{"as_of":"2026-08-14T02:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cb60e156c981201632aa773f045527f4d8422d8f165d0246a43f49e6d0091798","coverage":[{"denominator":2,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:23:27.757486Z","state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2507.14207/citation-record","integrity":"/paper/2507.14207/integrity","json":"/paper/2507.14207/citation-record.json","paper":"/paper/2507.14207"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:23:27.841667Z","title":"Training Compute of Frontier AI Models Grows by 4-5x per Year","venue":null,"work_id":"56937a06-2be0-42d1-a79e-139e6b303e78","year":2023},"citing_paper":{"arxiv_id":"2507.14207","last_updated":"2025-07-15T07:23:19Z","snapshot_observed_at":"2026-08-13T01:24:10.029596Z","submitted_at":"2025-07-15T07:23:19Z","title":"Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:23:27.707901Z"},"links":{"citing_paper":"/paper/2507.14207"},"observation_digest":"sha256:66774c94b5182b1b1c308e601ca861fc89f777f656f1357ddbc42841d61bfbea","observation_id":"5fbfe846-66af-4bc8-961e-5f4def5cc5f3","resolution":{"observed_at":"2026-08-06T17:23:27.876005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15041","last_updated":"2023-05-24T11:27:59Z","snapshot_observed_at":"2026-08-13T11:34:34.203262Z","submitted_at":"2023-05-24T11:27:59Z","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15041","snapshot_observed_at":"2026-08-06T17:23:27.757486Z","title":"500− T r i a lE x p e r i m e n tSummary","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.14207","last_updated":"2025-07-15T07:23:19Z","snapshot_observed_at":"2026-08-13T01:24:10.029596Z","submitted_at":"2025-07-15T07:23:19Z","title":"Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:23:27.757486Z"},"links":{"cited_paper":"/paper/2305.15041","citing_paper":"/paper/2507.14207"},"observation_digest":"sha256:2b9bef5bafc4b2a228ada0a0d968083f23ad648484581215e5192c4fb18415ee","observation_id":"2306a272-fc10-491b-98a4-90e2bf3eb8cd","resolution":{"observed_at":"2026-08-06T17:23:27.757486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.14207","last_updated":"2025-07-15T07:23:19Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-13T01:24:10.029596Z","submitted_at":"2025-07-15T07:23:19Z","title":"Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design"},"reference_resolution":{"displayed":2,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":2},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 0 inbound Pith citation observations for arXiv:2507.14207."}