{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YFZZSAM2JZXR5QZSNYHEJ34KWI","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":"0412a127b5cf6b5fcacbbe67c1b82127ac0df80e71172325e4104946f4430bff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T23:14:46Z","title_canon_sha256":"bb63b5e51b65091e15189dec3138b762852c6faa1cef0ded678781ab7e334cb7"},"schema_version":"1.0","source":{"id":"2606.04282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04282","created_at":"2026-06-04T01:09:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04282v1","created_at":"2026-06-04T01:09:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04282","created_at":"2026-06-04T01:09:01Z"},{"alias_kind":"pith_short_12","alias_value":"YFZZSAM2JZXR","created_at":"2026-06-04T01:09:01Z"},{"alias_kind":"pith_short_16","alias_value":"YFZZSAM2JZXR5QZS","created_at":"2026-06-04T01:09:01Z"},{"alias_kind":"pith_short_8","alias_value":"YFZZSAM2","created_at":"2026-06-04T01:09:01Z"}],"graph_snapshots":[{"event_id":"sha256:77b7ba21607015baf010b50a9243f83c6a000452dca3301ae088382094188853","target":"graph","created_at":"2026-06-04T01:09:01Z","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/2606.04282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, and summarization. However, their practical use is rapidly expanding to more structured computer vision settings, where users prompt models to perform localization-centric tasks such as object detection, often within larger agentic or decision-making systems. Despite this shift, there is currently no standardized benchmark that systematically evaluates these capabilities at scale. In this work, we introduce the first comprehensive benchmark spec","authors_text":"Eshika Khandelwal, Hilde Kuehne, Jingjing Pan, Lorenzo Garattoni, Mingfang Zhang, Quan Kong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T23:14:46Z","title":"FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04282","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":"sha256:2bea6b6c42ed6e9984584e8c427b3f4d39a074bfc087c601e3e4e8bb6e0d43fa","target":"record","created_at":"2026-06-04T01:09:01Z","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":"0412a127b5cf6b5fcacbbe67c1b82127ac0df80e71172325e4104946f4430bff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T23:14:46Z","title_canon_sha256":"bb63b5e51b65091e15189dec3138b762852c6faa1cef0ded678781ab7e334cb7"},"schema_version":"1.0","source":{"id":"2606.04282","kind":"arxiv","version":1}},"canonical_sha256":"c17399019a4e6f1ec3326e0e44ef8ab225854b9e33906cb78588ad926fc38f38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c17399019a4e6f1ec3326e0e44ef8ab225854b9e33906cb78588ad926fc38f38","first_computed_at":"2026-06-04T01:09:01.789998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:01.789998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X98+L+lZJm3DXunesXjROMLNcOvY6T8SIYJiksT3fIkTwUv73p6yllTwb3r05lQSADCHV4GhW0NDcvWN/t53DQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:01.790783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bea6b6c42ed6e9984584e8c427b3f4d39a074bfc087c601e3e4e8bb6e0d43fa","sha256:77b7ba21607015baf010b50a9243f83c6a000452dca3301ae088382094188853"],"state_sha256":"ceb5ab9714550be28e7095702a978fa47af36ab8c19e29d1a2b0856bc5008936"}