{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VG73B52FF7RLESK3TPPQGUZUKC","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":"4ff1d4aca271c9a97e1b7cbc690d6635ee6203d077465fe6ff025b411fda0ec4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T17:59:58Z","title_canon_sha256":"899f6dd882979d79404f98e0d99f89791dae76510e847d71836e3375e7522368"},"schema_version":"1.0","source":{"id":"2406.16866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16866","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16866v1","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16866","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"VG73B52FF7RL","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"VG73B52FF7RLESK3","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"VG73B52F","created_at":"2026-07-05T08:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:bf9be9dc94f587e2c39aee547d29b41ce70efeaf6649f418e17f37223d23bf24","target":"graph","created_at":"2026-07-05T08:36:04Z","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/2406.16866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring expression comprehension (REC) involves localizing a target instance based on a textual description. Recent advancements in REC have been driven by large multimodal models (LMMs) like CogVLM, which achieved 92.44% accuracy on RefCOCO. However, this study questions whether existing benchmarks such as RefCOCO, RefCOCO+, and RefCOCOg, capture LMMs' comprehensive capabilities. We begin with a manual examination of these benchmarks, revealing high labeling error rates: 14% in RefCOCO, 24% in RefCOCO+, and 5% in RefCOCOg, which undermines the authenticity of evaluations. We address this by","authors_text":"Bohuai Wu, Fangyun Wei, Hongyang Zhang, Jierun Chen, Jinjing Zhao, S.-H. Gary Chan, Sizhe Song, Zhuoxuan Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T17:59:58Z","title":"Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16866","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":"sha256:29915f7817761f82522ba207c6bb453241f1e054443908338e700e189f2679bd","target":"record","created_at":"2026-07-05T08:36:04Z","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":"4ff1d4aca271c9a97e1b7cbc690d6635ee6203d077465fe6ff025b411fda0ec4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T17:59:58Z","title_canon_sha256":"899f6dd882979d79404f98e0d99f89791dae76510e847d71836e3375e7522368"},"schema_version":"1.0","source":{"id":"2406.16866","kind":"arxiv","version":1}},"canonical_sha256":"a9bfb0f7452fe2b2495b9bdf035334509362ec78baeb9cae74ad1431e47097a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9bfb0f7452fe2b2495b9bdf035334509362ec78baeb9cae74ad1431e47097a0","first_computed_at":"2026-07-05T08:36:04.833222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:04.833222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vYe31arzKXDoSMah0lm4E6DhmuH1V6imRAu4FMcGlKYUtkat7WFuN/XS45tuvqkOM+fGvYUEFqJNZOBOFzF1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:04.833693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29915f7817761f82522ba207c6bb453241f1e054443908338e700e189f2679bd","sha256:bf9be9dc94f587e2c39aee547d29b41ce70efeaf6649f418e17f37223d23bf24"],"state_sha256":"6acc07649aac146436d3418e2de2a373fc26ea24b62aacc9c109ab4170af80e3"}