{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JAYXG4FF7SI5NMHOKGHZ42CTUG","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":"92e1eafa536035bfcd710e272023b9a1cd379e9dae791162443c6597d09f0b87","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:55Z","title_canon_sha256":"1be42e42c18d26957daa2eae9b0e93fd81da7bf1bf80f471cbb7b3cf3a9d3ea2"},"schema_version":"1.0","source":{"id":"2403.13805","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13805","created_at":"2026-05-20T00:00:14Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13805v2","created_at":"2026-05-20T00:00:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13805","created_at":"2026-05-20T00:00:14Z"},{"alias_kind":"pith_short_12","alias_value":"JAYXG4FF7SI5","created_at":"2026-05-20T00:00:14Z"},{"alias_kind":"pith_short_16","alias_value":"JAYXG4FF7SI5NMHO","created_at":"2026-05-20T00:00:14Z"},{"alias_kind":"pith_short_8","alias_value":"JAYXG4FF","created_at":"2026-05-20T00:00:14Z"}],"graph_snapshots":[{"event_id":"sha256:8d397366dc027e5786a564bbca27d79e5be66349ddb2015efcd4175b06a1bf4d","target":"graph","created_at":"2026-05-20T00:00:14Z","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/2403.13805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Wei Li, Xiaoyi Dong, Yuanjun Xiong, Yuhang Zang, Zeyi Sun, Ziyu Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:55Z","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13805","kind":"arxiv","version":2},"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":"sha256:5b50f1fa78ba2b1497ae564651f9af3605ecf6567d5f4e586fd3bfa75a23cc48","target":"record","created_at":"2026-05-20T00:00:14Z","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":"92e1eafa536035bfcd710e272023b9a1cd379e9dae791162443c6597d09f0b87","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:55Z","title_canon_sha256":"1be42e42c18d26957daa2eae9b0e93fd81da7bf1bf80f471cbb7b3cf3a9d3ea2"},"schema_version":"1.0","source":{"id":"2403.13805","kind":"arxiv","version":2}},"canonical_sha256":"48317370a5fc91d6b0ee518f9e6853a19b525bbb25e930ea16b097af3e82fc5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48317370a5fc91d6b0ee518f9e6853a19b525bbb25e930ea16b097af3e82fc5f","first_computed_at":"2026-05-20T00:00:14.972562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:14.972562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yZYcqso1EmmQdyrVyvUzWLgKzuJpItls2ka3AuioEYt0jVPlpoQxyMqxQCbKnVxuQGUwsAoEQJ7+X8lsw2kDCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:14.973373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13805","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b50f1fa78ba2b1497ae564651f9af3605ecf6567d5f4e586fd3bfa75a23cc48","sha256:8d397366dc027e5786a564bbca27d79e5be66349ddb2015efcd4175b06a1bf4d"],"state_sha256":"e937f721756384f6cd09dd7017bad821ce6a50528158379e9d1c4548c533aca3"}