{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4EXUYT2K3TMUXCXJ3C5H637366","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":"6a6a88d88fbaf235f411fec691204346f47900e6f49e1cdc25bf5c6c37c21c32","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:56:48Z","title_canon_sha256":"e24beb95e072cd52daaf39314ff1dac25854e2c501d1dc6176c356165683e700"},"schema_version":"1.0","source":{"id":"2402.16832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16832","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16832v2","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16832","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"pith_short_12","alias_value":"4EXUYT2K3TMU","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"pith_short_16","alias_value":"4EXUYT2K3TMUXCXJ","created_at":"2026-07-05T08:46:22Z"},{"alias_kind":"pith_short_8","alias_value":"4EXUYT2K","created_at":"2026-07-05T08:46:22Z"}],"graph_snapshots":[{"event_id":"sha256:f6f86605567de5f2fddec8079ef547c2fe5ae19ef5e7b1d12d9b4b3958f5591e","target":"graph","created_at":"2026-07-05T08:46:22Z","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/2402.16832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) like LLaVA and GPT-4(V) enable general-purpose conversations about images with the language modality. As off-the-shelf MLLMs may have limited capabilities on images from domains like dermatology and agriculture, they must be fine-tuned to unlock domain-specific applications. The prevalent architecture of current open-source MLLMs comprises two major modules: an image-language (cross-modal) projection network and a large language model. It is desirable to understand the roles of these two modules in modeling domain-specific visual attributes to inform th","authors_text":"Gaurav Verma, Jamelle Watson-Daniels, Kartik Sharma, Minje Choi, Sejoon Oh, Srijan Kumar","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:56:48Z","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16832","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:faa6065d6c179cc98f27b3901b3236b9cc3344ca2fc9fa1591870029609aff56","target":"record","created_at":"2026-07-05T08:46:22Z","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":"6a6a88d88fbaf235f411fec691204346f47900e6f49e1cdc25bf5c6c37c21c32","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:56:48Z","title_canon_sha256":"e24beb95e072cd52daaf39314ff1dac25854e2c501d1dc6176c356165683e700"},"schema_version":"1.0","source":{"id":"2402.16832","kind":"arxiv","version":2}},"canonical_sha256":"e12f4c4f4adcd94b8ae9d8ba7f6ffbf79a0af165761fb217fb312146eb961216","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e12f4c4f4adcd94b8ae9d8ba7f6ffbf79a0af165761fb217fb312146eb961216","first_computed_at":"2026-07-05T08:46:22.011176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:22.011176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dzo/wSKGHJOAZSiXg4Y5CWNUl0PEn/CCoHEqKD1D9uVXONf0v6naydHoHFcDmNxWPV2Mx7zADxndC1N9OmLYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:22.011611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faa6065d6c179cc98f27b3901b3236b9cc3344ca2fc9fa1591870029609aff56","sha256:f6f86605567de5f2fddec8079ef547c2fe5ae19ef5e7b1d12d9b4b3958f5591e"],"state_sha256":"ddd17d061ce15bbbcae91ba3a4c51117570b42cd08d4eb7c67e60b7b04809e5b"}