{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4NKPQE5LVDWCEYUHFQOJMQDOSC","short_pith_number":"pith:4NKPQE5L","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"},"canonical_sha256":"e354f813aba8ec2262872c1c96406e908d4066e9162fe86e1ae390fbeafdb754","source":{"kind":"arxiv","id":"2402.16315","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16315","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16315v4","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16315","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"pith_short_12","alias_value":"4NKPQE5LVDWC","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"pith_short_16","alias_value":"4NKPQE5LVDWCEYUH","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"pith_short_8","alias_value":"4NKPQE5L","created_at":"2026-07-05T09:57:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4NKPQE5LVDWCEYUHFQOJMQDOSC","target":"record","payload":{"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"},"canonical_sha256":"e354f813aba8ec2262872c1c96406e908d4066e9162fe86e1ae390fbeafdb754","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"},"source_kind":"arxiv","source_id":"2402.16315","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVB8Vg1rB68HcVjipkkUD09fVoibqOuF4icHQt0L3Nk+6ZcydyJ0hBF3X1DsaCMvkIjYoPsVt5GhzwwTnPkaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:38:49.332295Z"},"content_sha256":"3dde5e336b46198c02a09fb104a4a81e4ba321c89e1120f7d87f4258d965294e","schema_version":"1.0","event_id":"sha256:3dde5e336b46198c02a09fb104a4a81e4ba321c89e1120f7d87f4258d965294e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4NKPQE5LVDWCEYUHFQOJMQDOSC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4jcxlmhoEKkD/hUpdvNKc3OCWk9npZ4b3/WQr/L/0Bh+jL1spXDhNdJOrpDUb9iqHxfQ1k4/WDUhKZs0qlTXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:38:49.333222Z"},"content_sha256":"2d33e378c61588de47eb379928dc0d88dc8b5a92ab8fc500fa38c1f4f06e0469","schema_version":"1.0","event_id":"sha256:2d33e378c61588de47eb379928dc0d88dc8b5a92ab8fc500fa38c1f4f06e0469"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/bundle.json","state_url":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:38:49Z","links":{"resolver":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC","bundle":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/bundle.json","state":"https://pith.science/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NKPQE5LVDWCEYUHFQOJMQDOSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4NKPQE5LVDWCEYUHFQOJMQDOSC","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":"b1455ab151cdbf2a4eaa6cd6df3a48c2a609ef5c4e76f06d9fad62a0337ca025","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T05:43:51Z","title_canon_sha256":"1675d080f34fa999628ad5ec59f2a68318fa8d8d6e8b6dd901838eecb3427599"},"schema_version":"1.0","source":{"id":"2402.16315","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16315","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16315v4","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16315","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"pith_short_12","alias_value":"4NKPQE5LVDWC","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"pith_short_16","alias_value":"4NKPQE5LVDWCEYUH","created_at":"2026-07-05T09:57:39Z"},{"alias_kind":"pith_short_8","alias_value":"4NKPQE5L","created_at":"2026-07-05T09:57:39Z"}],"graph_snapshots":[{"event_id":"sha256:2d33e378c61588de47eb379928dc0d88dc8b5a92ab8fc500fa38c1f4f06e0469","target":"graph","created_at":"2026-07-05T09:57:39Z","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/2402.16315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Heng Ji, Jeonghwan Kim","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T05:43:51Z","title":"Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16315","kind":"arxiv","version":4},"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":"sha256:3dde5e336b46198c02a09fb104a4a81e4ba321c89e1120f7d87f4258d965294e","target":"record","created_at":"2026-07-05T09:57:39Z","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":"b1455ab151cdbf2a4eaa6cd6df3a48c2a609ef5c4e76f06d9fad62a0337ca025","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T05:43:51Z","title_canon_sha256":"1675d080f34fa999628ad5ec59f2a68318fa8d8d6e8b6dd901838eecb3427599"},"schema_version":"1.0","source":{"id":"2402.16315","kind":"arxiv","version":4}},"canonical_sha256":"e354f813aba8ec2262872c1c96406e908d4066e9162fe86e1ae390fbeafdb754","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e354f813aba8ec2262872c1c96406e908d4066e9162fe86e1ae390fbeafdb754","first_computed_at":"2026-07-05T09:57:39.898161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:39.898161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R4mc/8HjM9y3P5JgLNds6Cp1KoiIc5RkRyVY5PPsThMBFcK28bhGO2m5GIM060q/Tmv2dCud3Jg/ysr7YhW1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:39.898647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16315","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dde5e336b46198c02a09fb104a4a81e4ba321c89e1120f7d87f4258d965294e","sha256:2d33e378c61588de47eb379928dc0d88dc8b5a92ab8fc500fa38c1f4f06e0469"],"state_sha256":"c232dda3a4c470c07d7eb5fb375d479b5f9f2bfd10bafb5a6a0fe5ed188181e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pf6EfPQRofhL4ikrArECPe5wxdu+K24EpvOSKx32DOKVIquW77t83lMunsbU9o35W2YLOrejDlitaTA9XhdlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:38:49.338365Z","bundle_sha256":"d8c867bb9fc3f39ce24da6bfe2468dbad14b9a1d89f3c7354a7981593057370b"}}