{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LT73Z4J3R6ZOFZ3QJFKOQZWJE6","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":"04bf0976de38b14917d9ed60d3ace63a2d50fb55f18d67094d385dd6c506cc9f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T01:25:00Z","title_canon_sha256":"57d3cd6a4ab6da240d88f25d3bf2c0bc97ce2007968daa566563cd80149e3fd0"},"schema_version":"1.0","source":{"id":"2401.12425","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12425","created_at":"2026-07-05T08:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12425v3","created_at":"2026-07-05T08:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12425","created_at":"2026-07-05T08:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"LT73Z4J3R6ZO","created_at":"2026-07-05T08:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"LT73Z4J3R6ZOFZ3Q","created_at":"2026-07-05T08:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"LT73Z4J3","created_at":"2026-07-05T08:21:48Z"}],"graph_snapshots":[{"event_id":"sha256:f6de7bb6bd10f1875630e5b3cf8e5d629e5baf788d15c790d160fc48114d5998","target":"graph","created_at":"2026-07-05T08:21:48Z","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/2401.12425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below 10% for more than ten concepts like night snake, presumably due to their limited presence in the pretraining data. However, measuring the frequency of concepts in VLMs' large-scale datasets is challenging. We address this by using large language models (LLMs) to count the number of pretraining texts that contain synonyms of these concepts. Our analysis confirm","authors_text":"Deva Ramanan, James Caverlee, Shubham Parashar, Shu Kong, Tian Liu, Xiangjue Dong, Yanan Li, Zhiqiu Lin","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T01:25:00Z","title":"The Neglected Tails in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12425","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:e982bab469298a184e2bf8e57898cdd435f6a303e66ee3e38620240b9aa2e111","target":"record","created_at":"2026-07-05T08:21:48Z","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":"04bf0976de38b14917d9ed60d3ace63a2d50fb55f18d67094d385dd6c506cc9f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T01:25:00Z","title_canon_sha256":"57d3cd6a4ab6da240d88f25d3bf2c0bc97ce2007968daa566563cd80149e3fd0"},"schema_version":"1.0","source":{"id":"2401.12425","kind":"arxiv","version":3}},"canonical_sha256":"5cffbcf13b8fb2e2e7704954e866c927a118c9e7732c919cb023ec7ceaa61c92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cffbcf13b8fb2e2e7704954e866c927a118c9e7732c919cb023ec7ceaa61c92","first_computed_at":"2026-07-05T08:21:48.430009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:48.430009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Tu0555YQRQo+ZdhzevcFDqNwZeFeiV9app45b+q7FlCU/bCa+Q4a2OSHUUZgV5dfoLzFVBLTlHlnoiLY5DvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:48.430534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12425","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e982bab469298a184e2bf8e57898cdd435f6a303e66ee3e38620240b9aa2e111","sha256:f6de7bb6bd10f1875630e5b3cf8e5d629e5baf788d15c790d160fc48114d5998"],"state_sha256":"58b782298c21f6802acdf55e9d95b23323d2b103d63bfed8ca0d11918c9b7f70"}