{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FFOCHXK7RUTXGNAOXG6BY4PGGW","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":"2f38eeeaaa703c0b125eafc2297bafdff97202c8ac8b00c9151dbbf4843d1c36","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T08:52:43Z","title_canon_sha256":"1c5ba25337818662f5d4297a540988c7a0f23d84c7ab566b1796801845c212df"},"schema_version":"1.0","source":{"id":"2501.15140","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15140","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15140v3","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15140","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"FFOCHXK7RUTX","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"FFOCHXK7RUTXGNAO","created_at":"2026-07-05T10:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"FFOCHXK7","created_at":"2026-07-05T10:41:19Z"}],"graph_snapshots":[{"event_id":"sha256:5b11d0156b154d41ee92e1859c5aec09044e6e5c3df91de50f8797a3d93e4e40","target":"graph","created_at":"2026-07-05T10:41:19Z","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/2501.15140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks. However, MLLMs still struggle with fine-grained visual recognition (FGVR), which aims to identify subordinate-level categories from images. This can negatively impact more advanced capabilities of MLLMs, such as object-centric visual question answering and reasoning. In our study, we revisit three quintessential capabilities of MLLMs for FGVR, including object information extraction, category knowledge reserve, object-category alignment, and position of the root cause as a misalignm","authors_text":"Geng Li, Hulingxiao He, Jinglin Xu, Yuxin Peng, Zijun Geng","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T08:52:43Z","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15140","kind":"arxiv","version":3},"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":"sha256:2e20dbd6e938e7046b00b1b7d1b2eb5cbc4f9ee42acc4008657bdb2fd54ad3be","target":"record","created_at":"2026-07-05T10:41:19Z","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":"2f38eeeaaa703c0b125eafc2297bafdff97202c8ac8b00c9151dbbf4843d1c36","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T08:52:43Z","title_canon_sha256":"1c5ba25337818662f5d4297a540988c7a0f23d84c7ab566b1796801845c212df"},"schema_version":"1.0","source":{"id":"2501.15140","kind":"arxiv","version":3}},"canonical_sha256":"295c23dd5f8d2773340eb9bc1c71e63598d1a43ddb2a0bf6b4df1d0fa6b3daf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"295c23dd5f8d2773340eb9bc1c71e63598d1a43ddb2a0bf6b4df1d0fa6b3daf2","first_computed_at":"2026-07-05T10:41:19.880173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:19.880173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0uCwtr4bJwJlvQpi+0VfFg0AyDMYgxyiMZBNVT2/WT8Ifa2MHU8+QegToQI+jlH85tF7lR6GVqrSExhIiTmDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:19.880684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15140","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e20dbd6e938e7046b00b1b7d1b2eb5cbc4f9ee42acc4008657bdb2fd54ad3be","sha256:5b11d0156b154d41ee92e1859c5aec09044e6e5c3df91de50f8797a3d93e4e40"],"state_sha256":"927bdc5b134469b3b1831d5a1d00e0e38e8b898eb443de744765f2e46a30bbdf"}