{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2SLRRC7RIPPUYRYW3VAAKC6QG3","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":"4990404bbcc9be1bdf53b4686ce7cee11639e8076f67b87d2f92727825742b3b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T15:29:27Z","title_canon_sha256":"00b8a4ed8b2dd97ff3328ee6dc516e39208f1f8ab76cf0d32c8d58dcdd1c8bf3"},"schema_version":"1.0","source":{"id":"2203.07190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.07190","created_at":"2026-07-05T04:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2203.07190v1","created_at":"2026-07-05T04:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07190","created_at":"2026-07-05T04:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"2SLRRC7RIPPU","created_at":"2026-07-05T04:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"2SLRRC7RIPPUYRYW","created_at":"2026-07-05T04:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"2SLRRC7R","created_at":"2026-07-05T04:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:bcbc315c6ebe335d0d305063fb41156e6224e34a403f0184a72368a4052e7b47","target":"graph","created_at":"2026-07-05T04:05:00Z","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/2203.07190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLIP itself should also have acquired some few-shot abilities for vision-language tasks. In this work, we empirically show that CLIP can be a strong vision-language few-shot learner by leveraging the power of language. We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality ","authors_text":"Furu Wei, Haoyu Song, Li Dong, Ting Liu, Wei-Nan Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T15:29:27Z","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07190","kind":"arxiv","version":1},"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":"sha256:62cdfde95ae812895dcf2a348304bb06a65c9cfafcb152777fa29c453ead9c74","target":"record","created_at":"2026-07-05T04:05:00Z","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":"4990404bbcc9be1bdf53b4686ce7cee11639e8076f67b87d2f92727825742b3b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T15:29:27Z","title_canon_sha256":"00b8a4ed8b2dd97ff3328ee6dc516e39208f1f8ab76cf0d32c8d58dcdd1c8bf3"},"schema_version":"1.0","source":{"id":"2203.07190","kind":"arxiv","version":1}},"canonical_sha256":"d497188bf143df4c4716dd40050bd036c1cb8e313b1173a4cd69e118cfdb2c2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d497188bf143df4c4716dd40050bd036c1cb8e313b1173a4cd69e118cfdb2c2a","first_computed_at":"2026-07-05T04:05:00.499800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:00.499800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G7uh7W+6FMYvwnLqDy0+sfpwWcIEY/zBst61hVmoO8PZmASt3KrAMp5NvEayLwY5JDTg5VeoRGwEGrMElru8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:00.500287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.07190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62cdfde95ae812895dcf2a348304bb06a65c9cfafcb152777fa29c453ead9c74","sha256:bcbc315c6ebe335d0d305063fb41156e6224e34a403f0184a72368a4052e7b47"],"state_sha256":"7354d96da7396bf61833fb35068d6ab777831076167da0395ac16b98a29da5f8"}