{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MD3HXVF4D3VUOFPASKZG3TZDUI","short_pith_number":"pith:MD3HXVF4","canonical_record":{"source":{"id":"2506.17369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-20T15:30:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fa23e2805a53f316ab4b43d032cf7d0afe7050e93880d8d751d2d2b76e6e5ba","abstract_canon_sha256":"68e1e15db0433ada959e385a9f64cc88da14cca43d262a235ea678f6facb07d5"},"schema_version":"1.0"},"canonical_sha256":"60f67bd4bc1eeb4715e092b26dcf23a21458ad2f8e4588ce3b961d832a9f9315","source":{"kind":"arxiv","id":"2506.17369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17369","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17369v1","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17369","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"MD3HXVF4D3VU","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"MD3HXVF4D3VUOFPA","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"MD3HXVF4","created_at":"2026-07-05T11:25:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MD3HXVF4D3VUOFPASKZG3TZDUI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-20T15:30:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fa23e2805a53f316ab4b43d032cf7d0afe7050e93880d8d751d2d2b76e6e5ba","abstract_canon_sha256":"68e1e15db0433ada959e385a9f64cc88da14cca43d262a235ea678f6facb07d5"},"schema_version":"1.0"},"canonical_sha256":"60f67bd4bc1eeb4715e092b26dcf23a21458ad2f8e4588ce3b961d832a9f9315","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:16.704955Z","signature_b64":"HShB36OR35xWJV+LkdQvdlJ9MfX06RCrBlEXBBKk6pd6MkY+fKFhR/2x60Nr2cUYmTGjkM8omNhRIxdt2Et5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f67bd4bc1eeb4715e092b26dcf23a21458ad2f8e4588ce3b961d832a9f9315","last_reissued_at":"2026-07-05T11:25:16.704488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:16.704488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17369","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":"2026-07-05T11:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23sYmVk84t8YRTtDqt4IN56iEMzj6L9wg7f4WMbjytXF2/bG8x9AYpcrS+978cg2WrSYW8RsXcmlu6+v3pEpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:41:14.582997Z"},"content_sha256":"3f09fb8aa3318173cf37650f02e259b8f614afa163bdf6de8ef84c32ed68e5a9","schema_version":"1.0","event_id":"sha256:3f09fb8aa3318173cf37650f02e259b8f614afa163bdf6de8ef84c32ed68e5a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MD3HXVF4D3VUOFPASKZG3TZDUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Xiaohu Yang, Xing Hu, Xin Xia, Zhiyuan Pan","submitted_at":"2025-06-20T15:30:36Z","abstract_excerpt":"In the era of large language models (LLMs), code benchmarks have become an important research area in software engineering and are widely used by practitioners. These benchmarks evaluate the performance of LLMs on specific code-related tasks, such as code understanding and generation. A critical step in constructing code benchmarks is the design of prompts. However, as existing code benchmarks typically rely on a single prompt template per task, they are prone to the issue of prompt sensitivity, where minor prompt variations could result in substantial performance variations, leading to unreli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17369","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/2506.17369/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":"2026-07-05T11:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Sj8GrQ3APVKdloZAR4Tm/XDYo9djbfmck4WsAuXDU0YWmr9jZA+WWGXhOfxvzx2MJC8bP4ShcEMG8jvI8xDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:41:14.583538Z"},"content_sha256":"71a350f0d4a27e46cfb481c90f44476302c122c780eebe424516a96be98d2fc0","schema_version":"1.0","event_id":"sha256:71a350f0d4a27e46cfb481c90f44476302c122c780eebe424516a96be98d2fc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MD3HXVF4D3VUOFPASKZG3TZDUI/bundle.json","state_url":"https://pith.science/pith/MD3HXVF4D3VUOFPASKZG3TZDUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MD3HXVF4D3VUOFPASKZG3TZDUI/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":"2026-08-22T20:41:14Z","links":{"resolver":"https://pith.science/pith/MD3HXVF4D3VUOFPASKZG3TZDUI","bundle":"https://pith.science/pith/MD3HXVF4D3VUOFPASKZG3TZDUI/bundle.json","state":"https://pith.science/pith/MD3HXVF4D3VUOFPASKZG3TZDUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MD3HXVF4D3VUOFPASKZG3TZDUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MD3HXVF4D3VUOFPASKZG3TZDUI","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":"68e1e15db0433ada959e385a9f64cc88da14cca43d262a235ea678f6facb07d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-20T15:30:36Z","title_canon_sha256":"8fa23e2805a53f316ab4b43d032cf7d0afe7050e93880d8d751d2d2b76e6e5ba"},"schema_version":"1.0","source":{"id":"2506.17369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17369","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17369v1","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17369","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"MD3HXVF4D3VU","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"MD3HXVF4D3VUOFPA","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"MD3HXVF4","created_at":"2026-07-05T11:25:16Z"}],"graph_snapshots":[{"event_id":"sha256:71a350f0d4a27e46cfb481c90f44476302c122c780eebe424516a96be98d2fc0","target":"graph","created_at":"2026-07-05T11:25:16Z","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/2506.17369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of large language models (LLMs), code benchmarks have become an important research area in software engineering and are widely used by practitioners. These benchmarks evaluate the performance of LLMs on specific code-related tasks, such as code understanding and generation. A critical step in constructing code benchmarks is the design of prompts. However, as existing code benchmarks typically rely on a single prompt template per task, they are prone to the issue of prompt sensitivity, where minor prompt variations could result in substantial performance variations, leading to unreli","authors_text":"Xiaohu Yang, Xing Hu, Xin Xia, Zhiyuan Pan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-20T15:30:36Z","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17369","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":"sha256:3f09fb8aa3318173cf37650f02e259b8f614afa163bdf6de8ef84c32ed68e5a9","target":"record","created_at":"2026-07-05T11:25:16Z","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":"68e1e15db0433ada959e385a9f64cc88da14cca43d262a235ea678f6facb07d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-20T15:30:36Z","title_canon_sha256":"8fa23e2805a53f316ab4b43d032cf7d0afe7050e93880d8d751d2d2b76e6e5ba"},"schema_version":"1.0","source":{"id":"2506.17369","kind":"arxiv","version":1}},"canonical_sha256":"60f67bd4bc1eeb4715e092b26dcf23a21458ad2f8e4588ce3b961d832a9f9315","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60f67bd4bc1eeb4715e092b26dcf23a21458ad2f8e4588ce3b961d832a9f9315","first_computed_at":"2026-07-05T11:25:16.704488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:16.704488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HShB36OR35xWJV+LkdQvdlJ9MfX06RCrBlEXBBKk6pd6MkY+fKFhR/2x60Nr2cUYmTGjkM8omNhRIxdt2Et5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:16.704955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f09fb8aa3318173cf37650f02e259b8f614afa163bdf6de8ef84c32ed68e5a9","sha256:71a350f0d4a27e46cfb481c90f44476302c122c780eebe424516a96be98d2fc0"],"state_sha256":"bb1dcd94a28bddd88a3e421b0182d0dfee1fdb270e91654b537c06c193359f23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jUrPcN16Kn0xHlLgO7B8MHJhY0h9oU+iGWeO0D9E/GoqYyxX+ERzhb82DKO50AIZ82qdOHIP6fe0FAhJQARmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T20:41:14.590111Z","bundle_sha256":"b92ca892853b248a63acf7b5c23f496c5f5e2af1e1f72fadcb59f015567acb03"}}