{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VJYG3PL5UND6TZNL3MF3V64BKP","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":"838a3b9bceb067aebee1e1f3c85c4276875dcf413e23f5aa5966508b370dc14d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-28T03:16:34Z","title_canon_sha256":"7c7cf8b666808fae1e17b8cc89bb083f1db94973c8154117c6c06d44d7321040"},"schema_version":"1.0","source":{"id":"2504.19444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19444","created_at":"2026-07-05T10:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19444v1","created_at":"2026-07-05T10:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19444","created_at":"2026-07-05T10:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"VJYG3PL5UND6","created_at":"2026-07-05T10:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"VJYG3PL5UND6TZNL","created_at":"2026-07-05T10:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"VJYG3PL5","created_at":"2026-07-05T10:54:57Z"}],"graph_snapshots":[{"event_id":"sha256:ad14e593dc31e2161578d0b6cd95b5904a824291651d420f6b449f50b866c5a1","target":"graph","created_at":"2026-07-05T10:54:57Z","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/2504.19444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained code models rely heavily on high-quality pre-training data, particularly human-written reference comments that bridge code and natural language. However, these comments often become outdated as software evolves, degrading model performance. Large language models (LLMs) excel at generating high-quality code comments. We investigate whether replacing human-written comments with LLM-generated ones improves pre-training datasets. Since standard metrics cannot assess reference comment quality, we propose two novel reference-free evaluation tasks: code-comment inconsistency detection and","authors_text":"Bo Lin, Kamal Al-Sabahi, Kang Yang, Shangwen Wang, Tanghaoran Zhang, Xinjun Mao, Yanlin Wang, Yao Lu, Yihao Qin, Zhang Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-28T03:16:34Z","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19444","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":"sha256:9f20f0718d461444a9da062b3708e84a705cbdd13c7e3832c5dd87da679f7e26","target":"record","created_at":"2026-07-05T10:54:57Z","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":"838a3b9bceb067aebee1e1f3c85c4276875dcf413e23f5aa5966508b370dc14d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-28T03:16:34Z","title_canon_sha256":"7c7cf8b666808fae1e17b8cc89bb083f1db94973c8154117c6c06d44d7321040"},"schema_version":"1.0","source":{"id":"2504.19444","kind":"arxiv","version":1}},"canonical_sha256":"aa706dbd7da347e9e5abdb0bbafb8153f90446e284f9759b1153c4e6fe01c981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa706dbd7da347e9e5abdb0bbafb8153f90446e284f9759b1153c4e6fe01c981","first_computed_at":"2026-07-05T10:54:57.631924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:57.631924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VhmspgnOrTOlSEw7DdvamKRNaI2jIywkFeNQbl0yqzbb9nEXhKG+jchSNhE9oJKr91ODMDVegZei0PAxcfV9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:57.632434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f20f0718d461444a9da062b3708e84a705cbdd13c7e3832c5dd87da679f7e26","sha256:ad14e593dc31e2161578d0b6cd95b5904a824291651d420f6b449f50b866c5a1"],"state_sha256":"4170512160a7c565c080b0a9367ee3f7dd67500fda471c8ba456e28fe5ceb8d6"}