{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ELN7HBS2ICBSWD6OMJHJSWM5K7","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":"d530b2e406c465bb1c4ebe2674c89d6fac23a6465b4a0fa89af9f84a87d0762a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-07T10:52:28Z","title_canon_sha256":"a93fc538458dc4c10bcd159718cc32ece359f9e5315d937eb2ccc6c14b844223"},"schema_version":"1.0","source":{"id":"2505.04311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04311","created_at":"2026-07-05T10:59:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04311v1","created_at":"2026-07-05T10:59:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04311","created_at":"2026-07-05T10:59:39Z"},{"alias_kind":"pith_short_12","alias_value":"ELN7HBS2ICBS","created_at":"2026-07-05T10:59:39Z"},{"alias_kind":"pith_short_16","alias_value":"ELN7HBS2ICBSWD6O","created_at":"2026-07-05T10:59:39Z"},{"alias_kind":"pith_short_8","alias_value":"ELN7HBS2","created_at":"2026-07-05T10:59:39Z"}],"graph_snapshots":[{"event_id":"sha256:e27c022ef9d6c1e3d49792eaf1e0c431ea99f5f37741d91c29256d650106f46c","target":"graph","created_at":"2026-07-05T10:59:39Z","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/2505.04311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"BigCloneBench is a well-known and widely used large-scale dataset for the evaluation of recall of clone detection tools. It has been beneficial for research on clone detection and has become a standard in evaluating the performance of clone detection tools. More recently, it has also been widely used as a dataset to evaluate machine learning approaches to semantic clone detection or code similarity detection for functional or semantic similarity.\n  This paper demonstrates that BigCloneBench is problematic to use as ground truth for learning or evaluating semantic code similarity, and highlight","authors_text":"Chaiyong Ragkhitwetsagul, Jens Krinke","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-07T10:52:28Z","title":"How the Misuse of a Dataset Harmed Semantic Clone Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04311","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:d581f3deb8baa2b56a2f522015c6c08ebbf602ba4c2d273620acffd0fb49543e","target":"record","created_at":"2026-07-05T10:59:39Z","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":"d530b2e406c465bb1c4ebe2674c89d6fac23a6465b4a0fa89af9f84a87d0762a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-07T10:52:28Z","title_canon_sha256":"a93fc538458dc4c10bcd159718cc32ece359f9e5315d937eb2ccc6c14b844223"},"schema_version":"1.0","source":{"id":"2505.04311","kind":"arxiv","version":1}},"canonical_sha256":"22dbf3865a40832b0fce624e99599d57e03500b8f8c7d09e06bb9c41724be95a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22dbf3865a40832b0fce624e99599d57e03500b8f8c7d09e06bb9c41724be95a","first_computed_at":"2026-07-05T10:59:39.850067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:39.850067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xxCrD8m8ppugMxCm6aCa3dhclwcl+XnUbT6hPc4+yHeZwci7EUdyZqdl/sh8bf7T8tWXIxQZtL9Ny/d076G4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:39.850617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d581f3deb8baa2b56a2f522015c6c08ebbf602ba4c2d273620acffd0fb49543e","sha256:e27c022ef9d6c1e3d49792eaf1e0c431ea99f5f37741d91c29256d650106f46c"],"state_sha256":"e5c2a9fc2bbd719d1914a2ae701ffb572232f3ed818551885ed32de9d3f457a4"}