{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QITTRFOIUVPPRFCBHCQDGHN563","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":"a5694f55668cb96c2d61c6bb3c95b2abf1bc768c18acdfbb9e7dd4114e7d9b6b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-15T10:04:27Z","title_canon_sha256":"55d028c7056b368deb6172e31dfb9d83e2317b2475c297f24d384d68e5003567"},"schema_version":"1.0","source":{"id":"2507.11155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11155","created_at":"2026-07-05T11:37:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11155v1","created_at":"2026-07-05T11:37:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11155","created_at":"2026-07-05T11:37:33Z"},{"alias_kind":"pith_short_12","alias_value":"QITTRFOIUVPP","created_at":"2026-07-05T11:37:33Z"},{"alias_kind":"pith_short_16","alias_value":"QITTRFOIUVPPRFCB","created_at":"2026-07-05T11:37:33Z"},{"alias_kind":"pith_short_8","alias_value":"QITTRFOI","created_at":"2026-07-05T11:37:33Z"}],"graph_snapshots":[{"event_id":"sha256:691dffb2fff13ff881b3fbdfb884bc05b4cf33db8aa93708383f76abfebf07ab","target":"graph","created_at":"2026-07-05T11:37:33Z","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/2507.11155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various unsafe concepts when presented in different modalities, such as text and images. To address this, we first compile the UnsafeConcepts dataset, featuring 75 unsafe concepts, i.e., ``Swastika,'' ``Sexual Harassment,'' and ``Assaults,'' along with associated 1.5K images. We then conduct a systematic evaluation of VLMs' perception (concept recognition) and alignment","authors_text":"Michael Backes, Yang Zhang, Yiting Qu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-15T10:04:27Z","title":"Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11155","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:e973624a0b7216a5742a6c58226b49ed45a8d7493b87bb30eefebbb6bbd5026f","target":"record","created_at":"2026-07-05T11:37:33Z","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":"a5694f55668cb96c2d61c6bb3c95b2abf1bc768c18acdfbb9e7dd4114e7d9b6b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-15T10:04:27Z","title_canon_sha256":"55d028c7056b368deb6172e31dfb9d83e2317b2475c297f24d384d68e5003567"},"schema_version":"1.0","source":{"id":"2507.11155","kind":"arxiv","version":1}},"canonical_sha256":"82273895c8a55ef8944138a0331dbdf6c856b94eba3840ced7574aa8117d3deb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82273895c8a55ef8944138a0331dbdf6c856b94eba3840ced7574aa8117d3deb","first_computed_at":"2026-07-05T11:37:33.371285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:33.371285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qofYiiyRyoibDOjK85DAE8+cFYMHrSAcPPS2RkymSGyyGIwWpIQs28CaI9eTT/W0bsU3cAZYXFQOtwCMOqz8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:33.371724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e973624a0b7216a5742a6c58226b49ed45a8d7493b87bb30eefebbb6bbd5026f","sha256:691dffb2fff13ff881b3fbdfb884bc05b4cf33db8aa93708383f76abfebf07ab"],"state_sha256":"58d841cf7eedce34c5c8780554b7c92a27dd32270cbbde136cb84aac52d996d9"}