{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4NKPQE5LVDWCEYUHFQOJMQDOSC","short_pith_number":"pith:4NKPQE5L","schema_version":"1.0","canonical_sha256":"e354f813aba8ec2262872c1c96406e908d4066e9162fe86e1ae390fbeafdb754","source":{"kind":"arxiv","id":"2402.16315","version":4},"attestation_state":"computed","paper":{"title":"Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Heng Ji, Jeonghwan Kim","submitted_at":"2024-02-26T05:43:51Z","abstract_excerpt":"Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world knowledge contained within the Large Language Models (LLMs), our work reveals their shortcomings in fine-grained visual categorization (FGVC) across six different benchmark settings. Most recent state-of-the-art LVLMs like LLaVa-1.5, InstructBLIP and GPT-4V not only severely deteriorate in terms of classification performance, e.g., average drop of 65.58 in EM"},"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":"2402.16315","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T05:43:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1675d080f34fa999628ad5ec59f2a68318fa8d8d6e8b6dd901838eecb3427599","abstract_canon_sha256":"b1455ab151cdbf2a4eaa6cd6df3a48c2a609ef5c4e76f06d9fad62a0337ca025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:39.898647Z","signature_b64":"R4mc/8HjM9y3P5JgLNds6Cp1KoiIc5RkRyVY5PPsThMBFcK28bhGO2m5GIM060q/Tmv2dCud3Jg/ysr7YhW1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e354f813aba8ec2262872c1c96406e908d4066e9162fe86e1ae390fbeafdb754","last_reissued_at":"2026-07-05T09:57:39.898161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:39.898161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Heng Ji, Jeonghwan Kim","submitted_at":"2024-02-26T05:43:51Z","abstract_excerpt":"Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world knowledge contained within the Large Language Models (LLMs), our work reveals their shortcomings in fine-grained visual categorization (FGVC) across six different benchmark settings. Most recent state-of-the-art LVLMs like LLaVa-1.5, InstructBLIP and GPT-4V not only severely deteriorate in terms of classification performance, e.g., average drop of 65.58 in EM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16315","kind":"arxiv","version":4},"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/2402.16315/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":"2402.16315","created_at":"2026-07-05T09:57:39.898216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16315v4","created_at":"2026-07-05T09:57:39.898216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16315","created_at":"2026-07-05T09:57:39.898216+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NKPQE5LVDWC","created_at":"2026-07-05T09:57:39.898216+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NKPQE5LVDWCEYUH","created_at":"2026-07-05T09:57:39.898216+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NKPQE5L","created_at":"2026-07-05T09:57:39.898216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC","json":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC.json","graph_json":"https://pith.science/api/pith-number/4NKPQE5LVDWCEYUHFQOJMQDOSC/graph.json","events_json":"https://pith.science/api/pith-number/4NKPQE5LVDWCEYUHFQOJMQDOSC/events.json","paper":"https://pith.science/paper/4NKPQE5L"},"agent_actions":{"view_html":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC","download_json":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC.json","view_paper":"https://pith.science/paper/4NKPQE5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16315&json=true","fetch_graph":"https://pith.science/api/pith-number/4NKPQE5LVDWCEYUHFQOJMQDOSC/graph.json","fetch_events":"https://pith.science/api/pith-number/4NKPQE5LVDWCEYUHFQOJMQDOSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/action/storage_attestation","attest_author":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/action/author_attestation","sign_citation":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/action/citation_signature","submit_replication":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/action/replication_record"}},"created_at":"2026-07-05T09:57:39.898216+00:00","updated_at":"2026-07-05T09:57:39.898216+00:00"}