{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7YUNHCRRQ5G5INXQO3NIBNT4ZK","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":"6ad9c501178ec31d787ae6732d2927ae6b58d67793fa15b9334faa73d6074fe6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T20:48:12Z","title_canon_sha256":"4954c41cc5444b065841840cf6ef5811f6fc359fa18fb6eec942d33024354257"},"schema_version":"1.0","source":{"id":"2107.06383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06383","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06383v1","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06383","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_12","alias_value":"7YUNHCRRQ5G5","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_16","alias_value":"7YUNHCRRQ5G5INXQ","created_at":"2026-07-05T02:57:57Z"},{"alias_kind":"pith_short_8","alias_value":"7YUNHCRR","created_at":"2026-07-05T02:57:57Z"}],"graph_snapshots":[{"event_id":"sha256:9d7f9c8254d313958f6ccb86104e46192b60c0316a58db33f95225d49198dc78","target":"graph","created_at":"2026-07-05T02:57:57Z","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/2107.06383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that large-scale pretraining usually can result in better generalization performance, e.g., CLIP (Contrastive Language-Image Pre-training), trained on a massive amount of image-caption pairs, has shown a strong zero-shot capability on various vision tasks. To further study the advantage brought by CLIP, we propose to use CLIP as the visual encoder in various V&L ","authors_text":"Anna Rohrbach, Hao Tan, Kai-Wei Chang, Kurt Keutzer, Liunian Harold Li, Mohit Bansal, Sheng Shen, Zhewei Yao","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T20:48:12Z","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06383","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:a69187a2d35f1003be1136f16db7623bee0db7ace9fb5743329b9653a288374b","target":"record","created_at":"2026-07-05T02:57:57Z","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":"6ad9c501178ec31d787ae6732d2927ae6b58d67793fa15b9334faa73d6074fe6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T20:48:12Z","title_canon_sha256":"4954c41cc5444b065841840cf6ef5811f6fc359fa18fb6eec942d33024354257"},"schema_version":"1.0","source":{"id":"2107.06383","kind":"arxiv","version":1}},"canonical_sha256":"fe28d38a31874dd436f076da80b67cca9f4aa384dfb8797e0c758ae46c4b749c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe28d38a31874dd436f076da80b67cca9f4aa384dfb8797e0c758ae46c4b749c","first_computed_at":"2026-07-05T02:57:57.489264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:57.489264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vgs2BDgDVmZrW9JGapFo+6BmM/GClbGeCmG7gfH1KZ65sDgGTif5HI5vGjLeeZVTMbaOOz0LK1X88rQpBqRVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:57.489760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a69187a2d35f1003be1136f16db7623bee0db7ace9fb5743329b9653a288374b","sha256:9d7f9c8254d313958f6ccb86104e46192b60c0316a58db33f95225d49198dc78"],"state_sha256":"e2ccf6267ec2812ce286c3022ca0f6361139f2b352d44e86e126e8caf5a319f9"}