{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WE3DIJH5AKOVI7ADOSQ4SBAJII","short_pith_number":"pith:WE3DIJH5","canonical_record":{"source":{"id":"2111.09734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T14:49:15Z","cross_cats_sorted":[],"title_canon_sha256":"c2c4134138739a9737c29b2b0b1fe311c1124f104c842f11210de2dccc9846d0","abstract_canon_sha256":"f013ae48f7969453e4c9f3d43dd99453ed01fd855c90ede5b84ac6c28e1745c2"},"schema_version":"1.0"},"canonical_sha256":"b1363424fd029d547c0374a1c904094226b140ed12b97492116fb03a8790349a","source":{"kind":"arxiv","id":"2111.09734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09734","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09734v1","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09734","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"pith_short_12","alias_value":"WE3DIJH5AKOV","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"pith_short_16","alias_value":"WE3DIJH5AKOVI7AD","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"pith_short_8","alias_value":"WE3DIJH5","created_at":"2026-07-05T03:33:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WE3DIJH5AKOVI7ADOSQ4SBAJII","target":"record","payload":{"canonical_record":{"source":{"id":"2111.09734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T14:49:15Z","cross_cats_sorted":[],"title_canon_sha256":"c2c4134138739a9737c29b2b0b1fe311c1124f104c842f11210de2dccc9846d0","abstract_canon_sha256":"f013ae48f7969453e4c9f3d43dd99453ed01fd855c90ede5b84ac6c28e1745c2"},"schema_version":"1.0"},"canonical_sha256":"b1363424fd029d547c0374a1c904094226b140ed12b97492116fb03a8790349a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:14.847739Z","signature_b64":"Q5jFbqnQPFFBo6KvwrG/qYWjWqvz9t0ZQkN2Twey7JdTtSHBnfd3jzfJgsIXYUyrT3DbLtneByv1l5oKqR9WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1363424fd029d547c0374a1c904094226b140ed12b97492116fb03a8790349a","last_reissued_at":"2026-07-05T03:33:14.847169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:14.847169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.09734","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":"2026-07-05T03:33:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYPWNzWi7p5fG/EUPY9jeaKGTVZ9Qnpkbv1U9Dqm0GRX2R/tSLvo2AgOm2l6N1Z878fEig9A/2MrkU7zaoRiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:23:31.668450Z"},"content_sha256":"531c3055c33b085690908db8f3ea0e93d784abc3a73f80ab0c61db40ef1977d6","schema_version":"1.0","event_id":"sha256:531c3055c33b085690908db8f3ea0e93d784abc3a73f80ab0c61db40ef1977d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WE3DIJH5AKOVI7ADOSQ4SBAJII","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClipCap: CLIP Prefix for Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Hertz, Amit H. Bermano, Ron Mokady","submitted_at":"2021-11-18T14:49:15Z","abstract_excerpt":"Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image. In this paper, we present a simple approach to address this task. We use CLIP encoding as a prefix to the caption, by employing a simple mapping network, and then fine-tunes a language model to generate the image captions. The recently proposed CLIP model contains rich semantic features which were trained with textual context, making it best for vision-language perception. Our key idea is that together with a pre-trained language model (GPT2), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09734","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/2111.09734/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":"2026-07-05T03:33:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXB/Q77lIc9bPp2A+kVgJkSgpeI1KXp66VX+P9GlwJycuTOGPtbOibYMRn2Ry7V9y4KMR7rZMDNW+WZDLx09AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:23:31.669471Z"},"content_sha256":"140db3588f27ca732eda8f9dead763a96a64f7ce4b85d56f237c84bb3bfe6890","schema_version":"1.0","event_id":"sha256:140db3588f27ca732eda8f9dead763a96a64f7ce4b85d56f237c84bb3bfe6890"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII/bundle.json","state_url":"https://pith.science/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII/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":"2026-08-06T12:23:31Z","links":{"resolver":"https://pith.science/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII","bundle":"https://pith.science/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII/bundle.json","state":"https://pith.science/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WE3DIJH5AKOVI7ADOSQ4SBAJII/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WE3DIJH5AKOVI7ADOSQ4SBAJII","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":"f013ae48f7969453e4c9f3d43dd99453ed01fd855c90ede5b84ac6c28e1745c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T14:49:15Z","title_canon_sha256":"c2c4134138739a9737c29b2b0b1fe311c1124f104c842f11210de2dccc9846d0"},"schema_version":"1.0","source":{"id":"2111.09734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09734","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09734v1","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09734","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"pith_short_12","alias_value":"WE3DIJH5AKOV","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"pith_short_16","alias_value":"WE3DIJH5AKOVI7AD","created_at":"2026-07-05T03:33:14Z"},{"alias_kind":"pith_short_8","alias_value":"WE3DIJH5","created_at":"2026-07-05T03:33:14Z"}],"graph_snapshots":[{"event_id":"sha256:140db3588f27ca732eda8f9dead763a96a64f7ce4b85d56f237c84bb3bfe6890","target":"graph","created_at":"2026-07-05T03:33:14Z","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/2111.09734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image. In this paper, we present a simple approach to address this task. We use CLIP encoding as a prefix to the caption, by employing a simple mapping network, and then fine-tunes a language model to generate the image captions. The recently proposed CLIP model contains rich semantic features which were trained with textual context, making it best for vision-language perception. Our key idea is that together with a pre-trained language model (GPT2), ","authors_text":"Amir Hertz, Amit H. Bermano, Ron Mokady","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T14:49:15Z","title":"ClipCap: CLIP Prefix for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09734","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":"sha256:531c3055c33b085690908db8f3ea0e93d784abc3a73f80ab0c61db40ef1977d6","target":"record","created_at":"2026-07-05T03:33:14Z","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":"f013ae48f7969453e4c9f3d43dd99453ed01fd855c90ede5b84ac6c28e1745c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T14:49:15Z","title_canon_sha256":"c2c4134138739a9737c29b2b0b1fe311c1124f104c842f11210de2dccc9846d0"},"schema_version":"1.0","source":{"id":"2111.09734","kind":"arxiv","version":1}},"canonical_sha256":"b1363424fd029d547c0374a1c904094226b140ed12b97492116fb03a8790349a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1363424fd029d547c0374a1c904094226b140ed12b97492116fb03a8790349a","first_computed_at":"2026-07-05T03:33:14.847169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:14.847169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q5jFbqnQPFFBo6KvwrG/qYWjWqvz9t0ZQkN2Twey7JdTtSHBnfd3jzfJgsIXYUyrT3DbLtneByv1l5oKqR9WDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:14.847739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:531c3055c33b085690908db8f3ea0e93d784abc3a73f80ab0c61db40ef1977d6","sha256:140db3588f27ca732eda8f9dead763a96a64f7ce4b85d56f237c84bb3bfe6890"],"state_sha256":"36b347d1bf414d7174e5cc25135c90ebaf345dab57b76b3df678262c5b37c3df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ko95/bsCPbtopCit/GcnpJcqcJ2lc7e4bGYPrYBGgYHXzmnOJFk2VNGyUW/C66gRmsDMk1vtcI9/Cb2S0tQ0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:23:31.676631Z","bundle_sha256":"9dffbd79757124a73252c78c29e1fca1e70957334dcaa55e28458578734752c5"}}