{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7J4GVTWMPBIKUNZOHQWXUAXZXM","short_pith_number":"pith:7J4GVTWM","schema_version":"1.0","canonical_sha256":"fa786acecc7850aa372e3c2d7a02f9bb067fc41044e20cd4becdc8b657b1b905","source":{"kind":"arxiv","id":"2406.14496","version":1},"attestation_state":"computed","paper":{"title":"African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Goran Glava\\v{s}, Gregor Geigle, Radu Timofte","submitted_at":"2024-06-20T16:59:39Z","abstract_excerpt":"Recent Large Vision-Language Models (LVLMs) demonstrate impressive abilities on numerous image understanding and reasoning tasks. The task of fine-grained object classification (e.g., distinction between \\textit{animal species}), however, has been probed insufficiently, despite its downstream importance. We fill this evaluation gap by creating \\texttt{FOCI} (\\textbf{F}ine-grained \\textbf{O}bject \\textbf{C}lass\\textbf{I}fication), a difficult multiple-choice benchmark for fine-grained object classification, from existing object classification datasets: (1) multiple-choice avoids ambiguous answe"},"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":"2406.14496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T16:59:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc75b3d1dd1fd8de566c10a8ff848a2ee4719e096fdf6557dd3f6f91d89d8665","abstract_canon_sha256":"b344f9201bcaf0e5c88e35475f91b05435a9497342ba5ecc8749f4317ad1f51d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:51.591772Z","signature_b64":"HoiKYD1FbofFWdV8HaU4/fcivminwTnP6lCyXIf+uqoNZGkmOoL7TaU50VOGykto1R4ATd/t4JY7W3BlsOZ9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa786acecc7850aa372e3c2d7a02f9bb067fc41044e20cd4becdc8b657b1b905","last_reissued_at":"2026-07-05T08:34:51.591347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:51.591347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Goran Glava\\v{s}, Gregor Geigle, Radu Timofte","submitted_at":"2024-06-20T16:59:39Z","abstract_excerpt":"Recent Large Vision-Language Models (LVLMs) demonstrate impressive abilities on numerous image understanding and reasoning tasks. The task of fine-grained object classification (e.g., distinction between \\textit{animal species}), however, has been probed insufficiently, despite its downstream importance. We fill this evaluation gap by creating \\texttt{FOCI} (\\textbf{F}ine-grained \\textbf{O}bject \\textbf{C}lass\\textbf{I}fication), a difficult multiple-choice benchmark for fine-grained object classification, from existing object classification datasets: (1) multiple-choice avoids ambiguous answe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14496","kind":"arxiv","version":1},"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/2406.14496/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":"2406.14496","created_at":"2026-07-05T08:34:51.591405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14496v1","created_at":"2026-07-05T08:34:51.591405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14496","created_at":"2026-07-05T08:34:51.591405+00:00"},{"alias_kind":"pith_short_12","alias_value":"7J4GVTWMPBIK","created_at":"2026-07-05T08:34:51.591405+00:00"},{"alias_kind":"pith_short_16","alias_value":"7J4GVTWMPBIKUNZO","created_at":"2026-07-05T08:34:51.591405+00:00"},{"alias_kind":"pith_short_8","alias_value":"7J4GVTWM","created_at":"2026-07-05T08:34:51.591405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.14988","citing_title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06993","citing_title":"Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07605","citing_title":"Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM","json":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM.json","graph_json":"https://pith.science/api/pith-number/7J4GVTWMPBIKUNZOHQWXUAXZXM/graph.json","events_json":"https://pith.science/api/pith-number/7J4GVTWMPBIKUNZOHQWXUAXZXM/events.json","paper":"https://pith.science/paper/7J4GVTWM"},"agent_actions":{"view_html":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM","download_json":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM.json","view_paper":"https://pith.science/paper/7J4GVTWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14496&json=true","fetch_graph":"https://pith.science/api/pith-number/7J4GVTWMPBIKUNZOHQWXUAXZXM/graph.json","fetch_events":"https://pith.science/api/pith-number/7J4GVTWMPBIKUNZOHQWXUAXZXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM/action/storage_attestation","attest_author":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM/action/author_attestation","sign_citation":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM/action/citation_signature","submit_replication":"https://pith.science/pith/7J4GVTWMPBIKUNZOHQWXUAXZXM/action/replication_record"}},"created_at":"2026-07-05T08:34:51.591405+00:00","updated_at":"2026-07-05T08:34:51.591405+00:00"}