{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IKCRTACL7PGNFPLPVVANJA4TZQ","short_pith_number":"pith:IKCRTACL","canonical_record":{"source":{"id":"2407.11470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-16T08:08:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4b1f339e194f26cba3dc08ea440e8b65beec69800f6bee669e2e57874c470379","abstract_canon_sha256":"d96949756b13d9f3babdc14e2c39bd49df9f437a968752f5fc92b4e29a0ba1c6"},"schema_version":"1.0"},"canonical_sha256":"428519804bfbccd2bd6fad40d48393cc10c5430327dc1e23018306a5bdb12dc6","source":{"kind":"arxiv","id":"2407.11470","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11470","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11470v2","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11470","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"IKCRTACL7PGN","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"IKCRTACL7PGNFPLP","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"IKCRTACL","created_at":"2026-07-05T09:17:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IKCRTACL7PGNFPLPVVANJA4TZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-16T08:08:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4b1f339e194f26cba3dc08ea440e8b65beec69800f6bee669e2e57874c470379","abstract_canon_sha256":"d96949756b13d9f3babdc14e2c39bd49df9f437a968752f5fc92b4e29a0ba1c6"},"schema_version":"1.0"},"canonical_sha256":"428519804bfbccd2bd6fad40d48393cc10c5430327dc1e23018306a5bdb12dc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:45.999503Z","signature_b64":"yog027GxpQ/nj7EKNKgfA8NES8r1M4bT1ZkmlEBZ5tv1UmCe8UeEHlofLQ92GYGsSnmUmmmPGev/vCJ99bIkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"428519804bfbccd2bd6fad40d48393cc10c5430327dc1e23018306a5bdb12dc6","last_reissued_at":"2026-07-05T09:17:45.999015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:45.999015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11470","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EAyzCNgQ14bf6U4huVxr+4+BYkijdVYNjnr9W+J62pw9sdXnVhOVetsunWoGTuc/7idpqVzZgkOA0k5ipVGGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:35:11.968576Z"},"content_sha256":"f036c5246b7cb6629d52d97c8e305d43abd52b5a38ccd33132042f1cfa206e26","schema_version":"1.0","event_id":"sha256:f036c5246b7cb6629d52d97c8e305d43abd52b5a38ccd33132042f1cfa206e26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IKCRTACL7PGNFPLPVVANJA4TZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Boxi Cao, Hongyu Lin, Jiasheng Zheng, Le Sun, Ruotong Pan, Xianpei Han, Yaojie Lu, Zhengzhao Ma","submitted_at":"2024-07-16T08:08:48Z","abstract_excerpt":"In recent years, researchers have proposed numerous benchmarks to evaluate the impressive coding capabilities of large language models (LLMs). However, current benchmarks primarily assess the accuracy of LLM-generated code, while neglecting other critical dimensions that also significantly impact code quality in real-world development. Moreover, relying exclusively on correctness as the guiding metric renders LLMs susceptible to data contamination. Therefore, this paper proposes the RACE benchmark, which comprehensively evaluates the quality of code generated by LLMs across 4 dimensions: Reada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11470","kind":"arxiv","version":2},"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/2407.11470/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":"2026-07-05T09:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xzi0VAhbeo6VI3Vo5yAQCI8ZIGTjeRt5RsDuaIhICms++RTyeAIbIkFF9+JR8IUhKEjtNfHQuOyDL+HOd4+eBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:35:11.969280Z"},"content_sha256":"413225b1c2f8ba99581aed2f8b44fefc6e6a7998bc0a46f6db2a88f82d9745aa","schema_version":"1.0","event_id":"sha256:413225b1c2f8ba99581aed2f8b44fefc6e6a7998bc0a46f6db2a88f82d9745aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKCRTACL7PGNFPLPVVANJA4TZQ/bundle.json","state_url":"https://pith.science/pith/IKCRTACL7PGNFPLPVVANJA4TZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKCRTACL7PGNFPLPVVANJA4TZQ/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":"2026-08-04T21:35:11Z","links":{"resolver":"https://pith.science/pith/IKCRTACL7PGNFPLPVVANJA4TZQ","bundle":"https://pith.science/pith/IKCRTACL7PGNFPLPVVANJA4TZQ/bundle.json","state":"https://pith.science/pith/IKCRTACL7PGNFPLPVVANJA4TZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKCRTACL7PGNFPLPVVANJA4TZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IKCRTACL7PGNFPLPVVANJA4TZQ","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":"d96949756b13d9f3babdc14e2c39bd49df9f437a968752f5fc92b4e29a0ba1c6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-16T08:08:48Z","title_canon_sha256":"4b1f339e194f26cba3dc08ea440e8b65beec69800f6bee669e2e57874c470379"},"schema_version":"1.0","source":{"id":"2407.11470","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11470","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11470v2","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11470","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"IKCRTACL7PGN","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"IKCRTACL7PGNFPLP","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"IKCRTACL","created_at":"2026-07-05T09:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:413225b1c2f8ba99581aed2f8b44fefc6e6a7998bc0a46f6db2a88f82d9745aa","target":"graph","created_at":"2026-07-05T09:17:45Z","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/2407.11470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, researchers have proposed numerous benchmarks to evaluate the impressive coding capabilities of large language models (LLMs). However, current benchmarks primarily assess the accuracy of LLM-generated code, while neglecting other critical dimensions that also significantly impact code quality in real-world development. Moreover, relying exclusively on correctness as the guiding metric renders LLMs susceptible to data contamination. Therefore, this paper proposes the RACE benchmark, which comprehensively evaluates the quality of code generated by LLMs across 4 dimensions: Reada","authors_text":"Boxi Cao, Hongyu Lin, Jiasheng Zheng, Le Sun, Ruotong Pan, Xianpei Han, Yaojie Lu, Zhengzhao Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-16T08:08:48Z","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11470","kind":"arxiv","version":2},"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:f036c5246b7cb6629d52d97c8e305d43abd52b5a38ccd33132042f1cfa206e26","target":"record","created_at":"2026-07-05T09:17:45Z","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":"d96949756b13d9f3babdc14e2c39bd49df9f437a968752f5fc92b4e29a0ba1c6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-16T08:08:48Z","title_canon_sha256":"4b1f339e194f26cba3dc08ea440e8b65beec69800f6bee669e2e57874c470379"},"schema_version":"1.0","source":{"id":"2407.11470","kind":"arxiv","version":2}},"canonical_sha256":"428519804bfbccd2bd6fad40d48393cc10c5430327dc1e23018306a5bdb12dc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"428519804bfbccd2bd6fad40d48393cc10c5430327dc1e23018306a5bdb12dc6","first_computed_at":"2026-07-05T09:17:45.999015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:45.999015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yog027GxpQ/nj7EKNKgfA8NES8r1M4bT1ZkmlEBZ5tv1UmCe8UeEHlofLQ92GYGsSnmUmmmPGev/vCJ99bIkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:45.999503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11470","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f036c5246b7cb6629d52d97c8e305d43abd52b5a38ccd33132042f1cfa206e26","sha256:413225b1c2f8ba99581aed2f8b44fefc6e6a7998bc0a46f6db2a88f82d9745aa"],"state_sha256":"420791e0f8babd5cd5899cc0b61599d32b5033da727f64a750233dd56100efba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lva4HfxXUN4wow0gLbRAChyRbQqF+t8wAXjEpHx6gu7pVFNyDfE8s0dkvcZIY9NmoMV89yzT4mmpRCcxnNzDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:35:11.975308Z","bundle_sha256":"bc8059ed973e30e0fa8a8eb04e57c14a1dd105077af15fb4e6c23507e4409f65"}}