{"as_of":"2026-08-06T01:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1c6e7d8d68766a4154a48479dd146a89cd8ba388ba59d8d5006fcb511947ec03","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":"2026-08-05T06:32:48.257954+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":"2026-08-03T16:56:24.825344Z","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":"2026-05-15T17:26:22.106095Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.12823","last_updated":"2024-07-02T12:07:38Z","snapshot_observed_at":"2026-07-06T18:48:00.070861Z","submitted_at":"2024-07-02T12:07:38Z","title":"WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.12823","snapshot_observed_at":"2026-08-03T16:56:24.825344Z","title":"Wtu- eval: A whether-or-not tool usage evaluation benchmark for large language models.arXiv preprint arXiv:2407.12823, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.11935","last_updated":"2026-07-07T18:58:00Z","snapshot_observed_at":"2026-08-03T16:56:14.633932Z","submitted_at":"2025-12-12T06:28:28Z","title":"AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T16:56:24.825344Z"},"links":{"cited_paper":"/paper/2407.12823","citing_paper":"/paper/2512.11935"},"observation_digest":"sha256:1353977b495c4b2031eada22cc8ab4a26db57540be84d5398b41c25157cbb2dc","observation_id":"f3724a34-b6fe-4ef0-a8cf-04b09d6de3dc","resolution":{"observed_at":"2026-08-03T16:56:24.825344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12823","last_updated":"2024-07-02T12:07:38Z","snapshot_observed_at":"2026-07-06T18:48:00.070861Z","submitted_at":"2024-07-02T12:07:38Z","title":"WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models","version":1},"cited_work":{"arxiv_id":"2407.12823","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.12823","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ning, K., Su, Y ., Lv, X., Zhang, Y ., Liu, J., Liu, K., and Xu, J","venue":null,"work_id":"9f405ae5-4234-4b05-ace9-1806bcc8d22b","year":2024},"citing_paper":{"arxiv_id":"2604.19749","last_updated":"2026-03-03T08:55:55Z","snapshot_observed_at":"2026-07-06T23:06:21.774788Z","submitted_at":"2026-03-03T08:55:55Z","title":"The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-15T17:25:58.875055Z"},"links":{"cited_paper":"/paper/2407.12823","citing_paper":"/paper/2604.19749"},"observation_digest":"sha256:f1ab5fdeab2cbc34f197823773173fad664116a25740216bf5ba76388c5c72a9","observation_id":"201dadd7-5a20-47cd-905d-9eac6ec4efab","resolution":{"observed_at":"2026-05-15T17:26:22.109894Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12823","last_updated":"2024-07-02T12:07:38Z","snapshot_observed_at":"2026-07-06T18:48:00.070861Z","submitted_at":"2024-07-02T12:07:38Z","title":"WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models","version":1},"cited_work":{"arxiv_id":"2407.12823","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.12823","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ning, K., Su, Y ., Lv, X., Zhang, Y ., Liu, J., Liu, K., and Xu, J","venue":null,"work_id":"9f405ae5-4234-4b05-ace9-1806bcc8d22b","year":2024},"citing_paper":{"arxiv_id":"2605.09544","last_updated":"2026-05-10T13:56:46Z","snapshot_observed_at":"2026-07-31T07:40:23.585067Z","submitted_at":"2026-05-10T13:56:46Z","title":"TIDE-Bench: Task-Aware and Diagnostic Evaluation of Tool-Integrated Reasoning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-12T02:47:31.830410Z"},"links":{"cited_paper":"/paper/2407.12823","citing_paper":"/paper/2605.09544"},"observation_digest":"sha256:38c9b13e84f1960d8eb70a1dc6ad100838b62506b75c43a7a712c0bafa68828e","observation_id":"3193dece-5d4d-4a79-bc06-453ba78448c9","resolution":{"observed_at":"2026-05-12T07:31:23.915767Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.12823/citation-record","integrity":"/paper/2407.12823/integrity","json":"/paper/2407.12823/citation-record.json","paper":"/paper/2407.12823"},"outbound":[],"paper":{"arxiv_id":"2407.12823","last_updated":"2024-07-02T12:07:38Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:48:00.070861Z","submitted_at":"2024-07-02T12:07:38Z","title":"WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for 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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2407.12823."}