{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YHS4S3AI2XMWSSZ7YL3HNUNGYU","short_pith_number":"pith:YHS4S3AI","canonical_record":{"source":{"id":"2111.14447","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T11:01:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8497285d922229852e04128dae0786b43666c23f637cae1b9c9da45d7275c4b7","abstract_canon_sha256":"5d2e5f27558f797586229b0a48d9a11e3f50cb177c14d979e111fc4b64deb620"},"schema_version":"1.0"},"canonical_sha256":"c1e5c96c08d5d9694b3fc2f676d1a6c52aa0c16daa83ff69995f50ea18247187","source":{"kind":"arxiv","id":"2111.14447","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14447","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14447v2","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14447","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"YHS4S3AI2XMW","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"YHS4S3AI2XMWSSZ7","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"YHS4S3AI","created_at":"2026-07-05T04:10:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YHS4S3AI2XMWSSZ7YL3HNUNGYU","target":"record","payload":{"canonical_record":{"source":{"id":"2111.14447","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T11:01:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8497285d922229852e04128dae0786b43666c23f637cae1b9c9da45d7275c4b7","abstract_canon_sha256":"5d2e5f27558f797586229b0a48d9a11e3f50cb177c14d979e111fc4b64deb620"},"schema_version":"1.0"},"canonical_sha256":"c1e5c96c08d5d9694b3fc2f676d1a6c52aa0c16daa83ff69995f50ea18247187","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:24.751580Z","signature_b64":"Y1hYF/sVlwBx2CHJmOHoaYRSJcfD2vyONMSM/8N55o5uY2q5UP/bVGN/QmzH3FQz9oRvGm4PLdahUzVDo5+tBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1e5c96c08d5d9694b3fc2f676d1a6c52aa0c16daa83ff69995f50ea18247187","last_reissued_at":"2026-07-05T04:10:24.751109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:24.751109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.14447","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XN8PwvcLk9Rt3USvrwsUz+PQkLUHej5bxzjNARyoTo+bkY0kK7xn9IaUW/V1yxI3+aPVXzOSc+xSzOJLp+LnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:55:49.742946Z"},"content_sha256":"afe39ae5581e486a1fb04c4c4a76197576b2d2805481aebbaefc5b5c8e87ec47","schema_version":"1.0","event_id":"sha256:afe39ae5581e486a1fb04c4c4a76197576b2d2805481aebbaefc5b5c8e87ec47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YHS4S3AI2XMWSSZ7YL3HNUNGYU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Idan Schwartz, Lior Wolf, Yoad Tewel, Yoav Shalev","submitted_at":"2021-11-29T11:01:49Z","abstract_excerpt":"Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image. In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning steps. This is done by combining the visual-semantic model with a large language model, benefiting from the knowledge in both web-scale models. The resulting captions are much less "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14447","kind":"arxiv","version":2},"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/2111.14447/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":"2026-07-05T04:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9IjecD7xLWm6z6GpfdJ9NMzXcYra9QIciaSyv53MiBIiafylw/64BF3elk2XZUAbC2SwlhHSYVXP8+B/O/npCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:55:49.743594Z"},"content_sha256":"dc5cf3e12e787149e80c8e8f1596b28b8eca3f60a742919c46366fa0ffa116a8","schema_version":"1.0","event_id":"sha256:dc5cf3e12e787149e80c8e8f1596b28b8eca3f60a742919c46366fa0ffa116a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU/bundle.json","state_url":"https://pith.science/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU/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":"2026-08-14T07:55:49Z","links":{"resolver":"https://pith.science/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU","bundle":"https://pith.science/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU/bundle.json","state":"https://pith.science/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHS4S3AI2XMWSSZ7YL3HNUNGYU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YHS4S3AI2XMWSSZ7YL3HNUNGYU","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":"5d2e5f27558f797586229b0a48d9a11e3f50cb177c14d979e111fc4b64deb620","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T11:01:49Z","title_canon_sha256":"8497285d922229852e04128dae0786b43666c23f637cae1b9c9da45d7275c4b7"},"schema_version":"1.0","source":{"id":"2111.14447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14447","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14447v2","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14447","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"YHS4S3AI2XMW","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"YHS4S3AI2XMWSSZ7","created_at":"2026-07-05T04:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"YHS4S3AI","created_at":"2026-07-05T04:10:24Z"}],"graph_snapshots":[{"event_id":"sha256:dc5cf3e12e787149e80c8e8f1596b28b8eca3f60a742919c46366fa0ffa116a8","target":"graph","created_at":"2026-07-05T04:10:24Z","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/2111.14447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image. In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning steps. This is done by combining the visual-semantic model with a large language model, benefiting from the knowledge in both web-scale models. The resulting captions are much less ","authors_text":"Idan Schwartz, Lior Wolf, Yoad Tewel, Yoav Shalev","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T11:01:49Z","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14447","kind":"arxiv","version":2},"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:afe39ae5581e486a1fb04c4c4a76197576b2d2805481aebbaefc5b5c8e87ec47","target":"record","created_at":"2026-07-05T04:10:24Z","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":"5d2e5f27558f797586229b0a48d9a11e3f50cb177c14d979e111fc4b64deb620","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T11:01:49Z","title_canon_sha256":"8497285d922229852e04128dae0786b43666c23f637cae1b9c9da45d7275c4b7"},"schema_version":"1.0","source":{"id":"2111.14447","kind":"arxiv","version":2}},"canonical_sha256":"c1e5c96c08d5d9694b3fc2f676d1a6c52aa0c16daa83ff69995f50ea18247187","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1e5c96c08d5d9694b3fc2f676d1a6c52aa0c16daa83ff69995f50ea18247187","first_computed_at":"2026-07-05T04:10:24.751109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:24.751109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1hYF/sVlwBx2CHJmOHoaYRSJcfD2vyONMSM/8N55o5uY2q5UP/bVGN/QmzH3FQz9oRvGm4PLdahUzVDo5+tBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:24.751580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.14447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afe39ae5581e486a1fb04c4c4a76197576b2d2805481aebbaefc5b5c8e87ec47","sha256:dc5cf3e12e787149e80c8e8f1596b28b8eca3f60a742919c46366fa0ffa116a8"],"state_sha256":"1b04f67f83c7f816bd01db5683671466e8daf87646069cc6bb7b92259777e066"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6Dqjh9HyPVhXzyQpa6q6CyYatpxPwprKnegg2fmhBcl4tlhEJbhAjFn/mRHK2oaZyFK52NtIlgGb7XfXZWMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:55:49.749522Z","bundle_sha256":"1f1d75846a9d5288fca50dc7ad3cfcb6528340175994aa0dc117c3f9f7f3c284"}}