{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYU3WYYXH5OERSGBTFNNUV74MW","short_pith_number":"pith:YYU3WYYX","schema_version":"1.0","canonical_sha256":"c629bb63173f5c48c8c1995ada57fc65896b8e35ec1e7b793ff88da216995151","source":{"kind":"arxiv","id":"2509.25339","version":3},"attestation_state":"computed","paper":{"title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Hilde Kuehne, James Glass, M. Jehanzeb Mirza, Muhammad Huzaifa, Paul Gavrikov, Serena Yeung-Levy, Sivan Doveh, Soumya Jahagirdar, Wei Lin","submitted_at":"2025-09-29T18:00:25Z","abstract_excerpt":"Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth responses. Unlike prior VQA datasets that typically focus on near global image understanding, VisualOverload challenges models to perform simple, knowledge-free vision tasks in densely populated (or, overloaded) scenes. Our dataset consists of high-resolution scans of public-domain paintings that are populated with multiple figures, actions, and unfolding subplots "},"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":"2509.25339","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-29T18:00:25Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"7f7e98002c142dcea93b8648c3d53e9094d306ea8faef61f5a9bae7016b7efe9","abstract_canon_sha256":"2c44579daa548de79ce8b7106925b039f069f6cca915b319fc54d8263915eeff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:16.095746Z","signature_b64":"edSZIDkpFw3dhBqw1GogIcygtQoKPI2VuiS20Xbg/xVGN8oq/4UGaLnaHv3SfpJg4xr5x4SoQ1RLv7I/G7YzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c629bb63173f5c48c8c1995ada57fc65896b8e35ec1e7b793ff88da216995151","last_reissued_at":"2026-05-26T01:03:16.094947Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:16.094947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Hilde Kuehne, James Glass, M. Jehanzeb Mirza, Muhammad Huzaifa, Paul Gavrikov, Serena Yeung-Levy, Sivan Doveh, Soumya Jahagirdar, Wei Lin","submitted_at":"2025-09-29T18:00:25Z","abstract_excerpt":"Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth responses. Unlike prior VQA datasets that typically focus on near global image understanding, VisualOverload challenges models to perform simple, knowledge-free vision tasks in densely populated (or, overloaded) scenes. Our dataset consists of high-resolution scans of public-domain paintings that are populated with multiple figures, actions, and unfolding subplots "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.25339","kind":"arxiv","version":3},"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/2509.25339/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":"2509.25339","created_at":"2026-05-26T01:03:16.095048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.25339v3","created_at":"2026-05-26T01:03:16.095048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.25339","created_at":"2026-05-26T01:03:16.095048+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYU3WYYXH5OE","created_at":"2026-05-26T01:03:16.095048+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYU3WYYXH5OERSGB","created_at":"2026-05-26T01:03:16.095048+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYU3WYYX","created_at":"2026-05-26T01:03:16.095048+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/YYU3WYYXH5OERSGBTFNNUV74MW","json":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW.json","graph_json":"https://pith.science/api/pith-number/YYU3WYYXH5OERSGBTFNNUV74MW/graph.json","events_json":"https://pith.science/api/pith-number/YYU3WYYXH5OERSGBTFNNUV74MW/events.json","paper":"https://pith.science/paper/YYU3WYYX"},"agent_actions":{"view_html":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW","download_json":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW.json","view_paper":"https://pith.science/paper/YYU3WYYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.25339&json=true","fetch_graph":"https://pith.science/api/pith-number/YYU3WYYXH5OERSGBTFNNUV74MW/graph.json","fetch_events":"https://pith.science/api/pith-number/YYU3WYYXH5OERSGBTFNNUV74MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW/action/storage_attestation","attest_author":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW/action/author_attestation","sign_citation":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW/action/citation_signature","submit_replication":"https://pith.science/pith/YYU3WYYXH5OERSGBTFNNUV74MW/action/replication_record"}},"created_at":"2026-05-26T01:03:16.095048+00:00","updated_at":"2026-05-26T01:03:16.095048+00:00"}