{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G627CSU7AXN7RRDW5FEFTGPXDS","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":"f0ff155fe5828ae9280e77a74ea9edc5b2a92e878c7a2d37f4715f3f3984be7f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T04:03:41Z","title_canon_sha256":"f2b89275b72d6dae89e988ebd0fbeebf9b68cbfc6ada1322c3c8267329022943"},"schema_version":"1.0","source":{"id":"2309.05950","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05950","created_at":"2026-07-05T08:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05950v5","created_at":"2026-07-05T08:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05950","created_at":"2026-07-05T08:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"G627CSU7AXN7","created_at":"2026-07-05T08:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"G627CSU7AXN7RRDW","created_at":"2026-07-05T08:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"G627CSU7","created_at":"2026-07-05T08:18:44Z"}],"graph_snapshots":[{"event_id":"sha256:0e6fbac342d9a202890c7c4b40e59ee67db3804ec187850702c8529b1d64aad8","target":"graph","created_at":"2026-07-05T08:18:44Z","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/2309.05950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities on downstream tasks when fine-tuned with minimal data. However, many VLMs rely on proprietary data and are not open-source, which restricts the use of white-box approaches for fine-tuning. As such, we aim to develop a black-box approach to optimize VLMs through natural language prompts, thereby avoiding the need to access model parameters, feature embeddings, or even output logits. We propose employing chat-based LLMs to search for the best text prompt for VLMs. Specifically, we adopt an a","authors_text":"Deepak Pathak, Deva Ramanan, Ryan Lee, Samuel Yu, Shihong Liu, Tiffany Ling, Zhiqiu Lin","cross_cats":["cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T04:03:41Z","title":"Language Models as Black-Box Optimizers for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05950","kind":"arxiv","version":5},"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:ebdf6480e4bac06cda95a416b25f12cee39895d5402ed7ae5ec1d772deae5235","target":"record","created_at":"2026-07-05T08:18:44Z","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":"f0ff155fe5828ae9280e77a74ea9edc5b2a92e878c7a2d37f4715f3f3984be7f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T04:03:41Z","title_canon_sha256":"f2b89275b72d6dae89e988ebd0fbeebf9b68cbfc6ada1322c3c8267329022943"},"schema_version":"1.0","source":{"id":"2309.05950","kind":"arxiv","version":5}},"canonical_sha256":"37b5f14a9f05dbf8c476e9485999f71cb73df229a2da7419e8619c9d1bf163cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37b5f14a9f05dbf8c476e9485999f71cb73df229a2da7419e8619c9d1bf163cb","first_computed_at":"2026-07-05T08:18:44.112431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:44.112431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7DOfTQsSumxdZcimtXxR8lCzw+/EySmYj3JyRU8+Y3YE8fW5Ec3khWCkcZ4y+mwKm9BEm4+BSvQ8cn6QIhvODw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:44.112957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05950","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebdf6480e4bac06cda95a416b25f12cee39895d5402ed7ae5ec1d772deae5235","sha256:0e6fbac342d9a202890c7c4b40e59ee67db3804ec187850702c8529b1d64aad8"],"state_sha256":"2fcf7dc6f2f80a4d6209dd694fa52886c5764db92a93351fa60e6cc7e5bd3899"}