{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JAYXG4FF7SI5NMHOKGHZ42CTUG","short_pith_number":"pith:JAYXG4FF","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"},"canonical_sha256":"48317370a5fc91d6b0ee518f9e6853a19b525bbb25e930ea16b097af3e82fc5f","source":{"kind":"arxiv","id":"2403.13805","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JAYXG4FF7SI5NMHOKGHZ42CTUG","target":"record","payload":{"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"},"canonical_sha256":"48317370a5fc91d6b0ee518f9e6853a19b525bbb25e930ea16b097af3e82fc5f","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"},"source_kind":"arxiv","source_id":"2403.13805","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7fzAPcLFQ8A1/Q/W3YP6dndTs84/ePEq/+xxLA9I5OwMdLXz05vbSzKMQwKJCnFnQ44rbmPLcVOSACSAPwXcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:43:40.894885Z"},"content_sha256":"5b50f1fa78ba2b1497ae564651f9af3605ecf6567d5f4e586fd3bfa75a23cc48","schema_version":"1.0","event_id":"sha256:5b50f1fa78ba2b1497ae564651f9af3605ecf6567d5f4e586fd3bfa75a23cc48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JAYXG4FF7SI5NMHOKGHZ42CTUG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jlm4DqJvOhTlTcTtenVI4mS4LIjOwMpTWFZU8X3E/JTktYdEF2tnjYSU7BMJjYqJq5YeEqxmJpyxyMF6gu4vAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:43:40.895279Z"},"content_sha256":"8d397366dc027e5786a564bbca27d79e5be66349ddb2015efcd4175b06a1bf4d","schema_version":"1.0","event_id":"sha256:8d397366dc027e5786a564bbca27d79e5be66349ddb2015efcd4175b06a1bf4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/bundle.json","state_url":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/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":"2026-05-25T17:43:40Z","links":{"resolver":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG","bundle":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/bundle.json","state":"https://pith.science/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAYXG4FF7SI5NMHOKGHZ42CTUG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHWJ6nN6vawwKsdC7jGo2lqI9j8IoudEl/5VjetoWuBYdWP9D2EIpfWwx+rcPpriNlMPuuWeVDLfT81L6x8lDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:43:40.899331Z","bundle_sha256":"7c27b77512a3f9f196c0c70139ab3a0b70320b1bb393a537ac49d67276348139"}}