{"as_of":"2026-08-09T00:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4695e91d38b4bc8299be7749bc76d9612bd3da5c10fd2aa0989fd624ecf8b4db","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:29:19.036173Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T12:11:08.258913Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.15037","last_updated":"2025-01-26T00:56:43Z","snapshot_observed_at":"2026-08-05T15:39:57.235988Z","submitted_at":"2024-10-19T08:44:26Z","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15037","snapshot_observed_at":"2026-08-07T12:29:19.036173Z","title":"mHumanEval – A Multilingual Benchmark to Evaluate Large Language Models for Code Generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24324","last_updated":"2025-05-30T08:06:30Z","snapshot_observed_at":"2026-08-08T23:46:24.421775Z","submitted_at":"2025-05-30T08:06:30Z","title":"SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:29:19.036173Z"},"links":{"cited_paper":"/paper/2410.15037","citing_paper":"/paper/2505.24324"},"observation_digest":"sha256:d4f05ea903f8a1beaf9ab244b4e47cb26051f565ff1733435394243516b64c69","observation_id":"420e91c7-9ceb-44a7-802d-b81cf01f07ec","resolution":{"observed_at":"2026-08-07T12:29:19.036173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15037","last_updated":"2025-01-26T00:56:43Z","snapshot_observed_at":"2026-08-05T15:39:57.235988Z","submitted_at":"2024-10-19T08:44:26Z","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15037","snapshot_observed_at":"2026-08-06T17:24:05.899426Z","title":"mhumaneval–a multilingual benchmark to evaluate large language models for code generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.11014","last_updated":"2025-07-15T06:14:45Z","snapshot_observed_at":"2026-08-06T17:16:27.403210Z","submitted_at":"2025-07-15T06:14:45Z","title":"SIMCODE: A Benchmark for Natural Language to ns-3 Network Simulation Code Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:24:05.899426Z"},"links":{"cited_paper":"/paper/2410.15037","citing_paper":"/paper/2507.11014"},"observation_digest":"sha256:618ff39e39642892641ed0b8bcee46831460ebe9b97147a8cd4c46c0632b8262","observation_id":"b9f315b6-09bb-4839-8937-5233d01e3212","resolution":{"observed_at":"2026-08-06T17:24:05.899426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15037","last_updated":"2025-01-26T00:56:43Z","snapshot_observed_at":"2026-08-05T15:39:57.235988Z","submitted_at":"2024-10-19T08:44:26Z","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2410.15037","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.15037","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2410.15037 , year=","venue":null,"work_id":"ce44ec61-3b68-4b21-93ca-cf8143d33df3","year":null},"citing_paper":{"arxiv_id":"2604.18914","last_updated":"2026-04-20T23:35:24Z","snapshot_observed_at":"2026-08-07T21:55:26.980844Z","submitted_at":"2026-04-20T23:35:24Z","title":"MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-10T04:04:12.610168Z"},"links":{"cited_paper":"/paper/2410.15037","citing_paper":"/paper/2604.18914"},"observation_digest":"sha256:fa18e9c0b47be15f9017e507d7fe287f5e3093f8e2e16a4a01aaf6ad2fc6be72","observation_id":"fd395e90-bbf8-426b-80fa-84ca13aafef1","resolution":{"observed_at":"2026-05-11T12:11:08.267658Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.15037/citation-record","integrity":"/paper/2410.15037/integrity","json":"/paper/2410.15037/citation-record.json","paper":"/paper/2410.15037"},"outbound":[],"paper":{"arxiv_id":"2410.15037","last_updated":"2025-01-26T00:56:43Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T15:39:57.235988Z","submitted_at":"2024-10-19T08:44:26Z","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.15037."}