{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B6QOIM6VMXEWI6JKXFQLALRSHE","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":"70fa50c236999af8d20071ca534662ed7d703f99fc3c66e105aa17edb353b8db","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T22:59:56Z","title_canon_sha256":"0c0344880b7b1c78bb5ec1cb34691043a46375b719ef983c43e61f3df598361d"},"schema_version":"1.0","source":{"id":"2309.04041","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04041","created_at":"2026-07-05T07:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04041v2","created_at":"2026-07-05T07:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04041","created_at":"2026-07-05T07:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"B6QOIM6VMXEW","created_at":"2026-07-05T07:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"B6QOIM6VMXEWI6JK","created_at":"2026-07-05T07:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"B6QOIM6V","created_at":"2026-07-05T07:33:19Z"}],"graph_snapshots":[{"event_id":"sha256:6d6ff07717f08620e11582c6763a23153802eebad8df014b842baa6ccce24f77","target":"graph","created_at":"2026-07-05T07:33:19Z","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/2309.04041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is their constrained semantic grounding ability, which pertains to connecting language to the physical-world entities or concepts referenced in images. Therefore, a crucial need arises for a comprehensive study to assess the semantic grounding ability of widely used LVLMs. Despite the significance, sufficient investigation in this direction is currently lacking","authors_text":"Baochen Sun, Carl Yang, Jiaying Lu, Jie Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T22:59:56Z","title":"Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04041","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":"sha256:63c0ad89073cf513531ce4c5af27cbbd43cb9adb6904757b426349bb3dac867d","target":"record","created_at":"2026-07-05T07:33:19Z","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":"70fa50c236999af8d20071ca534662ed7d703f99fc3c66e105aa17edb353b8db","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T22:59:56Z","title_canon_sha256":"0c0344880b7b1c78bb5ec1cb34691043a46375b719ef983c43e61f3df598361d"},"schema_version":"1.0","source":{"id":"2309.04041","kind":"arxiv","version":2}},"canonical_sha256":"0fa0e433d565c964792ab960b02e323907a32621ffed6ea6f28b84d95e01f73c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fa0e433d565c964792ab960b02e323907a32621ffed6ea6f28b84d95e01f73c","first_computed_at":"2026-07-05T07:33:19.580153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:19.580153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2dMaNx1LMZKlL6Z7hKwsJ0GGC6l+3FPm+6jiKNXRo5/mQK9w4F+qCEoiDCDx6Nl/TlJvekryRqYuKNRAYSiOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:19.580694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04041","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63c0ad89073cf513531ce4c5af27cbbd43cb9adb6904757b426349bb3dac867d","sha256:6d6ff07717f08620e11582c6763a23153802eebad8df014b842baa6ccce24f77"],"state_sha256":"f8aa40c0e889a0a251b4030581e969f077d3c05230b0fd701715a84fa35cd757"}