{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L2NLX3UFBWZO5BCH5DQYFWR7UG","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":"419559ab3fbc5f846933061ef4a7031c96e14f70582d797edf07032c52227501","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-04T12:50:04Z","title_canon_sha256":"89c0fbb3234198b4541ba2a200192cbf26f5992a9666cc18f6792f0be679eaa8"},"schema_version":"1.0","source":{"id":"2507.03542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03542","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03542v2","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03542","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"L2NLX3UFBWZO","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"L2NLX3UFBWZO5BCH","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"L2NLX3UF","created_at":"2026-07-05T11:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:f30f8dcd869651bd05ca68f86060d31a4920730bd258a34f43640eb2417dac13","target":"graph","created_at":"2026-07-05T11:34:11Z","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/2507.03542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based visual descriptors--ranging from simple class names to more descriptive phrases--are widely used in visual concept discovery and image classification with vision-language models (VLMs). Their effectiveness, however, depends on a complex interplay of factors, including semantic clarity, presence in the VLM's pre-training data, and how well the descriptors serve as a meaningful representation space. In this work, we systematically analyze descriptor quality along two key dimensions: (1) representational capacity, and (2) relationship with VLM pre-training data. We evaluate a spectrum ","authors_text":"Atharva Sehgal, Ethan Lin, Jennifer J. Sun, Linxi Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-04T12:50:04Z","title":"Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03542","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:a7e070304d70bddf121ef000ae3c9d980718208864228adc61c268e1319a011f","target":"record","created_at":"2026-07-05T11:34:11Z","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":"419559ab3fbc5f846933061ef4a7031c96e14f70582d797edf07032c52227501","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-04T12:50:04Z","title_canon_sha256":"89c0fbb3234198b4541ba2a200192cbf26f5992a9666cc18f6792f0be679eaa8"},"schema_version":"1.0","source":{"id":"2507.03542","kind":"arxiv","version":2}},"canonical_sha256":"5e9abbee850db2ee8447e8e182da3fa1942dcb1e7389e647654b33502883c49b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e9abbee850db2ee8447e8e182da3fa1942dcb1e7389e647654b33502883c49b","first_computed_at":"2026-07-05T11:34:11.337262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:11.337262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35ct3l+EYaft7qXpcmIdl00th3WY/TX8fzs5SfY+w3eEc45ME6E+T5P738nrjtOR4RNExfkRJZStMBvR39JRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:11.337699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7e070304d70bddf121ef000ae3c9d980718208864228adc61c268e1319a011f","sha256:f30f8dcd869651bd05ca68f86060d31a4920730bd258a34f43640eb2417dac13"],"state_sha256":"5fe3efee7e95354c02345aaf1a28580ff916fb1be9d5a08fb5fb5ca5226a3e9a"}