{"as_of":"2026-08-18T02:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:51df57c533978b422273e01c2b1f0e73f0468ad7a38e32903cf23e26a4c34312","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":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":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:54:33.816350Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-11T23:42:15.372587Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.17787","last_updated":"2024-06-10T10:07:24Z","snapshot_observed_at":"2026-08-16T14:06:13.850035Z","submitted_at":"2024-03-26T15:20:49Z","title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.17787","snapshot_observed_at":"2026-08-12T05:54:33.816350Z","title":"arXiv preprint arXiv:2403.17787 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00166","last_updated":"2024-11-29T14:42:23Z","snapshot_observed_at":"2026-08-16T06:49:48.135986Z","submitted_at":"2024-11-29T14:42:23Z","title":"To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:54:33.816350Z"},"links":{"cited_paper":"/paper/2403.17787","citing_paper":"/paper/2412.00166"},"observation_digest":"sha256:e40a9a6a80079ac7c9ba88a51145101c10fcfe91f17233c6d5a8077d6a352e10","observation_id":"ae79573f-fe21-4444-adb4-2bd8db301d50","resolution":{"observed_at":"2026-08-12T05:54:33.816350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17787","last_updated":"2024-06-10T10:07:24Z","snapshot_observed_at":"2026-08-16T14:06:13.850035Z","submitted_at":"2024-03-26T15:20:49Z","title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications","version":2},"cited_work":{"arxiv_id":"2403.17787","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.17787","snapshot_observed_at":"2026-08-11T23:42:15.372587Z","title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications","venue":"cs.AI","work_id":"a4c1b0c5-0083-438f-a448-178731c37586","year":2024},"citing_paper":{"arxiv_id":"2412.02301","last_updated":"2024-12-03T09:13:52Z","snapshot_observed_at":"2026-08-14T11:21:19.869611Z","submitted_at":"2024-12-03T09:13:52Z","title":"Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T23:42:15.220128Z"},"links":{"cited_paper":"/paper/2403.17787","citing_paper":"/paper/2412.02301"},"observation_digest":"sha256:9130fc3c3cafecb65aac23b08355681f8d8f97d25d988223794b3ba7317b0869","observation_id":"40b50884-ed7d-44ce-93b2-2d6aded5ff33","resolution":{"observed_at":"2026-08-11T23:42:15.378820Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.17787/citation-record","integrity":"/paper/2403.17787/integrity","json":"/paper/2403.17787/citation-record.json","paper":"/paper/2403.17787"},"outbound":[],"paper":{"arxiv_id":"2403.17787","last_updated":"2024-06-10T10:07:24Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T14:06:13.850035Z","submitted_at":"2024-03-26T15:20:49Z","title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.17787."}