{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6WDWNNI64E4FQ5EFIIHVGCVPFK","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":"3436a29586edd0924a8329b35aebd3350b0e7659ad5aab506f6894e146da23ac","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-24T17:48:04Z","title_canon_sha256":"375b085ad16e461668133dae7879be8582c1bb9e6254a3daa59e8f8ef73904ce"},"schema_version":"1.0","source":{"id":"2310.16033","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16033","created_at":"2026-07-05T07:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16033v3","created_at":"2026-07-05T07:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16033","created_at":"2026-07-05T07:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"6WDWNNI64E4F","created_at":"2026-07-05T07:43:56Z"},{"alias_kind":"pith_short_16","alias_value":"6WDWNNI64E4FQ5EF","created_at":"2026-07-05T07:43:56Z"},{"alias_kind":"pith_short_8","alias_value":"6WDWNNI6","created_at":"2026-07-05T07:43:56Z"}],"graph_snapshots":[{"event_id":"sha256:5922f028476882c27f5dcaf8fd60ff18be1cabb9062da885a0ee34ff98d8833e","target":"graph","created_at":"2026-07-05T07:43:56Z","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/2310.16033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream applications and domains. Given the great potential for the broad use of these models, it is important to investigate their limitations in dealing with different image and question properties. In this work, we investigate whether MLLMs can perceive small details as well as large details in images. In particular, we show that their zero-shot accuracy in answering visual questions is very sensitive to the size of the vi","authors_text":"Filip Ilievski, Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-24T17:48:04Z","title":"Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16033","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:ce999fdd87cd39828b485d5953c05bb9ab280f1edd75592fc7ad4bbbb7c74fb7","target":"record","created_at":"2026-07-05T07:43:56Z","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":"3436a29586edd0924a8329b35aebd3350b0e7659ad5aab506f6894e146da23ac","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-24T17:48:04Z","title_canon_sha256":"375b085ad16e461668133dae7879be8582c1bb9e6254a3daa59e8f8ef73904ce"},"schema_version":"1.0","source":{"id":"2310.16033","kind":"arxiv","version":3}},"canonical_sha256":"f58766b51ee138587485420f530aaf2abab073aa4aedd25dce55572dde0a2cf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f58766b51ee138587485420f530aaf2abab073aa4aedd25dce55572dde0a2cf5","first_computed_at":"2026-07-05T07:43:56.866463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:56.866463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WegikQUbGfEPsNTkCAKGoXpFj3d67qtaMzefABiNMd8UAixlh9e8uatSMdND3m95EAkTj5LLtt/mbHN6YHUTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:56.866881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16033","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce999fdd87cd39828b485d5953c05bb9ab280f1edd75592fc7ad4bbbb7c74fb7","sha256:5922f028476882c27f5dcaf8fd60ff18be1cabb9062da885a0ee34ff98d8833e"],"state_sha256":"94faa76f4ac460bf856c7bb3d29f8ef37ba732e1c2011af98752fa7276e07d30"}