{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C4PYQ44KRJXJK2UXE2QQGKQ45Q","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":"b176cc1eb4bdff524aea2467d16a9f69ef85a50f2dec506f2d6fe929e78e3cd8","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:45:11Z","title_canon_sha256":"1e8cf3d4e8236e956847edf4ea4cac4f4c136f360dae28a285f51fb85364cef5"},"schema_version":"1.0","source":{"id":"2310.12520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12520","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12520v1","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12520","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"C4PYQ44KRJXJ","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"C4PYQ44KRJXJK2UX","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"C4PYQ44K","created_at":"2026-07-05T07:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:812308554a09d6ded56237587574ec597052156047e6677d460c100184b76f0e","target":"graph","created_at":"2026-07-05T07:02:39Z","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/2310.12520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multimodal techniques open exciting possibilities for models excelling in diverse tasks involving text, audio, and image processing. Models like GPT-4V, blending computer vision and language modeling, excel in complex text and image tasks. Numerous prior research endeavors have diligently examined the performance of these Vision Large Language Models (VLLMs) across tasks like object detection, image captioning and others. However, these analyses often focus on evaluating the performance of each modality in isolation, lacking insights into their cross-modal interactions. ","authors_text":"Ning Shi, Senyu Li, Xiang Zhang, Zijun Wu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:45:11Z","title":"Lost in Translation: When GPT-4V(ision) Can't See Eye to Eye with Text. A Vision-Language-Consistency Analysis of VLLMs and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12520","kind":"arxiv","version":1},"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:f46e5a06a7c7bfb4e277586765d40791bae6a0a708264257109770468d7f116e","target":"record","created_at":"2026-07-05T07:02:39Z","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":"b176cc1eb4bdff524aea2467d16a9f69ef85a50f2dec506f2d6fe929e78e3cd8","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:45:11Z","title_canon_sha256":"1e8cf3d4e8236e956847edf4ea4cac4f4c136f360dae28a285f51fb85364cef5"},"schema_version":"1.0","source":{"id":"2310.12520","kind":"arxiv","version":1}},"canonical_sha256":"171f88738a8a6e956a9726a1032a1cec29435f96240b202681759b874b73d5b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"171f88738a8a6e956a9726a1032a1cec29435f96240b202681759b874b73d5b8","first_computed_at":"2026-07-05T07:02:39.452800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:39.452800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LdLki1XusFe7Lz2QAH2Ar/epqmfJTnUbnHmLl7xlDwZXyTVA7IbuK9XwG2RO/VNuq3NCe+jdpJHMVO954S4yAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:39.453395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f46e5a06a7c7bfb4e277586765d40791bae6a0a708264257109770468d7f116e","sha256:812308554a09d6ded56237587574ec597052156047e6677d460c100184b76f0e"],"state_sha256":"4515f5f2c04ebc8915bfe280db4fad305b2d416ff034e97ca300d826a0768bed"}