{"as_of":"2026-08-09T12:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ac5d3efb4fabbf6785ab8cb02df70c25e04c41df39aacf61a857255aaf4a928f","coverage":[{"denominator":4,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T18:53:05.214761Z","state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2508.13938/citation-record","integrity":"/paper/2508.13938/integrity","json":"/paper/2508.13938/citation-record.json","paper":"/paper/2508.13938"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.03124","last_updated":"2025-06-28T12:31:45Z","snapshot_observed_at":"2026-08-07T08:05:38.374743Z","submitted_at":"2025-01-06T16:31:45Z","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03124","snapshot_observed_at":"2026-08-05T18:53:05.114132Z","title":"arXiv preprint arXiv:2501.03124","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.13938","last_updated":"2025-08-19T15:27:55Z","snapshot_observed_at":"2026-08-09T10:32:22.217253Z","submitted_at":"2025-08-19T15:27:55Z","title":"MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T18:53:05.114132Z"},"links":{"cited_paper":"/paper/2501.03124","citing_paper":"/paper/2508.13938"},"observation_digest":"sha256:792960b046a767a6908748de4e8b8445448c904e4360ecc7f29f77002e59735d","observation_id":"7464e93f-84fc-44e9-a514-0b3aa0c65612","resolution":{"observed_at":"2026-08-05T18:53:05.114132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12474","last_updated":"2024-02-24T15:44:21Z","snapshot_observed_at":"2026-08-08T08:58:54.609425Z","submitted_at":"2023-05-21T14:39:28Z","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12474","snapshot_observed_at":"2026-08-05T18:53:05.214761Z","title":"arXiv preprint arXiv:2305.12474","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.13938","last_updated":"2025-08-19T15:27:55Z","snapshot_observed_at":"2026-08-09T10:32:22.217253Z","submitted_at":"2025-08-19T15:27:55Z","title":"MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T18:53:05.214761Z"},"links":{"cited_paper":"/paper/2305.12474","citing_paper":"/paper/2508.13938"},"observation_digest":"sha256:247b7badcfea3c8b9e0efb81e8a24efb4b96cbce963fb7aae04ec753dd6ca797","observation_id":"dac95634-5e48-4fae-897d-b95e50e70bcc","resolution":{"observed_at":"2026-08-05T18:53:05.214761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15594","last_updated":"2025-10-19T10:32:43Z","snapshot_observed_at":"2026-08-02T10:23:50.881300Z","submitted_at":"2024-11-23T16:03:35Z","title":"A Survey on LLM-as-a-Judge","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15594","snapshot_observed_at":"2026-08-05T18:53:04.972885Z","title":"See https://vicuna","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.13938","last_updated":"2025-08-19T15:27:55Z","snapshot_observed_at":"2026-08-09T10:32:22.217253Z","submitted_at":"2025-08-19T15:27:55Z","title":"MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T18:53:04.972885Z"},"links":{"cited_paper":"/paper/2411.15594","citing_paper":"/paper/2508.13938"},"observation_digest":"sha256:797856f9d335da50070b7373bb4092389f3f0f361173285a831968d629bb8800","observation_id":"84f8d49f-094c-4fea-85e1-5baa35d2c0d5","resolution":{"observed_at":"2026-08-05T18:53:04.972885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02018","last_updated":"2025-05-04T07:48:36Z","snapshot_observed_at":"2026-08-08T09:28:02.889462Z","submitted_at":"2025-05-04T07:48:36Z","title":"R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02018","snapshot_observed_at":"2026-08-05T18:53:05.031094Z","title":"arXiv preprint arXiv:2505.02018","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.13938","last_updated":"2025-08-19T15:27:55Z","snapshot_observed_at":"2026-08-09T10:32:22.217253Z","submitted_at":"2025-08-19T15:27:55Z","title":"MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T18:53:05.031094Z"},"links":{"cited_paper":"/paper/2505.02018","citing_paper":"/paper/2508.13938"},"observation_digest":"sha256:358cfd355cb4d912592b4d12849ec2af50b5f7e843ba6df4c693c7ff74c39754","observation_id":"e2498c15-1ae6-4456-91ac-4b9828478eed","resolution":{"observed_at":"2026-08-05T18:53:05.031094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.13938","last_updated":"2025-08-19T15:27:55Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T10:32:22.217253Z","submitted_at":"2025-08-19T15:27:55Z","title":"MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":4},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2508.13938."}