{"as_of":"2026-08-12T23:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f7c23ab688b3cf43f114dafa26b4df0d2f7f53d1b6774bf683724e43c7415580","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T05:11:53.076473Z","state":"measured"},{"denominator":19,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":19,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2412.17933/citation-record","integrity":"/paper/2412.17933/integrity","json":"/paper/2412.17933/citation-record.json","paper":"/paper/2412.17933"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.08446","last_updated":"2025-02-11T18:59:26Z","snapshot_observed_at":"2026-08-12T07:08:42.356089Z","submitted_at":"2024-06-12T17:37:09Z","title":"OLMES: A Standard for Language Model Evaluations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08446","snapshot_observed_at":"2026-08-11T05:11:53.008559Z","title":"arXiv preprint arXiv:2406.08446","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.008559Z"},"links":{"cited_paper":"/paper/2406.08446","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:d381ee3ab430826f8e2dbaae243df78bb4c9614e9f12c2f61f5f76f83397de2e","observation_id":"91353968-e45e-429d-91ec-25358e755dfb","resolution":{"observed_at":"2026-08-11T05:11:53.008559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.335982Z","title":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt","venue":null,"work_id":"7ea49fcd-ab48-4a04-9a4b-b2eeaceb0acc","year":2021},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.014735Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:b15219aae8d74d85881006b2de7bc58e89b6134682657cb5858ece13a2c21626","observation_id":"24db0678-5e50-4973-b5e3-948ade7aa7c3","resolution":{"observed_at":"2026-08-11T05:11:53.341556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01856","last_updated":"2025-06-10T15:06:59Z","snapshot_observed_at":"2026-08-12T07:09:31.285404Z","submitted_at":"2024-04-02T11:34:12Z","title":"Poro 34B and the Blessing of Multilinguality","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01856","snapshot_observed_at":"2026-08-11T05:11:53.025254Z","title":"In Annual Meeting of the Association for Computational Linguistics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.025254Z"},"links":{"cited_paper":"/paper/2404.01856","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:c91c0cad4f3021ec9045a6027e5ee8a6525b56df587a5ecf7f0407e1fe6bd5ee","observation_id":"9aa41d7c-79fe-4c2c-bfd0-37a8d56406cc","resolution":{"observed_at":"2026-08-11T05:11:53.025254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1109.2378","last_updated":"2011-09-12T05:49:11Z","snapshot_observed_at":"2026-08-03T18:17:29.793532Z","submitted_at":"2011-09-12T05:49:11Z","title":"Modern hierarchical, agglomerative clustering algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1109.2378","snapshot_observed_at":"2026-08-11T05:11:53.030238Z","title":"Transactions of the Association for Computational Linguistics, 12:933–949","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.030238Z"},"links":{"cited_paper":"/paper/1109.2378","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:2c5b954a39217ca252411b61cb39d2e24fb499e1aa20d26cf9b50742b703c2c2","observation_id":"c4a51936-c669-4d25-8d21-2a06c5a99ef8","resolution":{"observed_at":"2026-08-11T05:11:53.030238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.351659Z","title":"Ústav ˇCeského národního korpusu FF UK, Praha","venue":null,"work_id":"ee86360a-8ac8-43d0-8d21-3fef3ca50f57","year":2021},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.002996Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:c59d37d1d8c5ec27b5e12a3dcfafe1fd05d5b5e0d8c3ea4fe2f254aacaf7a37c","observation_id":"f79551d9-dc9c-4fdb-880a-40e3c4d34d34","resolution":{"observed_at":"2026-08-11T05:11:53.356683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11548","last_updated":"2024-06-06T12:23:58Z","snapshot_observed_at":"2026-08-06T05:59:58.625725Z","submitted_at":"2024-02-18T11:41:07Z","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11548","snapshot_observed_at":"2026-08-11T05:11:53.040212Z","title":"In The Eleventh Interna- tional Conference on Learning Representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.040212Z"},"links":{"cited_paper":"/paper/2402.11548","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:17d2152dca9bfdf24e9a0c4c775e10243f5809b18e440fbe3868eb876180528d","observation_id":"a0aabde0-d0ac-4880-9271-5fd26780de5b","resolution":{"observed_at":"2026-08-11T05:11:53.040212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.320414Z","title":"Transactions on Machine Learning Re- search","venue":null,"work_id":"6d2c4ae8-4ddd-4bf6-a9c6-a87fd0a37ac5","year":2023},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.045188Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:aaafda7fcc149402af0342329d05a6ae45c3951d9f02cb9083775c742f02f2f6","observation_id":"6876d1b7-9d79-4372-abcc-836390f86d62","resolution":{"observed_at":"2026-08-11T05:11:53.325246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.304865Z","title":"I don’t know","venue":null,"work_id":"d3fcfbd3-4616-4638-881d-978b15dd64a3","year":2023},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.055916Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:0ca648235e258ab985499b04aec4a6ad319ecff63fa316081e04476f212e10a8","observation_id":"1d35e610-fd22-445f-b3a4-36dbd77e5119","resolution":{"observed_at":"2026-08-11T05:11:53.309458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.288660Z","title":"5 texts are original Czech works, and 3 are translations from German and Slovak","venue":null,"work_id":"bb53d49a-b9a4-4a6d-953e-2e4cf9a27c5a","year":1991},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.061569Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:4d53606398206dc614f4fe940db2f21242ccd8dd8890defd3e0a2605017dbe93","observation_id":"c1377cca-0f8b-4cd7-b378-7677f2ad976d","resolution":{"observed_at":"2026-08-11T05:11:53.294117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.273408Z","title":"• Private