{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IRFT7PVWVTD7G2CENVCSP635S6","short_pith_number":"pith:IRFT7PVW","schema_version":"1.0","canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","source":{"kind":"arxiv","id":"2408.06721","version":1},"attestation_state":"computed","paper":{"title":"Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leonid Sigal, Shivam Chandhok, Wan-Cyuan Fan","submitted_at":"2024-08-13T08:26:32Z","abstract_excerpt":"Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, also lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks: object classification, understanding spatial arrangement, and ability to delineate individual object instances (through counting), by constructing a series of tests that probe which components of design, specifically, maybe lacking. Importantly, "},"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":"2408.06721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T08:26:32Z","cross_cats_sorted":[],"title_canon_sha256":"c99ad9c607da345b3c64bf1e081c043631c416bbdbefbdb8c36eb674e79f0182","abstract_canon_sha256":"1d3996242a7b7d6e787371fdd75022908ebcdd0d9943959b63048ee829c91332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:01.081162Z","signature_b64":"XEis3aBsK20+3y40GusHC7aA2qifPOYNHpdV/c9cdMNwgeEuyBtL+j6bScXmRu/2BcghWDPh8hB6NY5uLoCmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"444b3fbeb6acc7f368446d4527fb7d9799a31660b5f2db8382a0ec2a5c591fa9","last_reissued_at":"2026-07-05T08:55:01.080743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:01.080743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leonid Sigal, Shivam Chandhok, Wan-Cyuan Fan","submitted_at":"2024-08-13T08:26:32Z","abstract_excerpt":"Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, also lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks: object classification, understanding spatial arrangement, and ability to delineate individual object instances (through counting), by constructing a series of tests that probe which components of design, specifically, maybe lacking. Importantly, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06721","kind":"arxiv","version":1},"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/2408.06721/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":"2408.06721","created_at":"2026-07-05T08:55:01.080796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06721v1","created_at":"2026-07-05T08:55:01.080796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06721","created_at":"2026-07-05T08:55:01.080796+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRFT7PVWVTD7","created_at":"2026-07-05T08:55:01.080796+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRFT7PVWVTD7G2CE","created_at":"2026-07-05T08:55:01.080796+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRFT7PVW","created_at":"2026-07-05T08:55:01.080796+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/IRFT7PVWVTD7G2CENVCSP635S6","json":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6.json","graph_json":"https://pith.science/api/pith-number/IRFT7PVWVTD7G2CENVCSP635S6/graph.json","events_json":"https://pith.science/api/pith-number/IRFT7PVWVTD7G2CENVCSP635S6/events.json","paper":"https://pith.science/paper/IRFT7PVW"},"agent_actions":{"view_html":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6","download_json":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6.json","view_paper":"https://pith.science/paper/IRFT7PVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06721&json=true","fetch_graph":"https://pith.science/api/pith-number/IRFT7PVWVTD7G2CENVCSP635S6/graph.json","fetch_events":"https://pith.science/api/pith-number/IRFT7PVWVTD7G2CENVCSP635S6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/action/storage_attestation","attest_author":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/action/author_attestation","sign_citation":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/action/citation_signature","submit_replication":"https://pith.science/pith/IRFT7PVWVTD7G2CENVCSP635S6/action/replication_record"}},"created_at":"2026-07-05T08:55:01.080796+00:00","updated_at":"2026-07-05T08:55:01.080796+00:00"}