{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2SLRRC7RIPPUYRYW3VAAKC6QG3","short_pith_number":"pith:2SLRRC7R","canonical_record":{"source":{"id":"2203.07190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T15:29:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"00b8a4ed8b2dd97ff3328ee6dc516e39208f1f8ab76cf0d32c8d58dcdd1c8bf3","abstract_canon_sha256":"4990404bbcc9be1bdf53b4686ce7cee11639e8076f67b87d2f92727825742b3b"},"schema_version":"1.0"},"canonical_sha256":"d497188bf143df4c4716dd40050bd036c1cb8e313b1173a4cd69e118cfdb2c2a","source":{"kind":"arxiv","id":"2203.07190","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2SLRRC7RIPPUYRYW3VAAKC6QG3","target":"record","payload":{"canonical_record":{"source":{"id":"2203.07190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T15:29:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"00b8a4ed8b2dd97ff3328ee6dc516e39208f1f8ab76cf0d32c8d58dcdd1c8bf3","abstract_canon_sha256":"4990404bbcc9be1bdf53b4686ce7cee11639e8076f67b87d2f92727825742b3b"},"schema_version":"1.0"},"canonical_sha256":"d497188bf143df4c4716dd40050bd036c1cb8e313b1173a4cd69e118cfdb2c2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:00.500287Z","signature_b64":"G7uh7W+6FMYvwnLqDy0+sfpwWcIEY/zBst61hVmoO8PZmASt3KrAMp5NvEayLwY5JDTg5VeoRGwEGrMElru8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d497188bf143df4c4716dd40050bd036c1cb8e313b1173a4cd69e118cfdb2c2a","last_reissued_at":"2026-07-05T04:05:00.499800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:00.499800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.07190","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0hcwbAwy0d8XDuNxIZwROupY0hMiMtHYPYjNC5rkg3opXZQi/ZQiqavQLjjoS0pyjpJwmiBV1o4ggXbNj95oCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:02:41.877047Z"},"content_sha256":"62cdfde95ae812895dcf2a348304bb06a65c9cfafcb152777fa29c453ead9c74","schema_version":"1.0","event_id":"sha256:62cdfde95ae812895dcf2a348304bb06a65c9cfafcb152777fa29c453ead9c74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2SLRRC7RIPPUYRYW3VAAKC6QG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Haoyu Song, Li Dong, Ting Liu, Wei-Nan Zhang","submitted_at":"2022-03-14T15:29:27Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07190","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.07190/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYqhCLjyuiu6uxInw4NMvqdQ+w91xdUIxogLny/rn/vF3BO63/WhmUmXvqdfyxK0UqWOFeW7/K0wBvhlXcj0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:02:41.877903Z"},"content_sha256":"bcbc315c6ebe335d0d305063fb41156e6224e34a403f0184a72368a4052e7b47","schema_version":"1.0","event_id":"sha256:bcbc315c6ebe335d0d305063fb41156e6224e34a403f0184a72368a4052e7b47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3/bundle.json","state_url":"https://pith.science/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T08:02:41Z","links":{"resolver":"https://pith.science/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3","bundle":"https://pith.science/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3/bundle.json","state":"https://pith.science/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SLRRC7RIPPUYRYW3VAAKC6QG3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cpxus3HqdDz1q/ZUkqJqW6SuQmPkwHv+5JHkznc3DGc1fVhQEOYiAXepEv2/kLazHIq5kjhDGmvbcgkJ5QFkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:02:41.882366Z","bundle_sha256":"31d89f809c2824d2c03412d25e5dbf517ede16d5f9929490c89fbf4aff6e1696"}}