{"as_of":"2026-08-14T14:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8c55b8c0468f31e7b87fede89b923342f1176ae5b4cc1efa92e6b7e8a4d633c2","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":"2026-08-14T06:32:32.682623+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":"2026-08-04T19:55:56.544665Z","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":"2026-06-29T17:03:40.890684Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.09785","last_updated":"2024-04-15T13:40:08Z","snapshot_observed_at":"2026-08-13T00:29:53.889623Z","submitted_at":"2024-04-15T13:40:08Z","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.09785","snapshot_observed_at":"2026-08-04T19:55:56.544665Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.08997","last_updated":"2025-09-10T20:47:56Z","snapshot_observed_at":"2026-08-08T06:23:27.336190Z","submitted_at":"2025-09-10T20:47:56Z","title":"YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T19:55:56.544665Z"},"links":{"cited_paper":"/paper/2404.09785","citing_paper":"/paper/2509.08997"},"observation_digest":"sha256:b67b08000b1371916dbb17d06f869c3eb763a31c9aefe057c0e3eba1e0d43fd7","observation_id":"bbabf8bd-3ce8-43a6-8cc9-f882708e390f","resolution":{"observed_at":"2026-08-04T19:55:56.544665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.09785","last_updated":"2024-04-15T13:40:08Z","snapshot_observed_at":"2026-08-13T00:29:53.889623Z","submitted_at":"2024-04-15T13:40:08Z","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","version":1},"cited_work":{"arxiv_id":"2404.09785","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.09785","snapshot_observed_at":"2026-06-29T17:03:40.890684Z","title":"arXiv preprint arXiv:2404.09785 , year=","venue":null,"work_id":"5a039cf0-137b-4352-adb8-27b517cb38ca","year":2024},"citing_paper":{"arxiv_id":"2605.12201","last_updated":"2026-05-12T14:40:29Z","snapshot_observed_at":"2026-08-14T07:55:57.003242Z","submitted_at":"2026-05-12T14:40:29Z","title":"Uncertainty Quantification for LLM-based Code Generation","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-05-13T04:01:31.679818Z"},"links":{"cited_paper":"/paper/2404.09785","citing_paper":"/paper/2605.12201"},"observation_digest":"sha256:c0edfc9963e4b2554ffb850a492fdd8e8357f556f70dfa6d9657c4dd4f52e4fe","observation_id":"542a737c-fd6d-42f2-b523-dae0c1989601","resolution":{"observed_at":"2026-05-13T04:02:13.056403Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.09785","last_updated":"2024-04-15T13:40:08Z","snapshot_observed_at":"2026-08-13T00:29:53.889623Z","submitted_at":"2024-04-15T13:40:08Z","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","version":1},"cited_work":{"arxiv_id":"2404.09785","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.09785","snapshot_observed_at":"2026-06-29T17:03:40.890684Z","title":"arXiv preprint arXiv:2404.09785 , year=","venue":null,"work_id":"5a039cf0-137b-4352-adb8-27b517cb38ca","year":2024},"citing_paper":{"arxiv_id":"2605.26942","last_updated":"2026-05-29T12:41:29Z","snapshot_observed_at":"2026-08-08T23:59:34.511470Z","submitted_at":"2026-05-26T12:32:17Z","title":"Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-29T16:59:53.490989Z"},"links":{"cited_paper":"/paper/2404.09785","citing_paper":"/paper/2605.26942"},"observation_digest":"sha256:944eb54ef46ad89f84281fb8ea756a5bc18551e429c41dfc63b1a207753fb623","observation_id":"11a5c1e0-25ea-4c1a-8d37-3839b25b65fd","resolution":{"observed_at":"2026-06-29T17:03:40.892079Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.09785/citation-record","integrity":"/paper/2404.09785/integrity","json":"/paper/2404.09785/citation-record.json","paper":"/paper/2404.09785"},"outbound":[],"paper":{"arxiv_id":"2404.09785","last_updated":"2024-04-15T13:40:08Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-13T00:29:53.889623Z","submitted_at":"2024-04-15T13:40:08Z","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2404.09785."}