{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J6A4BURFS6IQ7Y2UA2SHTR647N","short_pith_number":"pith:J6A4BURF","canonical_record":{"source":{"id":"2211.09778","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:52:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0faca857c59a7dcb15b9a52e0ce2792cf21c4a1f7fec9ba4706aca659a09b03b","abstract_canon_sha256":"555a301a7b72f0492bf5fb32ba4a1b861b925835c52dbf236a20e51362432c97"},"schema_version":"1.0"},"canonical_sha256":"4f81c0d22597910fe35406a479c7dcfb44afd6d58a7b6b9a90e982edbdd434b1","source":{"kind":"arxiv","id":"2211.09778","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09778","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09778v4","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09778","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"pith_short_12","alias_value":"J6A4BURFS6IQ","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"pith_short_16","alias_value":"J6A4BURFS6IQ7Y2U","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"pith_short_8","alias_value":"J6A4BURF","created_at":"2026-07-05T06:42:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J6A4BURFS6IQ7Y2UA2SHTR647N","target":"record","payload":{"canonical_record":{"source":{"id":"2211.09778","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:52:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0faca857c59a7dcb15b9a52e0ce2792cf21c4a1f7fec9ba4706aca659a09b03b","abstract_canon_sha256":"555a301a7b72f0492bf5fb32ba4a1b861b925835c52dbf236a20e51362432c97"},"schema_version":"1.0"},"canonical_sha256":"4f81c0d22597910fe35406a479c7dcfb44afd6d58a7b6b9a90e982edbdd434b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:40.654795Z","signature_b64":"9qlDrXzC/siRMGi6Ig9kXoHjBPWBTxfDxgTdfiUCScTruLJSxSWD+prJ4GJUklbCk1+o+JGjF151GHews7QaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f81c0d22597910fe35406a479c7dcfb44afd6d58a7b6b9a90e982edbdd434b1","last_reissued_at":"2026-07-05T06:42:40.653990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:40.653990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.09778","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:42:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BaTV8pSA3h0g+/jKnG0B3ivhUcTacPyOobPXaNyNpLC0bCS9EtLOOKgZQnNwZHWAiJfrhg3o4x7jLPZjBz3NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:41:30.188370Z"},"content_sha256":"25119e724bdfb7f08a76615347851595c7abf655267d36543404090f45c54b07","schema_version":"1.0","event_id":"sha256:25119e724bdfb7f08a76615347851595c7abf655267d36543404090f45c54b07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J6A4BURFS6IQ7Y2UA2SHTR647N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Christopher Clark, Sophia Gu","submitted_at":"2022-11-17T18:52:19Z","abstract_excerpt":"Many high-level skills that are required for computer vision tasks, such as parsing questions, comparing and contrasting semantics, and writing descriptions, are also required in other domains such as natural language processing. In this paper, we ask whether it is possible to learn those skills from text data and then transfer them to vision tasks without ever training on visual training data. Key to our approach is exploiting the joint embedding space of contrastively trained vision and language encoders. In practice, there can be systematic differences between embedding spaces for different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09778","kind":"arxiv","version":4},"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/2211.09778/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":"2026-07-05T06:42:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00WT9XL9GIGCCoKIX8KWpGVvlcyn4xG+P6+LNPigO7ta7jUtPyz8WSeKkJFpAFzdsBS96CwZPzaYyIIUtRmhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:41:30.188880Z"},"content_sha256":"c60c6f73c4418b9d3610c0624bd40b6671f469546d1c2aef59cf883438cc0c10","schema_version":"1.0","event_id":"sha256:c60c6f73c4418b9d3610c0624bd40b6671f469546d1c2aef59cf883438cc0c10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J6A4BURFS6IQ7Y2UA2SHTR647N/bundle.json","state_url":"https://pith.science/pith/J6A4BURFS6IQ7Y2UA2SHTR647N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J6A4BURFS6IQ7Y2UA2SHTR647N/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":"2026-08-08T10:41:30Z","links":{"resolver":"https://pith.science/pith/J6A4BURFS6IQ7Y2UA2SHTR647N","bundle":"https://pith.science/pith/J6A4BURFS6IQ7Y2UA2SHTR647N/bundle.json","state":"https://pith.science/pith/J6A4BURFS6IQ7Y2UA2SHTR647N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J6A4BURFS6IQ7Y2UA2SHTR647N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J6A4BURFS6IQ7Y2UA2SHTR647N","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":"555a301a7b72f0492bf5fb32ba4a1b861b925835c52dbf236a20e51362432c97","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:52:19Z","title_canon_sha256":"0faca857c59a7dcb15b9a52e0ce2792cf21c4a1f7fec9ba4706aca659a09b03b"},"schema_version":"1.0","source":{"id":"2211.09778","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09778","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09778v4","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09778","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"pith_short_12","alias_value":"J6A4BURFS6IQ","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"pith_short_16","alias_value":"J6A4BURFS6IQ7Y2U","created_at":"2026-07-05T06:42:40Z"},{"alias_kind":"pith_short_8","alias_value":"J6A4BURF","created_at":"2026-07-05T06:42:40Z"}],"graph_snapshots":[{"event_id":"sha256:c60c6f73c4418b9d3610c0624bd40b6671f469546d1c2aef59cf883438cc0c10","target":"graph","created_at":"2026-07-05T06:42:40Z","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/2211.09778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many high-level skills that are required for computer vision tasks, such as parsing questions, comparing and contrasting semantics, and writing descriptions, are also required in other domains such as natural language processing. In this paper, we ask whether it is possible to learn those skills from text data and then transfer them to vision tasks without ever training on visual training data. Key to our approach is exploiting the joint embedding space of contrastively trained vision and language encoders. In practice, there can be systematic differences between embedding spaces for different","authors_text":"Aniruddha Kembhavi, Christopher Clark, Sophia Gu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:52:19Z","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09778","kind":"arxiv","version":4},"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":"sha256:25119e724bdfb7f08a76615347851595c7abf655267d36543404090f45c54b07","target":"record","created_at":"2026-07-05T06:42:40Z","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":"555a301a7b72f0492bf5fb32ba4a1b861b925835c52dbf236a20e51362432c97","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:52:19Z","title_canon_sha256":"0faca857c59a7dcb15b9a52e0ce2792cf21c4a1f7fec9ba4706aca659a09b03b"},"schema_version":"1.0","source":{"id":"2211.09778","kind":"arxiv","version":4}},"canonical_sha256":"4f81c0d22597910fe35406a479c7dcfb44afd6d58a7b6b9a90e982edbdd434b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f81c0d22597910fe35406a479c7dcfb44afd6d58a7b6b9a90e982edbdd434b1","first_computed_at":"2026-07-05T06:42:40.653990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:40.653990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9qlDrXzC/siRMGi6Ig9kXoHjBPWBTxfDxgTdfiUCScTruLJSxSWD+prJ4GJUklbCk1+o+JGjF151GHews7QaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:40.654795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09778","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25119e724bdfb7f08a76615347851595c7abf655267d36543404090f45c54b07","sha256:c60c6f73c4418b9d3610c0624bd40b6671f469546d1c2aef59cf883438cc0c10"],"state_sha256":"09ed0872f96f7fb6bd274094b1df5b6fc80d07ce4480101600dd809b8b6169fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmzoEhINzrSs5gu1E+GEzwWQDX716R47YlcHNMFRr0QOhhNEJnxUdV2C9gl7tJ1IjGp27rspiEH6TwxWFMCVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:41:30.192813Z","bundle_sha256":"8c761daa4d8987d338db1eb5e292e002981059dbd3c774b3f2ebd79981556eaf"}}