{"as_of":"2026-08-15T21:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:92be2e0652559d4a1c9fca3792bc4604ce3b8325181e194aeb66e7ad3228ee4d","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":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":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T11:40:13.907632Z","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":"2026-05-22T23:10:41.139960Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.06003","last_updated":"2024-04-09T04:17:51Z","snapshot_observed_at":"2026-08-15T17:00:19.914157Z","submitted_at":"2024-04-09T04:17:51Z","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","version":1},"cited_work":{"arxiv_id":"2404.06003","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.06003","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"24396527-9def-4b34-805a-753e8531e423","year":2024},"citing_paper":{"arxiv_id":"2406.04244","last_updated":"2024-06-06T16:41:39Z","snapshot_observed_at":"2026-07-30T15:43:06.151242Z","submitted_at":"2024-06-06T16:41:39Z","title":"Benchmark Data Contamination of Large Language Models: A Survey","version":1},"reference_index":175,"source":"pdf_text","source_observed_at":"2026-05-22T23:10:40.420241Z"},"links":{"cited_paper":"/paper/2404.06003","citing_paper":"/paper/2406.04244"},"observation_digest":"sha256:f10b8502a1c0dc5dc7d02434b5defc20634d4efdc8e997a7a1516d389bf92fc0","observation_id":"a3c7e143-51de-4d68-9ec0-e218f84b6280","resolution":{"observed_at":"2026-05-22T23:10:41.142309Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06003","last_updated":"2024-04-09T04:17:51Z","snapshot_observed_at":"2026-08-15T17:00:19.914157Z","submitted_at":"2024-04-09T04:17:51Z","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06003","snapshot_observed_at":"2026-08-11T11:40:13.907632Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.15118","last_updated":"2025-06-06T12:13:42Z","snapshot_observed_at":"2026-08-13T12:39:00.588330Z","submitted_at":"2024-12-19T17:59:42Z","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","version":2},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-11T11:40:13.907632Z"},"links":{"cited_paper":"/paper/2404.06003","citing_paper":"/paper/2412.15118"},"observation_digest":"sha256:c553cf5445c0221d7b9cc4a9846daa6caf93a9547be777c4f71cd7bfd62601e2","observation_id":"7dca7866-e9b6-499c-960e-481489b1c060","resolution":{"observed_at":"2026-08-11T11:40:13.907632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06003","last_updated":"2024-04-09T04:17:51Z","snapshot_observed_at":"2026-08-15T17:00:19.914157Z","submitted_at":"2024-04-09T04:17:51Z","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06003","snapshot_observed_at":"2026-08-07T11:04:07.109652Z","title":"Freeeval: A modular framework for trustworthy and efficient evaluation of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03637","last_updated":"2025-07-07T09:53:22Z","snapshot_observed_at":"2026-08-08T03:23:19.289933Z","submitted_at":"2025-06-04T07:30:16Z","title":"RewardAnything: Generalizable Principle-Following Reward Models","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T11:04:07.109652Z"},"links":{"cited_paper":"/paper/2404.06003","citing_paper":"/paper/2506.03637"},"observation_digest":"sha256:3217051b64c67f903fa4e0ac5e4eb75eeb398de98bb6e6f3aec9ba576396acc9","observation_id":"aac12416-9c89-4f07-a085-38a7e4404567","resolution":{"observed_at":"2026-08-07T11:04:07.109652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06003","last_updated":"2024-04-09T04:17:51Z","snapshot_observed_at":"2026-08-15T17:00:19.914157Z","submitted_at":"2024-04-09T04:17:51Z","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06003","snapshot_observed_at":"2026-08-05T12:04:08.940093Z","title":"Freeeval: A modular framework for trustworthy and efficient evaluation of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.04504","last_updated":"2025-09-02T07:03:20Z","snapshot_observed_at":"2026-08-05T12:04:06.559550Z","submitted_at":"2025-09-02T07:03:20Z","title":"Behavioral Fingerprinting of Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T12:04:08.940093Z"},"links":{"cited_paper":"/paper/2404.06003","citing_paper":"/paper/2509.04504"},"observation_digest":"sha256:261098d9d4673c7314988aa04f3c3bed509d9c59fd12072bbc4cc04734553773","observation_id":"0c2c9326-3176-47d3-bd94-fa9397f04101","resolution":{"observed_at":"2026-08-05T12:04:08.940093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.06003/citation-record","integrity":"/paper/2404.06003/integrity","json":"/paper/2404.06003/citation-record.json","paper":"/paper/2404.06003"},"outbound":[],"paper":{"arxiv_id":"2404.06003","last_updated":"2024-04-09T04:17:51Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T17:00:19.914157Z","submitted_at":"2024-04-09T04:17:51Z","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2404.06003."}