{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OK26KLOXAUWAMW7VKUBTFUOFIT","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":"b9464d7434e3f9d2d7682b110bb71ba4f93fc49025392f6130014ee751bc4a5f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T05:48:24Z","title_canon_sha256":"d1e4eba2786c1c307afdd028ba9e6ed3698c7e4734d5a2133c08be7c9757a0e3"},"schema_version":"1.0","source":{"id":"2410.19808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19808","created_at":"2026-07-05T09:26:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19808v1","created_at":"2026-07-05T09:26:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19808","created_at":"2026-07-05T09:26:33Z"},{"alias_kind":"pith_short_12","alias_value":"OK26KLOXAUWA","created_at":"2026-07-05T09:26:33Z"},{"alias_kind":"pith_short_16","alias_value":"OK26KLOXAUWAMW7V","created_at":"2026-07-05T09:26:33Z"},{"alias_kind":"pith_short_8","alias_value":"OK26KLOX","created_at":"2026-07-05T09:26:33Z"}],"graph_snapshots":[{"event_id":"sha256:d25986e286a2934710cc31e7bb8c1a4855cff7c0c401edf06729f623729f3228","target":"graph","created_at":"2026-07-05T09:26:33Z","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/2410.19808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to locate an object in an image according to natural language instructions is crucial for many real-world applications. In this work we propose LocateBench, a high-quality benchmark dedicated to evaluating this ability. We experiment with multiple prompting approaches, and measure the accuracy of several large vision language models. We find that even the accuracy of the strongest model, GPT-4o, lags behind human accuracy by more than 10%.","authors_text":"Dani Yogatama, Joshua Robinson, Ting-Rui Chiang, Xinyan Velocity Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T05:48:24Z","title":"LocateBench: Evaluating the Locating Ability of Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19808","kind":"arxiv","version":1},"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":"sha256:00e0203bcfcf80190bf3557785c8cd7183ddffb4416f19a6405492f3ef19434c","target":"record","created_at":"2026-07-05T09:26:33Z","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":"b9464d7434e3f9d2d7682b110bb71ba4f93fc49025392f6130014ee751bc4a5f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T05:48:24Z","title_canon_sha256":"d1e4eba2786c1c307afdd028ba9e6ed3698c7e4734d5a2133c08be7c9757a0e3"},"schema_version":"1.0","source":{"id":"2410.19808","kind":"arxiv","version":1}},"canonical_sha256":"72b5e52dd7052c065bf5550332d1c544f17d128ce2dbb11e72691487540e5116","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72b5e52dd7052c065bf5550332d1c544f17d128ce2dbb11e72691487540e5116","first_computed_at":"2026-07-05T09:26:33.623258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:33.623258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lxKHuij5M4hmRDdxyrdzop0OXsksJIg3ggW95DwK1+o2l0MHS9fZnVpP6nfX/UrKsgks/SInPKAKWtRJmEbcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:33.623708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e0203bcfcf80190bf3557785c8cd7183ddffb4416f19a6405492f3ef19434c","sha256:d25986e286a2934710cc31e7bb8c1a4855cff7c0c401edf06729f623729f3228"],"state_sha256":"3c38f884372a84a3b385021303e971b19eef027a49fc630e1612aecc1224e15c"}