{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:REHWSRU6FOLG2OPPLWYWG3XOMC","short_pith_number":"pith:REHWSRU6","schema_version":"1.0","canonical_sha256":"890f69469e2b966d39ef5db1636eee60be699d3aa6c49f7d900d6075a2ce6192","source":{"kind":"arxiv","id":"2401.13837","version":2},"attestation_state":"computed","paper":{"title":"Democratizing Fine-grained Visual Recognition with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Mingxuan Liu, Nicu Sebe, Subhankar Roy, Wenjing Li, Zhun Zhong","submitted_at":"2024-01-24T22:28:26Z","abstract_excerpt":"Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average layperson does not excel at differentiating species of birds or mushrooms due to subtle differences among the species. A major bottleneck in developing FGVR systems is caused by the need of high-quality paired expert annotations. To circumvent the need of expert knowledge we propose Fine-grained Semantic Category Reasoning (FineR) that internally leverages the world"},"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":"2401.13837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T22:28:26Z","cross_cats_sorted":[],"title_canon_sha256":"b74a5cd2b7f756d80e3df9f9f086e24b41f4294838f5e8c4e647a9f7db645621","abstract_canon_sha256":"b08072256ad41e0a580a6251394951b74f7ff5522cab3433c3f809cd9acc233e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:07.660577Z","signature_b64":"rMUO/TFQ9TLCuFMhvV4M+1RIBBeYrRBLSxU8a7raNI9tdqiNTYn70jB6dlTBlQ6nwqgf6pc69j+LWJ0xFFUECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"890f69469e2b966d39ef5db1636eee60be699d3aa6c49f7d900d6075a2ce6192","last_reissued_at":"2026-07-05T07:54:07.660125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:07.660125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Democratizing Fine-grained Visual Recognition with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Mingxuan Liu, Nicu Sebe, Subhankar Roy, Wenjing Li, Zhun Zhong","submitted_at":"2024-01-24T22:28:26Z","abstract_excerpt":"Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average layperson does not excel at differentiating species of birds or mushrooms due to subtle differences among the species. A major bottleneck in developing FGVR systems is caused by the need of high-quality paired expert annotations. To circumvent the need of expert knowledge we propose Fine-grained Semantic Category Reasoning (FineR) that internally leverages the world"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13837","kind":"arxiv","version":2},"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/2401.13837/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":"2401.13837","created_at":"2026-07-05T07:54:07.660192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13837v2","created_at":"2026-07-05T07:54:07.660192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13837","created_at":"2026-07-05T07:54:07.660192+00:00"},{"alias_kind":"pith_short_12","alias_value":"REHWSRU6FOLG","created_at":"2026-07-05T07:54:07.660192+00:00"},{"alias_kind":"pith_short_16","alias_value":"REHWSRU6FOLG2OPP","created_at":"2026-07-05T07:54:07.660192+00:00"},{"alias_kind":"pith_short_8","alias_value":"REHWSRU6","created_at":"2026-07-05T07:54:07.660192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.06993","citing_title":"Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03045","citing_title":"TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC","json":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC.json","graph_json":"https://pith.science/api/pith-number/REHWSRU6FOLG2OPPLWYWG3XOMC/graph.json","events_json":"https://pith.science/api/pith-number/REHWSRU6FOLG2OPPLWYWG3XOMC/events.json","paper":"https://pith.science/paper/REHWSRU6"},"agent_actions":{"view_html":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC","download_json":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC.json","view_paper":"https://pith.science/paper/REHWSRU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13837&json=true","fetch_graph":"https://pith.science/api/pith-number/REHWSRU6FOLG2OPPLWYWG3XOMC/graph.json","fetch_events":"https://pith.science/api/pith-number/REHWSRU6FOLG2OPPLWYWG3XOMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC/action/storage_attestation","attest_author":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC/action/author_attestation","sign_citation":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC/action/citation_signature","submit_replication":"https://pith.science/pith/REHWSRU6FOLG2OPPLWYWG3XOMC/action/replication_record"}},"created_at":"2026-07-05T07:54:07.660192+00:00","updated_at":"2026-07-05T07:54:07.660192+00:00"}