{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z2SWVFT5IPSA5EHO6DCULKZNP4","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":"c7f9fe813715de8429a2968995a6445f58fdc6e9f60292c689707e1a511e335d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T18:52:03Z","title_canon_sha256":"96c0e86b9eca1e8e0c7d790f7d8440f8ef3815c5173ef813a82e5b8fb156c983"},"schema_version":"1.0","source":{"id":"2212.08044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08044","created_at":"2026-07-05T07:35:17Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08044v3","created_at":"2026-07-05T07:35:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08044","created_at":"2026-07-05T07:35:17Z"},{"alias_kind":"pith_short_12","alias_value":"Z2SWVFT5IPSA","created_at":"2026-07-05T07:35:17Z"},{"alias_kind":"pith_short_16","alias_value":"Z2SWVFT5IPSA5EHO","created_at":"2026-07-05T07:35:17Z"},{"alias_kind":"pith_short_8","alias_value":"Z2SWVFT5","created_at":"2026-07-05T07:35:17Z"}],"graph_snapshots":[{"event_id":"sha256:4c6692b67de82ab59b58dbcc520f90467941a1972a29658f45c60813f4ca40f6","target":"graph","created_at":"2026-07-05T07:35:17Z","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/2212.08044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal image-text models have shown remarkable performance in the past few years. However, evaluating robustness against distribution shifts is crucial before adopting them in real-world applications. In this work, we investigate the robustness of 12 popular open-sourced image-text models under common perturbations on five tasks (image-text retrieval, visual reasoning, visual entailment, image captioning, and text-to-image generation). In particular, we propose several new multimodal robustness benchmarks by applying 17 image perturbation and 16 text perturbation techniques on top of exist","authors_text":"Bo Li, Ding Zhao, Florian Wenzel, Jielin Qiu, Mu Li, Xingjian Shi, Yi Zhu, Zhiqiang Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T18:52:03Z","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08044","kind":"arxiv","version":3},"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":"sha256:73d8ea4330cbda8cd67e3365672e1f7a77bdeca3158b85ea76d291db2e5881d6","target":"record","created_at":"2026-07-05T07:35:17Z","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":"c7f9fe813715de8429a2968995a6445f58fdc6e9f60292c689707e1a511e335d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T18:52:03Z","title_canon_sha256":"96c0e86b9eca1e8e0c7d790f7d8440f8ef3815c5173ef813a82e5b8fb156c983"},"schema_version":"1.0","source":{"id":"2212.08044","kind":"arxiv","version":3}},"canonical_sha256":"cea56a967d43e40e90eef0c545ab2d7f049e82ff23453362caee163a5ab32c96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cea56a967d43e40e90eef0c545ab2d7f049e82ff23453362caee163a5ab32c96","first_computed_at":"2026-07-05T07:35:17.403006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:17.403006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0LAkHWP5pyM6UncnnERnr1zK8v0NMgCfbcuKPBUFUAMEpqWtrs0qqEso0E1ECWgZNo3mAir6HOLz7KtsXfgeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:17.403503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d8ea4330cbda8cd67e3365672e1f7a77bdeca3158b85ea76d291db2e5881d6","sha256:4c6692b67de82ab59b58dbcc520f90467941a1972a29658f45c60813f4ca40f6"],"state_sha256":"22239e9d6ba382ee6fe5027ebab43e51d3f94119045e9c3d2a5af4bd01935841"}