{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GAQB47LGMEUWTRVCU2H5HVNOQ6","short_pith_number":"pith:GAQB47LG","canonical_record":{"source":{"id":"2406.08731","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-13T01:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"b8fe662eb2b74bdc21916e4c544248101599a296f83de1a1329300114f71301b","abstract_canon_sha256":"10aa667ba08332087176fce4e02e927886d144cec79ae7dc1dc0cf812916580b"},"schema_version":"1.0"},"canonical_sha256":"30201e7d66612969c6a2a68fd3d5ae878e62443450266aa6ccd39b8c194f75b7","source":{"kind":"arxiv","id":"2406.08731","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08731","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08731v3","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08731","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"GAQB47LGMEUW","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"GAQB47LGMEUWTRVC","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"GAQB47LG","created_at":"2026-07-05T10:13:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GAQB47LGMEUWTRVCU2H5HVNOQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08731","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-13T01:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"b8fe662eb2b74bdc21916e4c544248101599a296f83de1a1329300114f71301b","abstract_canon_sha256":"10aa667ba08332087176fce4e02e927886d144cec79ae7dc1dc0cf812916580b"},"schema_version":"1.0"},"canonical_sha256":"30201e7d66612969c6a2a68fd3d5ae878e62443450266aa6ccd39b8c194f75b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:26.506814Z","signature_b64":"rORl/XKArsEdNN6cMpv/ng79V3YIYgFg5SH5VKeA1u5/zWKjWRshoYweJEa/w3qb3ayUEyKjhsIURkQbD8amBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30201e7d66612969c6a2a68fd3d5ae878e62443450266aa6ccd39b8c194f75b7","last_reissued_at":"2026-07-05T10:13:26.506271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:26.506271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08731","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mPJ3KftauA7YmJtFaBS0tMfYxvbBABviq9qq0R1dnqZ8qrY4+MyJc04HjUfGcAwUtMt0KZp3tUpAiiZQoH/lCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T08:26:41.765562Z"},"content_sha256":"be6cbe2b72f743df1ab0c406f6149550fd7c7e7f4ad765e98a24236069618301","schema_version":"1.0","event_id":"sha256:be6cbe2b72f743df1ab0c406f6149550fd7c7e7f4ad765e98a24236069618301"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GAQB47LGMEUWTRVCU2H5HVNOQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Da Song, Lei Ma, Shengmai Chen, Tianyi Zhang, Yuheng Huang, Zhijie Wang, Zijie Zhou","submitted_at":"2024-06-13T01:29:52Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated unprecedented capabilities in code generation. However, there remains a limited understanding of code generation errors that LLMs can produce. To bridge the gap, we conducted an in-depth analysis of code generation errors across six representative LLMs on the HumanEval dataset. Specifically, we first employed open coding and thematic analysis to distill a comprehensive taxonomy of code generation errors. We analyzed two dimensions of error characteristics -- semantic characteristics and syntactic characteristics. Our analysis revealed that LLMs of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08731","kind":"arxiv","version":3},"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/2406.08731/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":"2026-07-05T10:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BTpAxLZE8ZsgXl1T1EbYy3Ad4mbh+Qvu6AGgXnW2k16Bg9t2QyRQv+HjFP6c2UHblLb28fvF6xZEa7Q7vXugCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T08:26:41.766059Z"},"content_sha256":"2f9dbda38b8e6912b20a8e73adb3fec9bb00d6907f34c400cbb9b2852fa0c2d2","schema_version":"1.0","event_id":"sha256:2f9dbda38b8e6912b20a8e73adb3fec9bb00d6907f34c400cbb9b2852fa0c2d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6/bundle.json","state_url":"https://pith.science/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6/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":"2026-08-03T08:26:41Z","links":{"resolver":"https://pith.science/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6","bundle":"https://pith.science/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6/bundle.json","state":"https://pith.science/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAQB47LGMEUWTRVCU2H5HVNOQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GAQB47LGMEUWTRVCU2H5HVNOQ6","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":"10aa667ba08332087176fce4e02e927886d144cec79ae7dc1dc0cf812916580b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-13T01:29:52Z","title_canon_sha256":"b8fe662eb2b74bdc21916e4c544248101599a296f83de1a1329300114f71301b"},"schema_version":"1.0","source":{"id":"2406.08731","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08731","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08731v3","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08731","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"GAQB47LGMEUW","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"GAQB47LGMEUWTRVC","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"GAQB47LG","created_at":"2026-07-05T10:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:2f9dbda38b8e6912b20a8e73adb3fec9bb00d6907f34c400cbb9b2852fa0c2d2","target":"graph","created_at":"2026-07-05T10:13:26Z","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/2406.08731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated unprecedented capabilities in code generation. However, there remains a limited understanding of code generation errors that LLMs can produce. To bridge the gap, we conducted an in-depth analysis of code generation errors across six representative LLMs on the HumanEval dataset. Specifically, we first employed open coding and thematic analysis to distill a comprehensive taxonomy of code generation errors. We analyzed two dimensions of error characteristics -- semantic characteristics and syntactic characteristics. Our analysis revealed that LLMs of","authors_text":"Da Song, Lei Ma, Shengmai Chen, Tianyi Zhang, Yuheng Huang, Zhijie Wang, Zijie Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-13T01:29:52Z","title":"Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08731","kind":"arxiv","version":3},"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:be6cbe2b72f743df1ab0c406f6149550fd7c7e7f4ad765e98a24236069618301","target":"record","created_at":"2026-07-05T10:13:26Z","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":"10aa667ba08332087176fce4e02e927886d144cec79ae7dc1dc0cf812916580b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-13T01:29:52Z","title_canon_sha256":"b8fe662eb2b74bdc21916e4c544248101599a296f83de1a1329300114f71301b"},"schema_version":"1.0","source":{"id":"2406.08731","kind":"arxiv","version":3}},"canonical_sha256":"30201e7d66612969c6a2a68fd3d5ae878e62443450266aa6ccd39b8c194f75b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30201e7d66612969c6a2a68fd3d5ae878e62443450266aa6ccd39b8c194f75b7","first_computed_at":"2026-07-05T10:13:26.506271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:26.506271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rORl/XKArsEdNN6cMpv/ng79V3YIYgFg5SH5VKeA1u5/zWKjWRshoYweJEa/w3qb3ayUEyKjhsIURkQbD8amBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:26.506814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08731","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be6cbe2b72f743df1ab0c406f6149550fd7c7e7f4ad765e98a24236069618301","sha256:2f9dbda38b8e6912b20a8e73adb3fec9bb00d6907f34c400cbb9b2852fa0c2d2"],"state_sha256":"bb7cd688003e6bb602cf4185d4a60687baaec9d5a28d9fb7f4a377b11eb78243"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yldk8gUmRZ0xp/1gJ0LWiLTskqqpobUUoZlRYkXMJLzlD6jaVK8/Ik0fItfAHoflvC3wflnGMsob1U1jfst+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T08:26:41.769631Z","bundle_sha256":"cc283cb4ed19b61ea744a1ec043875bde88837dae2c29a501c180c6ddee4b094"}}