{"as_of":"2026-08-10T21:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:634d78306af1cde26ff9c309de6dd9a463a2896e2ada4b87adc6e5ff2501acd3","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":"2026-05-07T08:02:49.168872Z","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":"2026-08-10T06:31:04.303077+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/2604.27405/citation-record","integrity":"/paper/2604.27405/integrity","json":"/paper/2604.27405/citation-record.json","paper":"/paper/2604.27405"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"InProceedings of the International Con- ference on Machine Learning","venue":null,"work_id":"57d2ec4e-926c-4152-9b8b-0cbc5dd91484","year":null},"citing_paper":{"arxiv_id":"2604.27405","last_updated":"2026-04-30T04:16:13Z","snapshot_observed_at":"2026-07-06T23:12:52.141592Z","submitted_at":"2026-04-30T04:16:13Z","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-07T08:02:49.168872Z"},"links":{"citing_paper":"/paper/2604.27405"},"observation_digest":"sha256:eeeb0b7a792be86b741dc510c4ca5628a465d0a95caa3f11caed75ea22c58be0","observation_id":"76e9b7d9-eb75-43b7-a72c-423c0acb1dcf","resolution":{"observed_at":"2026-05-27T09:13:52.231365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-06-05T21:23:00.469572Z","title":"InAdvances in Neural Information Processing Systems","venue":null,"work_id":"84e6ce91-d0cb-4a56-8342-4111d6deb119","year":null},"citing_paper":{"arxiv_id":"2604.27405","last_updated":"2026-04-30T04:16:13Z","snapshot_observed_at":"2026-07-06T23:12:52.141592Z","submitted_at":"2026-04-30T04:16:13Z","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-07T08:02:49.168872Z"},"links":{"citing_paper":"/paper/2604.27405"},"observation_digest":"sha256:71ffec0434f1f87b66ffbf4e65af3f3508423e4ad0c30977b5cc1927eeda2ac8","observation_id":"b6584e4d-1a75-43b8-b2f4-97479d74664a","resolution":{"observed_at":"2026-05-27T09:13:52.235793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03461","last_updated":"2025-02-05T18:58:19Z","snapshot_observed_at":"2026-08-10T16:22:07.766175Z","submitted_at":"2025-02-05T18:58:19Z","title":"Do Large Language Model Benchmarks Test Reliability?","version":1},"cited_work":{"arxiv_id":"2502.03461","doi":"10.48550/arxiv.2502.03461","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.03461","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Do large language model benchmarks test reliability?","venue":"ArXiv.org","work_id":"11771fd3-b9c9-4098-a437-00e057657bb7","year":2025},"citing_paper":{"arxiv_id":"2604.27405","last_updated":"2026-04-30T04:16:13Z","snapshot_observed_at":"2026-07-06T23:12:52.141592Z","submitted_at":"2026-04-30T04:16:13Z","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-07T08:02:49.168872Z"},"links":{"cited_paper":"/paper/2502.03461","citing_paper":"/paper/2604.27405"},"observation_digest":"sha256:bb3744b51ac9a1eb05c72374de1bd2c80cb25cb30f780151c8dce463fce486ae","observation_id":"24f5328d-8cc5-4a49-9c81-d91b044b41d4","resolution":{"observed_at":"2026-05-12T10:06:27.313724Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.10512","last_updated":"2025-05-08T03:45:24Z","snapshot_observed_at":"2026-07-06T15:43:54.377120Z","submitted_at":"2023-06-18T09:54:33Z","title":"Position: AI Evaluation Should Learn from How We Test Humans","version":4},"cited_work":{"arxiv_id":"2306.10512","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.10512","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"From static benchmarks to adaptive testing: Psychometrics in ai evaluation","venue":null,"work_id":"7ee4296f-47ac-46d5-8d9d-b833e4f618d4","year":2023},"citing_paper":{"arxiv_id":"2604.27405","last_updated":"2026-04-30T04:16:13Z","snapshot_observed_at":"2026-07-06T23:12:52.141592Z","submitted_at":"2026-04-30T04:16:13Z","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-07T08:02:49.168872Z"},"links":{"cited_paper":"/paper/2306.10512","citing_paper":"/paper/2604.27405"},"observation_digest":"sha256:b2d24298a5179580edb7e5c03472a8be4622274c81c6178d76b51f4faa074fbd","observation_id":"5504ef60-7b19-44d4-9713-039aaca1b0b4","resolution":{"observed_at":"2026-05-12T10:06:27.320015Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.27405","last_updated":"2026-04-30T04:16:13Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T23:12:52.141592Z","submitted_at":"2026-04-30T04:16:13Z","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":1,"verified_fuzzy":2},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2604.27405."}