{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P3F4VIW4ZNYYYSUW3TALSF3UUX","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":"d71aef7de5132d02af992d302350745583f84d36c97c3aafbe2e862830904897","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-17T13:41:44Z","title_canon_sha256":"913e903ddfa17eb6400cf48dd6d1222527cfd05a74d82478b907e6215799d395"},"schema_version":"1.0","source":{"id":"2402.11281","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11281","created_at":"2026-07-05T08:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11281v3","created_at":"2026-07-05T08:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11281","created_at":"2026-07-05T08:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"P3F4VIW4ZNYY","created_at":"2026-07-05T08:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"P3F4VIW4ZNYYYSUW","created_at":"2026-07-05T08:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"P3F4VIW4","created_at":"2026-07-05T08:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:36c9de3da6aa3109f2bd1a0fedab261048a230025473e1b334c404ddcbf8f83d","target":"graph","created_at":"2026-07-05T08:34:13Z","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/2402.11281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the deep semantics of images is essential in the era dominated by social media. However, current research works primarily on the superficial description of images, revealing a notable deficiency in the systematic investigation of the inherent deep semantics. In this work, we introduce DEEPEVAL, a comprehensive benchmark to assess Large Multimodal Models' (LMMs) capacities of visual deep semantics. DEEPEVAL includes human-annotated dataset and three progressive subtasks: fine-grained description selection, in-depth title matching, and deep semantics understanding. Utilizing DEEPEV","authors_text":"Heming Xia, Qingxiu Dong, Yixin Yang, Zheng Li, Zhifang Sui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-17T13:41:44Z","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11281","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":"sha256:804f569c81ed9fc908b0fde7769c71ed7b795c422528b001cd2e1822c50fe7ce","target":"record","created_at":"2026-07-05T08:34:13Z","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":"d71aef7de5132d02af992d302350745583f84d36c97c3aafbe2e862830904897","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-17T13:41:44Z","title_canon_sha256":"913e903ddfa17eb6400cf48dd6d1222527cfd05a74d82478b907e6215799d395"},"schema_version":"1.0","source":{"id":"2402.11281","kind":"arxiv","version":3}},"canonical_sha256":"7ecbcaa2dccb718c4a96dcc0b91774a5f91d2e306906f63f070977de817aa7a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ecbcaa2dccb718c4a96dcc0b91774a5f91d2e306906f63f070977de817aa7a9","first_computed_at":"2026-07-05T08:34:13.273513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:13.273513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ddEOLG4qhpt9VTPLrAAvUKDK4maOEwzixGTY12LM0HtI1S8akO2SSiEyTmsoNUhPsNBnXt3mzt2Csp2+3Vt7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:13.273925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11281","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:804f569c81ed9fc908b0fde7769c71ed7b795c422528b001cd2e1822c50fe7ce","sha256:36c9de3da6aa3109f2bd1a0fedab261048a230025473e1b334c404ddcbf8f83d"],"state_sha256":"9fb3debab19d5cdc4e9cd646fc67dbdf638924e9eee5aece3f9c4f3462b2d26d"}