{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5KGSXI3V2LLVT467QLPYWB3XFJ","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":"64a589cddd6a08963db9e3a06bac297adb67b7f67088ba4fa36f47fa2807cd08","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T13:23:26Z","title_canon_sha256":"0adebeb7205275a566a1399387288a9e9e85547bb15e78468f8d84323b0f60f3"},"schema_version":"1.0","source":{"id":"2606.19053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19053","created_at":"2026-06-19T16:11:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19053v1","created_at":"2026-06-19T16:11:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19053","created_at":"2026-06-19T16:11:55Z"},{"alias_kind":"pith_short_12","alias_value":"5KGSXI3V2LLV","created_at":"2026-06-19T16:11:55Z"},{"alias_kind":"pith_short_16","alias_value":"5KGSXI3V2LLVT467","created_at":"2026-06-19T16:11:55Z"},{"alias_kind":"pith_short_8","alias_value":"5KGSXI3V","created_at":"2026-06-19T16:11:55Z"}],"graph_snapshots":[{"event_id":"sha256:4713e291dc6633bd50bdc205d9ce03bfa901d2e38865d832f09c2f8ffb9f35a4","target":"graph","created_at":"2026-06-19T16:11:55Z","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/2606.19053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception and reasoning capabilities. While numerous benchmarks have evaluated LVLMs from holistic or task-specific perspectives, their capabilities on fine-grained image tasks-fundamental to computer vision-remain insufficiently understood. To address this gap, we introduce FG-BMK, a comprehensive fine-grained evaluation benchmark containing 1.01 million questions and 0.28 million images, covering diverse scenarios from common object-centric domains to specialized domains. FG-BMK jointly evalu","authors_text":"Chen-Wei Xie, Hong-Tao Yu, Serge Belongie, Xiu-Shen Wei, Yuxin Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T13:23:26Z","title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19053","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":"sha256:555f7bd46807ae001f4aa43c1204d3470d974580ceb5a07321a9c9d946358ed1","target":"record","created_at":"2026-06-19T16:11:55Z","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":"64a589cddd6a08963db9e3a06bac297adb67b7f67088ba4fa36f47fa2807cd08","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T13:23:26Z","title_canon_sha256":"0adebeb7205275a566a1399387288a9e9e85547bb15e78468f8d84323b0f60f3"},"schema_version":"1.0","source":{"id":"2606.19053","kind":"arxiv","version":1}},"canonical_sha256":"ea8d2ba375d2d759f3df82df8b07772a45758321382e287dc6f53b4d3314696e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea8d2ba375d2d759f3df82df8b07772a45758321382e287dc6f53b4d3314696e","first_computed_at":"2026-06-19T16:11:55.475670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:55.475670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YbIVOb99F32nkIg2oR+SMMM0Ih6nO3StN76zgnHG6dzoCfPaJCSqXysFS0psF+hn2CFJWoNKmYewHny/J2JTCQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:55.476020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:555f7bd46807ae001f4aa43c1204d3470d974580ceb5a07321a9c9d946358ed1","sha256:4713e291dc6633bd50bdc205d9ce03bfa901d2e38865d832f09c2f8ffb9f35a4"],"state_sha256":"6b7c1708074d4485c1f9fe52d56a9f00dae963201188da3d3aca1166e1b35fab"}