{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WDAFBTB5RISC3SYNXFA5ANRHEZ","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":"36a4842bc1f68003335608e76a0821f5b22c921332f951c51e2300fa53cf9c67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-28T09:29:06Z","title_canon_sha256":"e98315189e5a7a4388b1b99141586776b137b292c1ba2d9db1a6e101270e073e"},"schema_version":"1.0","source":{"id":"2306.16048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16048","created_at":"2026-07-05T08:33:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16048v3","created_at":"2026-07-05T08:33:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16048","created_at":"2026-07-05T08:33:30Z"},{"alias_kind":"pith_short_12","alias_value":"WDAFBTB5RISC","created_at":"2026-07-05T08:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WDAFBTB5RISC3SYN","created_at":"2026-07-05T08:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WDAFBTB5","created_at":"2026-07-05T08:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:f0d00afeaa11e775b2aa9bc9e2d2a0ed6d9b314085a19c0ef1722ba61af8177c","target":"graph","created_at":"2026-07-05T08:33:30Z","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/2306.16048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world settings. Our benchmarks test VLMs' consistency in understanding concepts across semantic granularity levels and their response to varying text specificity. Findings show that VLMs favor moderately fine-grained concepts and struggle with specificity, often misjudging texts that differ from their training data. Extensive evaluations reveal limitations in current ","authors_text":"Abhay Mittal, Davide Modolo, Joseph Tighe, Manchen Wang, Paolo Favaro, Tiffany Deng, Yanbei Chen, Yi Zhu, Zhenlin Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-28T09:29:06Z","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16048","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":"sha256:243f64a67f5852fb6eb1c33db2fa7a6742129e481b856fd1f031726e9395e3da","target":"record","created_at":"2026-07-05T08:33:30Z","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":"36a4842bc1f68003335608e76a0821f5b22c921332f951c51e2300fa53cf9c67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-28T09:29:06Z","title_canon_sha256":"e98315189e5a7a4388b1b99141586776b137b292c1ba2d9db1a6e101270e073e"},"schema_version":"1.0","source":{"id":"2306.16048","kind":"arxiv","version":3}},"canonical_sha256":"b0c050cc3d8a242dcb0db941d03627265981eda3c35e99308b3fb9d6102a44d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0c050cc3d8a242dcb0db941d03627265981eda3c35e99308b3fb9d6102a44d3","first_computed_at":"2026-07-05T08:33:30.873183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:30.873183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"84flMrqBkJYm2StOC/rZwvxYzdB5iqgnCQx4ufGBF6miW/rvy+CE4KWQlv6EQa8hDDCaksif6MNgUFmkOr0fDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:30.873900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243f64a67f5852fb6eb1c33db2fa7a6742129e481b856fd1f031726e9395e3da","sha256:f0d00afeaa11e775b2aa9bc9e2d2a0ed6d9b314085a19c0ef1722ba61af8177c"],"state_sha256":"2a8adbab3327ad4a6f58b36ef022a254962b86b616340e243b7f7d1a9902f91e"}