{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NQ7C5VQSCJILMA76KVJGDRTTOS","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":"5e8076b7c2f685e560a535cec0ada5f2ae4219be93ec67f371372255651155ad","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:41:44Z","title_canon_sha256":"5e28547f3c01f1286288b26ba08f516c52feebfe63441892a645bc61e54a2ec1"},"schema_version":"1.0","source":{"id":"2211.11720","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11720","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11720v3","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11720","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"NQ7C5VQSCJIL","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"NQ7C5VQSCJILMA76","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"NQ7C5VQS","created_at":"2026-07-05T05:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:9d7605eec6bbf7a789c3e39955dae9df44ec4c2438ae3f872048e0df21677b48","target":"graph","created_at":"2026-07-05T05:22:12Z","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/2211.11720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (","authors_text":"Bohan Zhai, Joseph E. Gonzalez, Kurt Keutzer, Sheng Shen, Shijia Yang, Tianjun Zhang, Trevor Darrell","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:41:44Z","title":"Multitask Vision-Language Prompt Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11720","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:ee5fa62259ca2152ce793dea29818710fbbfcdcd86e2b9b5f5c66c69b4c537e3","target":"record","created_at":"2026-07-05T05:22:12Z","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":"5e8076b7c2f685e560a535cec0ada5f2ae4219be93ec67f371372255651155ad","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:41:44Z","title_canon_sha256":"5e28547f3c01f1286288b26ba08f516c52feebfe63441892a645bc61e54a2ec1"},"schema_version":"1.0","source":{"id":"2211.11720","kind":"arxiv","version":3}},"canonical_sha256":"6c3e2ed6121250b603fe555261c67374925d50388b9d8b5347bf706abe03b0d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c3e2ed6121250b603fe555261c67374925d50388b9d8b5347bf706abe03b0d7","first_computed_at":"2026-07-05T05:22:12.663236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:12.663236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LbVnMDkYwdPqKMImOKdRdvehU32hnc1A5ooUswsoRtkX1gaXGDurpU/X6KYkbWQSOvfHvs+SJFZgRlbkHzIdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:12.663709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11720","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee5fa62259ca2152ce793dea29818710fbbfcdcd86e2b9b5f5c66c69b4c537e3","sha256:9d7605eec6bbf7a789c3e39955dae9df44ec4c2438ae3f872048e0df21677b48"],"state_sha256":"1ba2fb591698f09003f90b6b8b84e92abf2dc809d00db9fff57451aab86c6dee"}