{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DYDU6I6VDAQHXG42F5TKITW5NA","short_pith_number":"pith:DYDU6I6V","schema_version":"1.0","canonical_sha256":"1e074f23d518207b9b9a2f66a44edd6835091109259d4cf97f91385ed6a7d9de","source":{"kind":"arxiv","id":"2502.15812","version":1},"attestation_state":"computed","paper":{"title":"InsightVision: A Comprehensive, Multi-Level Chinese-based Benchmark for Evaluating Implicit Visual Semantics in Large Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gongshen Liu, Huijia Zhu, Weiqiang Wang, Xiaofei Yin, Ya Guo, Yijie Hong, Yi Tu","submitted_at":"2025-02-19T13:42:37Z","abstract_excerpt":"In the evolving landscape of multimodal language models, understanding the nuanced meanings conveyed through visual cues - such as satire, insult, or critique - remains a significant challenge. Existing evaluation benchmarks primarily focus on direct tasks like image captioning or are limited to a narrow set of categories, such as humor or satire, for deep semantic understanding. To address this gap, we introduce, for the first time, a comprehensive, multi-level Chinese-based benchmark designed specifically for evaluating the understanding of implicit meanings in images. This benchmark is syst"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.15812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T13:42:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1922ecc061603a0747e95c65454e2ba8100c7d2992ba712c278ca1a9ab717b6b","abstract_canon_sha256":"ac7275bad18c80a3d8ab6e9d6275a2153176b467ed0f32a2826e03a26d947a9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:16.670029Z","signature_b64":"vMPq6s+rXk3wJ2breQ3eKEMLY7Ldx0O8NPNjYLN+CUu6/9AlkQ+I2b51DF+L0outcQWQEhVbBVv8kGxQnlESBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e074f23d518207b9b9a2f66a44edd6835091109259d4cf97f91385ed6a7d9de","last_reissued_at":"2026-07-05T10:18:16.669603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:16.669603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InsightVision: A Comprehensive, Multi-Level Chinese-based Benchmark for Evaluating Implicit Visual Semantics in Large Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gongshen Liu, Huijia Zhu, Weiqiang Wang, Xiaofei Yin, Ya Guo, Yijie Hong, Yi Tu","submitted_at":"2025-02-19T13:42:37Z","abstract_excerpt":"In the evolving landscape of multimodal language models, understanding the nuanced meanings conveyed through visual cues - such as satire, insult, or critique - remains a significant challenge. Existing evaluation benchmarks primarily focus on direct tasks like image captioning or are limited to a narrow set of categories, such as humor or satire, for deep semantic understanding. To address this gap, we introduce, for the first time, a comprehensive, multi-level Chinese-based benchmark designed specifically for evaluating the understanding of implicit meanings in images. This benchmark is syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15812","kind":"arxiv","version":1},"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/2502.15812/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.15812","created_at":"2026-07-05T10:18:16.669659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15812v1","created_at":"2026-07-05T10:18:16.669659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15812","created_at":"2026-07-05T10:18:16.669659+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYDU6I6VDAQH","created_at":"2026-07-05T10:18:16.669659+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYDU6I6VDAQHXG42","created_at":"2026-07-05T10:18:16.669659+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYDU6I6V","created_at":"2026-07-05T10:18:16.669659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24344","citing_title":"Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA","json":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA.json","graph_json":"https://pith.science/api/pith-number/DYDU6I6VDAQHXG42F5TKITW5NA/graph.json","events_json":"https://pith.science/api/pith-number/DYDU6I6VDAQHXG42F5TKITW5NA/events.json","paper":"https://pith.science/paper/DYDU6I6V"},"agent_actions":{"view_html":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA","download_json":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA.json","view_paper":"https://pith.science/paper/DYDU6I6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15812&json=true","fetch_graph":"https://pith.science/api/pith-number/DYDU6I6VDAQHXG42F5TKITW5NA/graph.json","fetch_events":"https://pith.science/api/pith-number/DYDU6I6VDAQHXG42F5TKITW5NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA/action/storage_attestation","attest_author":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA/action/author_attestation","sign_citation":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA/action/citation_signature","submit_replication":"https://pith.science/pith/DYDU6I6VDAQHXG42F5TKITW5NA/action/replication_record"}},"created_at":"2026-07-05T10:18:16.669659+00:00","updated_at":"2026-07-05T10:18:16.669659+00:00"}