{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HDB5PCWIBFP4GCORQ7R6ZKBM5U","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":"60d77f9e236f6038593d2cae79a5c854edf7bce0b9fbf6baf2bc5e187e14ec5f","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T14:53:19Z","title_canon_sha256":"c584c04fbe428013809b1ab472a76fe5e9df4e6c6eaac0fddc1f1a4eb45085b8"},"schema_version":"1.0","source":{"id":"2402.04050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04050","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04050v2","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04050","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"HDB5PCWIBFP4","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"HDB5PCWIBFP4GCOR","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"HDB5PCWI","created_at":"2026-07-05T08:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:ba8da51dcb54fd1547bfdecaeaa4b8446f8226733f0befd4c5c79053608df9d1","target":"graph","created_at":"2026-07-05T08:26:18Z","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/2402.04050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the emergence of pretrained vision-language models (VLMs), considerable efforts have been devoted to fine-tuning them for downstream tasks. Despite the progress made in designing efficient fine-tuning methods, such methods require access to the model's parameters, which can be challenging as model owners often opt to provide their models as a black box to safeguard model ownership. This paper proposes a \\textbf{C}ollabo\\textbf{ra}tive \\textbf{F}ine-\\textbf{T}uning (\\textbf{CraFT}) approach for fine-tuning black-box VLMs to downstream tasks, where one only has access to the input prompts a","authors_text":"Jian Liang, Ran He, Tieniu Tan, Zhengbo Wang, Zilei Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T14:53:19Z","title":"Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04050","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:f9fa6e3a203dd1ee6814406b570e703e316779260347da2f556cfa12c4fc9baa","target":"record","created_at":"2026-07-05T08:26:18Z","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":"60d77f9e236f6038593d2cae79a5c854edf7bce0b9fbf6baf2bc5e187e14ec5f","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T14:53:19Z","title_canon_sha256":"c584c04fbe428013809b1ab472a76fe5e9df4e6c6eaac0fddc1f1a4eb45085b8"},"schema_version":"1.0","source":{"id":"2402.04050","kind":"arxiv","version":2}},"canonical_sha256":"38c3d78ac8095fc309d187e3eca82ced04c0bea6a231913e36c1391f10518488","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38c3d78ac8095fc309d187e3eca82ced04c0bea6a231913e36c1391f10518488","first_computed_at":"2026-07-05T08:26:18.849709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:18.849709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N3S2b1QjGVI3TBHqNxlYTihrDXuB04gjE4Ax4QJ27p2CDIv7AZeUeD/jBVrBs2jEI4XhmTbF7s3He87sIZ3sCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:18.850195Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9fa6e3a203dd1ee6814406b570e703e316779260347da2f556cfa12c4fc9baa","sha256:ba8da51dcb54fd1547bfdecaeaa4b8446f8226733f0befd4c5c79053608df9d1"],"state_sha256":"98f3b8cab37f8b9d53b33cbb346876a166fe82b213894702e1452ea02f449a8c"}