{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X3PHAEEZGKYOM2HS4R3UGRZGIS","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":"4cd1f6128939422f37061f2b587864dd5dedcbcec76a88a314bf580ccaa1b836","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T07:15:09Z","title_canon_sha256":"0b608cb1c98107f09753df470ab5f3a9b91093cc9fe11f44f41af1838b99ad23"},"schema_version":"1.0","source":{"id":"2410.21802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21802","created_at":"2026-07-05T09:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21802v2","created_at":"2026-07-05T09:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21802","created_at":"2026-07-05T09:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"X3PHAEEZGKYO","created_at":"2026-07-05T09:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"X3PHAEEZGKYOM2HS","created_at":"2026-07-05T09:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"X3PHAEEZ","created_at":"2026-07-05T09:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:51a72a34618f1d8cf8d34200c42a17bc212da302bad2aa9276cf233c38cb4222","target":"graph","created_at":"2026-07-05T09:28:14Z","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/2410.21802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: the Attention Refinement module and the A","authors_text":"Changsheng Xu, Haiyang Zhang, Lu Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T07:15:09Z","title":"Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21802","kind":"arxiv","version":2},"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":"sha256:2002c4e294bb36f28ea1f8ebd91d4bbfd7e4e41a536cc30c5f13b686635f5909","target":"record","created_at":"2026-07-05T09:28:14Z","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":"4cd1f6128939422f37061f2b587864dd5dedcbcec76a88a314bf580ccaa1b836","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T07:15:09Z","title_canon_sha256":"0b608cb1c98107f09753df470ab5f3a9b91093cc9fe11f44f41af1838b99ad23"},"schema_version":"1.0","source":{"id":"2410.21802","kind":"arxiv","version":2}},"canonical_sha256":"bede70109932b0e668f2e47743472644a2abecd4d3146e53354ae3c852171950","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bede70109932b0e668f2e47743472644a2abecd4d3146e53354ae3c852171950","first_computed_at":"2026-07-05T09:28:14.651962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:14.651962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C0Q7PxMGIjrShVPocwWEL47FW9Pb1of+rNk7jWhfkb/awdWPqthGsKHCoZSmBzSZPjOFKNzqd2XyKt0sn0iUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:14.652411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2002c4e294bb36f28ea1f8ebd91d4bbfd7e4e41a536cc30c5f13b686635f5909","sha256:51a72a34618f1d8cf8d34200c42a17bc212da302bad2aa9276cf233c38cb4222"],"state_sha256":"b87de71c76b0a67c38ed23540774642b1b48fb36db2fe7bf5e70fe57c88416b0"}