{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XEYJVJNBE4JLIHYGAE4AF6YLR7","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":"3bd7a42cccf3392d3b234bb411715aa0a8a65716c68ac3ed767ee8a3ce9e9998","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:39:36Z","title_canon_sha256":"f63f928dd6cc6c33bb07ace4bf90ff217a28652e66ed7c0feefe4ee167e49fd0"},"schema_version":"1.0","source":{"id":"2112.09106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.09106","created_at":"2026-07-05T03:41:35Z"},{"alias_kind":"arxiv_version","alias_value":"2112.09106v1","created_at":"2026-07-05T03:41:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09106","created_at":"2026-07-05T03:41:35Z"},{"alias_kind":"pith_short_12","alias_value":"XEYJVJNBE4JL","created_at":"2026-07-05T03:41:35Z"},{"alias_kind":"pith_short_16","alias_value":"XEYJVJNBE4JLIHYG","created_at":"2026-07-05T03:41:35Z"},{"alias_kind":"pith_short_8","alias_value":"XEYJVJNB","created_at":"2026-07-05T03:41:35Z"}],"graph_snapshots":[{"event_id":"sha256:17823242f868e66e5cf55b58beedc75d3dbf2c22f743e74a3153eb8da38f3cae","target":"graph","created_at":"2026-07-05T03:41:35Z","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/2112.09106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visu","authors_text":"Chunyuan Li, Jianfeng Gao, Jianwei Yang, Liunian Harold Li, Luowei Zhou, Lu Yuan, Noel Codella, Pengchuan Zhang, Xiyang Dai, Yin Li, Yiwu Zhong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:39:36Z","title":"RegionCLIP: Region-based Language-Image Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09106","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":"sha256:66d8bfa63b0c5d6d98941439210ebf6453f1e72bd2ddb4e0d8ba8608a727420d","target":"record","created_at":"2026-07-05T03:41:35Z","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":"3bd7a42cccf3392d3b234bb411715aa0a8a65716c68ac3ed767ee8a3ce9e9998","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:39:36Z","title_canon_sha256":"f63f928dd6cc6c33bb07ace4bf90ff217a28652e66ed7c0feefe4ee167e49fd0"},"schema_version":"1.0","source":{"id":"2112.09106","kind":"arxiv","version":1}},"canonical_sha256":"b9309aa5a12712b41f06013802fb0b8fe0501dcdd720883d79ee0e8729df7591","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9309aa5a12712b41f06013802fb0b8fe0501dcdd720883d79ee0e8729df7591","first_computed_at":"2026-07-05T03:41:35.960158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:35.960158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PLNJW40SvIjBXFG+oD5dIk90rhMWoxV0iMs+8U3BmdmHBYEfKDM3kRE/DkmvjV9o4Y6/Ak34Nj/GHnDWIlYdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:35.960566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.09106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66d8bfa63b0c5d6d98941439210ebf6453f1e72bd2ddb4e0d8ba8608a727420d","sha256:17823242f868e66e5cf55b58beedc75d3dbf2c22f743e74a3153eb8da38f3cae"],"state_sha256":"bbd3e18c3d4ddcf1b794db81f488b039510c6d1ee14baba07aeb04809f23dfca"}