{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4VWJ56OSVU3YRW7B7G3GN6PVJH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"23eb6b2ea5edc65df8661d7a5f4a2be188a7810577095522cd0c644be735c183","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T23:45:55Z","title_canon_sha256":"57207b9460916f862c1c89fd5323c7b47f53bfb263ab4087705be2cdd357d23a"},"schema_version":"1.0","source":{"id":"2505.22943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22943","created_at":"2026-07-05T11:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22943v1","created_at":"2026-07-05T11:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22943","created_at":"2026-07-05T11:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"4VWJ56OSVU3Y","created_at":"2026-07-05T11:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"4VWJ56OSVU3YRW7B","created_at":"2026-07-05T11:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"4VWJ56OS","created_at":"2026-07-05T11:11:52Z"}],"graph_snapshots":[{"event_id":"sha256:9a97798b53d5d35a368e9afffcef0b37f745ae6b1fcb2ad9584ab165f9c0ca8d","target":"graph","created_at":"2026-07-05T11:11:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.22943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While pre-trained multimodal representations (e.g., CLIP) have shown impressive capabilities, they exhibit significant compositional vulnerabilities leading to counterintuitive judgments. We introduce Multimodal Adversarial Compositionality (MAC), a benchmark that leverages large language models (LLMs) to generate deceptive text samples to exploit these vulnerabilities across different modalities and evaluates them through both sample-wise attack success rate and group-wise entropy-based diversity. To improve zero-shot methods, we propose a self-training approach that leverages rejection-sampl","authors_text":"Dayoon Ko, Gunhee Kim, Heeseung Yun, Jaewoo Ahn","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T23:45:55Z","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22943","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:800fd4482cf38f408e40deb6a99a59c224b27894ef59f47317f0628a84132745","target":"record","created_at":"2026-07-05T11:11:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"23eb6b2ea5edc65df8661d7a5f4a2be188a7810577095522cd0c644be735c183","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T23:45:55Z","title_canon_sha256":"57207b9460916f862c1c89fd5323c7b47f53bfb263ab4087705be2cdd357d23a"},"schema_version":"1.0","source":{"id":"2505.22943","kind":"arxiv","version":1}},"canonical_sha256":"e56c9ef9d2ad3788dbe1f9b666f9f549fcb9010b386d335dee6435bed7c080e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56c9ef9d2ad3788dbe1f9b666f9f549fcb9010b386d335dee6435bed7c080e2","first_computed_at":"2026-07-05T11:11:52.085083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:52.085083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+8+0dCu5NNoTXLlmgwGGDUukZOTxL9m+Oqo/u36GYDagYB24lGLpt0aS5/yVxpjfQkAebbcz+MNv9QSQLQRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:52.085619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:800fd4482cf38f408e40deb6a99a59c224b27894ef59f47317f0628a84132745","sha256:9a97798b53d5d35a368e9afffcef0b37f745ae6b1fcb2ad9584ab165f9c0ca8d"],"state_sha256":"dd5b64df93e9862a4014d92bcd77ae890ebfbcfbae8e53684a2346cb851428e7"}