{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VV4EJOMAMVXFYYYJYXNVGLZSGS","short_pith_number":"pith:VV4EJOMA","schema_version":"1.0","canonical_sha256":"ad7844b980656e5c6309c5db532f32349b6e85bac32e00b7d0907df4cebce160","source":{"kind":"arxiv","id":"2404.13945","version":3},"attestation_state":"computed","paper":{"title":"How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ao Sun, Daoyuan Wu, Liwen Wang, Pingchuan Ma, Shuai Wang, Yuanyuan Yuan, Zongjie Li","submitted_at":"2024-04-22T07:41:41Z","abstract_excerpt":"Visual deep learning (VDL) systems have shown significant success in real-world applications like image recognition, object detection, and autonomous driving. To evaluate the reliability of VDL, a mainstream approach is software testing, which requires diverse mutations over image semantics. The rapid development of multi-modal large language models (MLLMs) has introduced revolutionary image mutation potentials through instruction-driven methods. Users can now freely describe desired mutations and let MLLMs generate the mutated images. Hence, parallel to large language models' (LLMs) recent su"},"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":"2404.13945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-04-22T07:41:41Z","cross_cats_sorted":[],"title_canon_sha256":"884b76310528d6247046cc53432bccd21bb446be9622a2144a1d5265f7e11b9b","abstract_canon_sha256":"0f6b91070adc0ecffa41093f898b76dcb19e5d0d26d478d3bac0a7e0fd1123b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:00.869233Z","signature_b64":"S+2U4aiGX6il6c3iW5EB0VFKs+ICu2BlXz38hULb0+Y1uUckg0bwiK2bzDyKtMXi4y8QyLkeBs03A1nKH6wvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad7844b980656e5c6309c5db532f32349b6e85bac32e00b7d0907df4cebce160","last_reissued_at":"2026-07-05T09:53:00.868768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:00.868768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ao Sun, Daoyuan Wu, Liwen Wang, Pingchuan Ma, Shuai Wang, Yuanyuan Yuan, Zongjie Li","submitted_at":"2024-04-22T07:41:41Z","abstract_excerpt":"Visual deep learning (VDL) systems have shown significant success in real-world applications like image recognition, object detection, and autonomous driving. To evaluate the reliability of VDL, a mainstream approach is software testing, which requires diverse mutations over image semantics. The rapid development of multi-modal large language models (MLLMs) has introduced revolutionary image mutation potentials through instruction-driven methods. Users can now freely describe desired mutations and let MLLMs generate the mutated images. Hence, parallel to large language models' (LLMs) recent su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13945","kind":"arxiv","version":3},"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/2404.13945/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":"2404.13945","created_at":"2026-07-05T09:53:00.868823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13945v3","created_at":"2026-07-05T09:53:00.868823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13945","created_at":"2026-07-05T09:53:00.868823+00:00"},{"alias_kind":"pith_short_12","alias_value":"VV4EJOMAMVXF","created_at":"2026-07-05T09:53:00.868823+00:00"},{"alias_kind":"pith_short_16","alias_value":"VV4EJOMAMVXFYYYJ","created_at":"2026-07-05T09:53:00.868823+00:00"},{"alias_kind":"pith_short_8","alias_value":"VV4EJOMA","created_at":"2026-07-05T09:53:00.868823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19307","citing_title":"MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS","json":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS.json","graph_json":"https://pith.science/api/pith-number/VV4EJOMAMVXFYYYJYXNVGLZSGS/graph.json","events_json":"https://pith.science/api/pith-number/VV4EJOMAMVXFYYYJYXNVGLZSGS/events.json","paper":"https://pith.science/paper/VV4EJOMA"},"agent_actions":{"view_html":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS","download_json":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS.json","view_paper":"https://pith.science/paper/VV4EJOMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13945&json=true","fetch_graph":"https://pith.science/api/pith-number/VV4EJOMAMVXFYYYJYXNVGLZSGS/graph.json","fetch_events":"https://pith.science/api/pith-number/VV4EJOMAMVXFYYYJYXNVGLZSGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS/action/storage_attestation","attest_author":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS/action/author_attestation","sign_citation":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS/action/citation_signature","submit_replication":"https://pith.science/pith/VV4EJOMAMVXFYYYJYXNVGLZSGS/action/replication_record"}},"created_at":"2026-07-05T09:53:00.868823+00:00","updated_at":"2026-07-05T09:53:00.868823+00:00"}