Correspondence Corpus (Hladká,","venue":null,"work_id":"9908b550-f075-42ff-ae9e-77c81196a6c9","year":null},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.066427Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:9164c0de03220dc610757b4474e21ff941c95fad5b146f5bb995174fdd72210d","observation_id":"a2c5e7e9-081b-48a7-a08c-dfed19c2859e","resolution":{"observed_at":"2026-08-11T05:11:53.278156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-11T05:11:52.990279Z","title":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael Jordan, Joseph E Gonzalez, et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":1901,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:52.990279Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:4b2b97ee41b012b7377a5989ebc2b6d281a89a608ccad0db393f37bee5a7d8f5","observation_id":"fd388948-9e22-4d55-a0c2-db78b3d76fd2","resolution":{"observed_at":"2026-08-11T05:11:52.990279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.257985Z","title":"<initial 20 ws tokens>, ..., <sampled window>","venue":null,"work_id":"bf790328-823c-4d95-b2ec-b0205d212dd1","year":2023},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.071360Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:7d847f306a736a201d5193047971c45676491ea6c9a6cbaf1839c7dd80b0a7d0","observation_id":"d8d6f831-d224-492f-90d6-08071433519d","resolution":{"observed_at":"2026-08-11T05:11:53.263031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.382346Z","title":"Ústav ˇCeského národ- ního korpusu FF UK, Praha","venue":null,"work_id":"323a55d2-dde9-459e-8808-2ce3e6531234","year":1995},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:52.984965Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:0219d3f57b36e02bcb9571a0ffdbf81214a40302c096d5590382cdc5cb67f542","observation_id":"f458c937-2f0d-453c-8ded-f2b3ff1f0323","resolution":{"observed_at":"2026-08-11T05:11:53.387359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.238556Z","title":"The speeches were made by Czech presidents, or their deputies, announced periodically on the occasion of anniversaries and public holidays (New Year, 28 October, etc.)","venue":null,"work_id":"a784280d-e751-465c-83c3-1aa6900d8c5c","year":1918},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.076473Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:683b93e2de7e29463a4ae8873cd7e8a9f2f3c2787441d748984a58ab26f0d261","observation_id":"b1f62c74-4019-4219-b637-0dad72a660f8","resolution":{"observed_at":"2026-08-11T05:11:53.246617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-11T05:11:53.019984Z","title":"Ústav ˇCeského národního korpusu FF UK, Praha","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.019984Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:4b6c9679ced46c3d57a75fdc56f234656cce402631181554ab974b20678d043d","observation_id":"7863614d-33cc-4ac0-836e-4379ce2ebc7a","resolution":{"observed_at":"2026-08-11T05:11:53.019984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.05892","last_updated":"2023-03-15T06:57:46Z","snapshot_observed_at":"2026-07-06T14:03:57.555580Z","submitted_at":"2022-10-12T03:13:28Z","title":"Perplexity from PLM Is Unreliable for Evaluating Text Quality","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.05892","snapshot_observed_at":"2026-08-11T05:11:53.050856Z","title":"In BlackboxNLP@EMNLP","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.050856Z"},"links":{"cited_paper":"/paper/2210.05892","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:8885a93b46477be60073230d0ea4316a60d87527458114282a73d7c559751366","observation_id":"74060821-c78e-4791-964c-a062092db89a","resolution":{"observed_at":"2026-08-11T05:11:53.050856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.367417Z","title":null,"venue":null,"work_id":"58ada7a9-450d-436f-9205-0eedec895b64","year":null},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:52.997195Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:0473ffda725a79a825175d4e40e7d6bb24953747c032011f144fcdea6ccc7625","observation_id":"2fa25e51-5f54-4ddc-a6d1-db3c32659492","resolution":{"observed_at":"2026-08-11T05:11:53.372483Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16149","last_updated":"2023-09-29T11:51:51Z","snapshot_observed_at":"2026-08-10T13:04:52.644739Z","submitted_at":"2023-08-30T17:07:17Z","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16149","snapshot_observed_at":"2026-08-11T05:11:53.034975Z","title":"Yixin Nie, Haonan Chen, and Mohit Bansal","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:53.034975Z"},"links":{"cited_paper":"/paper/2308.16149","citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:a9ad0a433490b0c9d7408519540aca4501f14c7f6aa0edd30a6ba46909434d9e","observation_id":"add1dddc-0135-4bde-93ed-5c05a8725fc1","resolution":{"observed_at":"2026-08-11T05:11:53.034975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:11:53.396724Z","title":"In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa- pers), pages 7421–7454, Bangkok, Thailand","venue":null,"work_id":"994b272a-68c1-48c5-a7ab-f4f10bd2f983","year":2024},"citing_paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T05:11:52.979062Z"},"links":{"citing_paper":"/paper/2412.17933"},"observation_digest":"sha256:bcf383219ddb8694a3169c960e95331101606a4debc227d470da0b260e4af65c","observation_id":"c907c2af-f280-4ad0-99db-1a2c779e89b8","resolution":{"observed_at":"2026-08-11T05:11:53.401444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.17933","last_updated":"2025-05-22T08:47:46Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-12T07:09:10.637310Z","submitted_at":"2024-12-23T19:45:20Z","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":10},"total_outbound_references":19},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2412.17933."}