{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:456F6KSNSL5OPDRJNF2JUICSJG","short_pith_number":"pith:456F6KSN","canonical_record":{"source":{"id":"2505.24098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T01:00:34Z","cross_cats_sorted":[],"title_canon_sha256":"84bbd61baf4c801fefadf5afb69be9ae3cd68892e8935ed3cd580a386dc81cbb","abstract_canon_sha256":"1091f49d455e8fa9266f5d0db9892c0f60266819d6e1e9c60b09be25d9fc6116"},"schema_version":"1.0"},"canonical_sha256":"e77c5f2a4d92fae78e2969749a205249b6e6c8508c3068365b8faf8ba798a0c1","source":{"kind":"arxiv","id":"2505.24098","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:456F6KSNSL5OPDRJNF2JUICSJG","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T01:00:34Z","cross_cats_sorted":[],"title_canon_sha256":"84bbd61baf4c801fefadf5afb69be9ae3cd68892e8935ed3cd580a386dc81cbb","abstract_canon_sha256":"1091f49d455e8fa9266f5d0db9892c0f60266819d6e1e9c60b09be25d9fc6116"},"schema_version":"1.0"},"canonical_sha256":"e77c5f2a4d92fae78e2969749a205249b6e6c8508c3068365b8faf8ba798a0c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:41.854763Z","signature_b64":"EX00apbVWzaaxzut8ZGY9cIJUv3ldRiDznXlXgjBP770Sw1kjArNDYtr58NlE6Ir+Wiw1GY8w34SbSIWyGUNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e77c5f2a4d92fae78e2969749a205249b6e6c8508c3068365b8faf8ba798a0c1","last_reissued_at":"2026-07-05T11:12:41.854207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:41.854207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24098","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cPHPNBUJYuts5bmEd9WKalhFrg06m1jl8dx0smh3yBOEJBv8SrRGFSrySeHjJw8bxKnRa1LtOzshBLOT0uwpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:53:42.135784Z"},"content_sha256":"bb820c1b80c1b10f3e2022cd1122b2bfad7816cda2104b3eb77cf21f7d663801","schema_version":"1.0","event_id":"sha256:bb820c1b80c1b10f3e2022cd1122b2bfad7816cda2104b3eb77cf21f7d663801"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:456F6KSNSL5OPDRJNF2JUICSJG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aidan Zhang, Dejia Xu, Ivan Bercovich, Jiabao Ji, Junting Zhou, Kexun Zhang, Lei Li, Yee Man Choi, Zhongmou He","submitted_at":"2025-05-30T01:00:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24098","kind":"arxiv","version":1},"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/2505.24098/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E/8wZAmWVrmisfEFro48W43cCjYB4T4UT9Knbna5uZ717HJKTK2t+FhIwgmcyvHQ7IgvIMIZ1aI4Cgsy58EuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:53:42.136703Z"},"content_sha256":"f84b0280f7f130291cd8b3d07b1983b0798b9d41b3c93ea72407381667cea374","schema_version":"1.0","event_id":"sha256:f84b0280f7f130291cd8b3d07b1983b0798b9d41b3c93ea72407381667cea374"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/456F6KSNSL5OPDRJNF2JUICSJG/bundle.json","state_url":"https://pith.science/pith/456F6KSNSL5OPDRJNF2JUICSJG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/456F6KSNSL5OPDRJNF2JUICSJG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:53:42Z","links":{"resolver":"https://pith.science/pith/456F6KSNSL5OPDRJNF2JUICSJG","bundle":"https://pith.science/pith/456F6KSNSL5OPDRJNF2JUICSJG/bundle.json","state":"https://pith.science/pith/456F6KSNSL5OPDRJNF2JUICSJG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/456F6KSNSL5OPDRJNF2JUICSJG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1pCyV4NU8LtJ8bRErqJ7NLZA78lJpNeNn1i1QLxwKEkv7gEz12q7xUEsYxdqXTenfoWRgwW0msLnvIi/7fmQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:53:42.147959Z","bundle_sha256":"800f39909cf56bfa6c72ba9509667bfa723ce01c7176d6494bb1b602a3dfabac"}}