{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ALJ524OCCCBPRSYOYBVOYPOJSP","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":"32234b838acca1c0571c380cd8724f38c01b883698d7c5262fa98b1c73617613","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-29T01:21:05Z","title_canon_sha256":"09341d802883d5163a13ffaf33af9b5f7fdc3d7748440e60d05916d935963d73"},"schema_version":"1.0","source":{"id":"2410.21647","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21647","created_at":"2026-07-05T11:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21647v4","created_at":"2026-07-05T11:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21647","created_at":"2026-07-05T11:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"ALJ524OCCCBP","created_at":"2026-07-05T11:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"ALJ524OCCCBPRSYO","created_at":"2026-07-05T11:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"ALJ524OC","created_at":"2026-07-05T11:26:44Z"}],"graph_snapshots":[{"event_id":"sha256:c9b591cc9f25fcceb4827cd3a2e8275dcdc8074677b8048fc825311fbe16ae1f","target":"graph","created_at":"2026-07-05T11:26:44Z","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/2410.21647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standalone benchmarks like HumanEval and MBPP. Thus, a natural question is, would LLMs have similar performance in real world coding tasks as their performance in these benchmarks? Unfortunately, one cannot answer this question, since these benchmarks consist of short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks","authors_text":"Lin Tan, Nan Jiang, Shanchao Liang, Yiran Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-29T01:21:05Z","title":"Can Language Models Replace Programmers for Coding? REPOCOD Says 'Not Yet'"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21647","kind":"arxiv","version":4},"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:c00ea15e7f1281cd87d09bd80981f7014be8a3be6c60c709b53671dd82925fda","target":"record","created_at":"2026-07-05T11:26:44Z","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":"32234b838acca1c0571c380cd8724f38c01b883698d7c5262fa98b1c73617613","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-29T01:21:05Z","title_canon_sha256":"09341d802883d5163a13ffaf33af9b5f7fdc3d7748440e60d05916d935963d73"},"schema_version":"1.0","source":{"id":"2410.21647","kind":"arxiv","version":4}},"canonical_sha256":"02d3dd71c21082f8cb0ec06aec3dc993c99f47781892ac04b2fdb96bd35beb6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02d3dd71c21082f8cb0ec06aec3dc993c99f47781892ac04b2fdb96bd35beb6d","first_computed_at":"2026-07-05T11:26:44.625539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:44.625539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yoa5O7XeCmlMCrVt4zkUQ/ZpS1HrgfGahznwvXQ4YfFIw10GC+PUIk0ildJOAzuLO6G12ovsZmEpSBSYA3ACBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:44.625986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21647","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c00ea15e7f1281cd87d09bd80981f7014be8a3be6c60c709b53671dd82925fda","sha256:c9b591cc9f25fcceb4827cd3a2e8275dcdc8074677b8048fc825311fbe16ae1f"],"state_sha256":"34856247d45ef2bdba5f4e2e03ea49e54616767a71477c158594265c4ccc64f6"}