{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JAYXG4FF7SI5NMHOKGHZ42CTUG","short_pith_number":"pith:JAYXG4FF","schema_version":"1.0","canonical_sha256":"48317370a5fc91d6b0ee518f9e6853a19b525bbb25e930ea16b097af3e82fc5f","source":{"kind":"arxiv","id":"2403.13805","version":2},"attestation_state":"computed","paper":{"title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Wei Li, Xiaoyi Dong, Yuanjun Xiong, Yuhang Zang, Zeyi Sun, Ziyu Liu","submitted_at":"2024-03-20T17:59:55Z","abstract_excerpt":"CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited conte"},"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":"2403.13805","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1be42e42c18d26957daa2eae9b0e93fd81da7bf1bf80f471cbb7b3cf3a9d3ea2","abstract_canon_sha256":"92e1eafa536035bfcd710e272023b9a1cd379e9dae791162443c6597d09f0b87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:14.973373Z","signature_b64":"yZYcqso1EmmQdyrVyvUzWLgKzuJpItls2ka3AuioEYt0jVPlpoQxyMqxQCbKnVxuQGUwsAoEQJ7+X8lsw2kDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48317370a5fc91d6b0ee518f9e6853a19b525bbb25e930ea16b097af3e82fc5f","last_reissued_at":"2026-05-20T00:00:14.972562Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:14.972562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Wei Li, Xiaoyi Dong, Yuanjun Xiong, Yuhang Zang, Zeyi Sun, Ziyu Liu","submitted_at":"2024-03-20T17:59:55Z","abstract_excerpt":"CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13805","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/2403.13805/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":"2403.13805","created_at":"2026-05-20T00:00:14.972698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13805v2","created_at":"2026-05-20T00:00:14.972698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13805","created_at":"2026-05-20T00:00:14.972698+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAYXG4FF7SI5","created_at":"2026-05-20T00:00:14.972698+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAYXG4FF7SI5NMHO","created_at":"2026-05-20T00:00:14.972698+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAYXG4FF","created_at":"2026-05-20T00:00:14.972698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2410.17247","citing_title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG","json":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG.json","graph_json":"https://pith.science/api/pith-number/JAYXG4FF7SI5NMHOKGHZ42CTUG/graph.json","events_json":"https://pith.science/api/pith-number/JAYXG4FF7SI5NMHOKGHZ42CTUG/events.json","paper":"https://pith.science/paper/JAYXG4FF"},"agent_actions":{"view_html":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG","download_json":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG.json","view_paper":"https://pith.science/paper/JAYXG4FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13805&json=true","fetch_graph":"https://pith.science/api/pith-number/JAYXG4FF7SI5NMHOKGHZ42CTUG/graph.json","fetch_events":"https://pith.science/api/pith-number/JAYXG4FF7SI5NMHOKGHZ42CTUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/action/storage_attestation","attest_author":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/action/author_attestation","sign_citation":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/action/citation_signature","submit_replication":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/action/replication_record"}},"created_at":"2026-05-20T00:00:14.972698+00:00","updated_at":"2026-05-20T00:00:14.972698+00:00"}