{"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"}