{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UGRJ44EBUYHCSALADSWDTUKBQ5","short_pith_number":"pith:UGRJ44EB","schema_version":"1.0","canonical_sha256":"a1a29e7081a60e2901601cac39d141876ddc7cfed96063e54596086bfcea4c6d","source":{"kind":"arxiv","id":"2403.17787","version":2},"attestation_state":"computed","paper":{"title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ali Chehab, Fouad Trad","submitted_at":"2024-03-26T15:20:49Z","abstract_excerpt":"The success of Large Language Models (LLMs) has led to a parallel rise in the development of Large Multimodal Models (LMMs), which have begun to transform a variety of applications. These sophisticated multimodal models are designed to interpret and analyze complex data by integrating multiple modalities such as text and images, thereby opening new avenues for a range of applications. This paper investigates the applicability and effectiveness of prompt-engineered LMMs that process both images and text, including models such as LLaVA, BakLLaVA, Moondream, Gemini-pro-vision, and GPT-4o, compare"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.17787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-26T15:20:49Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"502b3848794816a252b08ce412144997ab9b6282bb23ac8db6e8f02698b1e2ac","abstract_canon_sha256":"78ecce41a3a6fc938cfbc65dfbedd51f64a415f51a1cf6c9b87c6b2a76793e3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:36.388275Z","signature_b64":"C3o1gfenhTem8vzduKxmApFRVthZExmGuTvdw458Xc4jsBonEIMTFc42sxxw4mAMJibR96z9cvig91Yrjio/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1a29e7081a60e2901601cac39d141876ddc7cfed96063e54596086bfcea4c6d","last_reissued_at":"2026-07-05T11:04:36.387843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:36.387843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ali Chehab, Fouad Trad","submitted_at":"2024-03-26T15:20:49Z","abstract_excerpt":"The success of Large Language Models (LLMs) has led to a parallel rise in the development of Large Multimodal Models (LMMs), which have begun to transform a variety of applications. These sophisticated multimodal models are designed to interpret and analyze complex data by integrating multiple modalities such as text and images, thereby opening new avenues for a range of applications. This paper investigates the applicability and effectiveness of prompt-engineered LMMs that process both images and text, including models such as LLaVA, BakLLaVA, Moondream, Gemini-pro-vision, and GPT-4o, compare"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17787","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.17787/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.17787","created_at":"2026-07-05T11:04:36.387896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17787v2","created_at":"2026-07-05T11:04:36.387896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17787","created_at":"2026-07-05T11:04:36.387896+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGRJ44EBUYHC","created_at":"2026-07-05T11:04:36.387896+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGRJ44EBUYHCSALA","created_at":"2026-07-05T11:04:36.387896+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGRJ44EB","created_at":"2026-07-05T11:04:36.387896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02301","citing_title":"Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5","json":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5.json","graph_json":"https://pith.science/api/pith-number/UGRJ44EBUYHCSALADSWDTUKBQ5/graph.json","events_json":"https://pith.science/api/pith-number/UGRJ44EBUYHCSALADSWDTUKBQ5/events.json","paper":"https://pith.science/paper/UGRJ44EB"},"agent_actions":{"view_html":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5","download_json":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5.json","view_paper":"https://pith.science/paper/UGRJ44EB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17787&json=true","fetch_graph":"https://pith.science/api/pith-number/UGRJ44EBUYHCSALADSWDTUKBQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/UGRJ44EBUYHCSALADSWDTUKBQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5/action/storage_attestation","attest_author":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5/action/author_attestation","sign_citation":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5/action/citation_signature","submit_replication":"https://pith.science/pith/UGRJ44EBUYHCSALADSWDTUKBQ5/action/replication_record"}},"created_at":"2026-07-05T11:04:36.387896+00:00","updated_at":"2026-07-05T11:04:36.387896+00:00"}