{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I6AHPNSRHOXIICW7Y4K5DAN2BN","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":"44ab5805e1303117795239cc7ab7dc677a3e86834cd24969bacc82280480040e","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-02T14:42:37Z","title_canon_sha256":"1f66cce1ac326a74d563ea7986e8edb9061674453f0cc915ab23494e56efa28d"},"schema_version":"1.0","source":{"id":"2501.01282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01282","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01282v1","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01282","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"I6AHPNSRHOXI","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"I6AHPNSRHOXIICW7","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"I6AHPNSR","created_at":"2026-07-05T09:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:d636f9692f431a417a7d8208a1579a862ff146cffdb1a6fd4a20d3a8f6e07f94","target":"graph","created_at":"2026-07-05T09:56:17Z","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/2501.01282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding, often misinterpreting symbols, gestures, and artifacts due to biases in predominantly Western-centric training data. In this paper, we construct CultureVerse, a large-scale multimodal benchmark covering 19, 682 cultural concepts, 188 countries/regions, 15 cultural concepts, and 3 question types, with the aim of characterizing and improving VLMs' multicultural understanding capabilities. Then, we propose CultureVLM, a series of VLMs fine-tuned on our dataset to achieve significant performa","authors_text":"Cheng Li, Derek F. Wong, Haipeng Chen, Jindong Wang, Lichao Sun, Qingsong Wen, Shudong Liu, Xing Xie, Yiqiao Jin","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-02T14:42:37Z","title":"CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01282","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:ce4f6688dd824d87f7d23dc2947442c4b7116cb0afe75837a4c2dbd5ef16509c","target":"record","created_at":"2026-07-05T09:56:17Z","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":"44ab5805e1303117795239cc7ab7dc677a3e86834cd24969bacc82280480040e","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-02T14:42:37Z","title_canon_sha256":"1f66cce1ac326a74d563ea7986e8edb9061674453f0cc915ab23494e56efa28d"},"schema_version":"1.0","source":{"id":"2501.01282","kind":"arxiv","version":1}},"canonical_sha256":"478077b6513bae840adfc715d181ba0b7d4927694b8ab7d1ebc723901788d634","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"478077b6513bae840adfc715d181ba0b7d4927694b8ab7d1ebc723901788d634","first_computed_at":"2026-07-05T09:56:17.394910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:17.394910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkYAdDeXY/bwZpc0CMeJcGlwSIQ9pr2hW7EDR9R0SjGVG19uzFZYkg5LnNJDFKOtwkMBoJN9by/N/INOyQz+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:17.395385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce4f6688dd824d87f7d23dc2947442c4b7116cb0afe75837a4c2dbd5ef16509c","sha256:d636f9692f431a417a7d8208a1579a862ff146cffdb1a6fd4a20d3a8f6e07f94"],"state_sha256":"9b71b1ff311d5162a6458bd0f559ea30c5c3df7d1d3a5cd1ea4d3e0bf246bb81"}