{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UAJHP7IZ2CDO77ZPHZ36WVJQD5","short_pith_number":"pith:UAJHP7IZ","schema_version":"1.0","canonical_sha256":"a01277fd19d086efff2f3e77eb55301f41b11c356131d985e8f7c16be7f377e8","source":{"kind":"arxiv","id":"2409.18023","version":2},"attestation_state":"computed","paper":{"title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannah Sterz, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2024-09-26T16:31:50Z","abstract_excerpt":"Vision Language Models (VLMs) extend remarkable capabilities of text-only large language models and vision-only models, and are able to learn from and process multi-modal vision-text input. While modern VLMs perform well on a number of standard image classification and image-text matching tasks, they still struggle with a number of crucial vision-language (VL) reasoning abilities such as counting and spatial reasoning. Moreover, while they might be very brittle to small variations in instructions and/or evaluation protocols, existing benchmarks fail to evaluate their robustness (or rather the "},"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":"2409.18023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:31:50Z","cross_cats_sorted":[],"title_canon_sha256":"64dfe6edb5692c1ea62d1e75273a57c6387c32fa1fc036b95616d7a7ef762ff9","abstract_canon_sha256":"c32cdf6ff18ec69246ac7a2e41157f9d05d25b931816376282d2d2ae57860810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:31.536886Z","signature_b64":"gY4OCwlhB9m06QIoqYCPKl+AV4Kd0sKY7/2BdlVbWOtVJDRfP5Fzru/lV/gyY4ZhIvinmfnGRvvcAhu2rgH+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a01277fd19d086efff2f3e77eb55301f41b11c356131d985e8f7c16be7f377e8","last_reissued_at":"2026-07-05T11:40:31.536393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:31.536393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannah Sterz, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2024-09-26T16:31:50Z","abstract_excerpt":"Vision Language Models (VLMs) extend remarkable capabilities of text-only large language models and vision-only models, and are able to learn from and process multi-modal vision-text input. While modern VLMs perform well on a number of standard image classification and image-text matching tasks, they still struggle with a number of crucial vision-language (VL) reasoning abilities such as counting and spatial reasoning. Moreover, while they might be very brittle to small variations in instructions and/or evaluation protocols, existing benchmarks fail to evaluate their robustness (or rather the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18023","kind":"arxiv","version":2},"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/2409.18023/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":"2409.18023","created_at":"2026-07-05T11:40:31.536450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18023v2","created_at":"2026-07-05T11:40:31.536450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18023","created_at":"2026-07-05T11:40:31.536450+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAJHP7IZ2CDO","created_at":"2026-07-05T11:40:31.536450+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAJHP7IZ2CDO77ZP","created_at":"2026-07-05T11:40:31.536450+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAJHP7IZ","created_at":"2026-07-05T11:40:31.536450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5","json":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5.json","graph_json":"https://pith.science/api/pith-number/UAJHP7IZ2CDO77ZPHZ36WVJQD5/graph.json","events_json":"https://pith.science/api/pith-number/UAJHP7IZ2CDO77ZPHZ36WVJQD5/events.json","paper":"https://pith.science/paper/UAJHP7IZ"},"agent_actions":{"view_html":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5","download_json":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5.json","view_paper":"https://pith.science/paper/UAJHP7IZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18023&json=true","fetch_graph":"https://pith.science/api/pith-number/UAJHP7IZ2CDO77ZPHZ36WVJQD5/graph.json","fetch_events":"https://pith.science/api/pith-number/UAJHP7IZ2CDO77ZPHZ36WVJQD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5/action/storage_attestation","attest_author":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5/action/author_attestation","sign_citation":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5/action/citation_signature","submit_replication":"https://pith.science/pith/UAJHP7IZ2CDO77ZPHZ36WVJQD5/action/replication_record"}},"created_at":"2026-07-05T11:40:31.536450+00:00","updated_at":"2026-07-05T11:40:31.536450+00:00"}