{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:53K2NLBLSJYSSHTJD72EBN35VZ","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":"2f6d1f05e4521ed389c99203400cd5921cca00666d5c215e528bd0772f138ddd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T08:07:29Z","title_canon_sha256":"8b98fc9237b7e04a571f64088d86971268182cb1d822bb39f4962d72c56a1501"},"schema_version":"1.0","source":{"id":"2109.11797","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11797","created_at":"2026-07-05T04:24:56Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11797v3","created_at":"2026-07-05T04:24:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11797","created_at":"2026-07-05T04:24:56Z"},{"alias_kind":"pith_short_12","alias_value":"53K2NLBLSJYS","created_at":"2026-07-05T04:24:56Z"},{"alias_kind":"pith_short_16","alias_value":"53K2NLBLSJYSSHTJ","created_at":"2026-07-05T04:24:56Z"},{"alias_kind":"pith_short_8","alias_value":"53K2NLBL","created_at":"2026-07-05T04:24:56Z"}],"graph_snapshots":[{"event_id":"sha256:b14df4e4ee6a4d895a3c85644c18313d1c8a7f35b2ee2e987479043d392705f6","target":"graph","created_at":"2026-07-05T04:24:56Z","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/2109.11797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks. However, we note that there exists a significant gap between the objective forms of model pre-training and fine-tuning, resulting in a need for large amounts of labeled data to stimulate the visual grounding capability of VL-PTMs for downstream tasks. To address the challenge, we present Cross-modal Prompt Tuning (CPT, alternatively, Colorful Prompt Tuning), a novel paradigm for tuning VL-PTMs, which reformulates visual g","authors_text":"Ao Zhang, Maosong Sun, Tat-Seng Chua, Yuan Yao, Zhengyan Zhang, Zhiyuan Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T08:07:29Z","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11797","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":"sha256:5e2db5c1d1aeec0da75704942d6ab66df1c1c6bfe31441e6797d4a1d7e749d72","target":"record","created_at":"2026-07-05T04:24:56Z","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":"2f6d1f05e4521ed389c99203400cd5921cca00666d5c215e528bd0772f138ddd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T08:07:29Z","title_canon_sha256":"8b98fc9237b7e04a571f64088d86971268182cb1d822bb39f4962d72c56a1501"},"schema_version":"1.0","source":{"id":"2109.11797","kind":"arxiv","version":3}},"canonical_sha256":"eed5a6ac2b9271291e691ff440b77dae60033ae1448b76e1361f90c82f5e8960","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eed5a6ac2b9271291e691ff440b77dae60033ae1448b76e1361f90c82f5e8960","first_computed_at":"2026-07-05T04:24:56.469298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:56.469298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UeRA2SYJ+GsIt4xeZPbrpFQfbKAI5dGPxbucK9mgw9vIGq4wF+P+y4yLLJMVRwq7QTDQNZVc4yqRAW6Vakh3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:56.469707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.11797","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e2db5c1d1aeec0da75704942d6ab66df1c1c6bfe31441e6797d4a1d7e749d72","sha256:b14df4e4ee6a4d895a3c85644c18313d1c8a7f35b2ee2e987479043d392705f6"],"state_sha256":"968d97c0ee7614aa31e5a8dfc219fc150be0352fc61eafd8a0194e8353ab14ad"}