00:34Z","title_canon_sha256":"84bbd61baf4c801fefadf5afb69be9ae3cd68892e8935ed3cd580a386dc81cbb"},"schema_version":"1.0","source":{"id":"2505.24098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24098","created_at":"2026-07-05T11:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24098v1","created_at":"2026-07-05T11:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24098","created_at":"2026-07-05T11:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"456F6KSNSL5O","created_at":"2026-07-05T11:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"456F6KSNSL5OPDRJ","created_at":"2026-07-05T11:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"456F6KSN","created_at":"2026-07-05T11:12:41Z"}],"graph_snapshots":[{"event_id":"sha256:f84b0280f7f130291cd8b3d07b1983b0798b9d41b3c93ea72407381667cea374","target":"graph","created_at":"2026-07-05T11:12:41Z","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/2505.24098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared wit","authors_text":"Aidan Zhang, Dejia Xu, Ivan Bercovich, Jiabao Ji, Junting Zhou, Kexun Zhang, Lei Li, Yee Man Choi, Zhongmou He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T01:00:34Z","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24098","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:bb820c1b80c1b10f3e2022cd1122b2bfad7816cda2104b3eb77cf21f7d663801","target":"record","created_at":"2026-07-05T11:12:41Z","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":"1091f49d455e8fa9266f5d0db9892c0f60266819d6e1e9c60b09be25d9fc6116","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T01:00:34Z","title_canon_sha256":"84bbd61baf4c801fefadf5afb69be9ae3cd68892e8935ed3cd580a386dc81cbb"},"schema_version":"1.0","source":{"id":"2505.24098","kind":"arxiv","version":1}},"canonical_sha256":"e77c5f2a4d92fae78e2969749a205249b6e6c8508c3068365b8faf8ba798a0c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e77c5f2a4d92fae78e2969749a205249b6e6c8508c3068365b8faf8ba798a0c1","first_computed_at":"2026-07-05T11:12:41.854207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:41.854207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EX00apbVWzaaxzut8ZGY9cIJUv3ldRiDznXlXgjBP770Sw1kjArNDYtr58NlE6Ir+Wiw1GY8w34SbSIWyGUNAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:41.854763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb820c1b80c1b10f3e2022cd1122b2bfad7816cda2104b3eb77cf21f7d663801","sha256:f84b0280f7f130291cd8b3d07b1983b0798b9d41b3c93ea72407381667cea374"],"state_sha256":"70b2e0b3097b7535a0d6de275512cd58fba404c9fdeeeeecd031729230d3d1d9"}