{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BPHR6WNDSWYU546TSICMCE34R7","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":"5ba28c24ef036c7f28c3c420b3bdc28ff50966317d395f44948c687c58e2eeba","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:30Z","title_canon_sha256":"b3a3fd8e37b4f0ce5426ed39c1134208f7a1a396f08680b7cf1b429fb6b01244"},"schema_version":"1.0","source":{"id":"2312.03818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03818","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03818v2","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03818","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"BPHR6WNDSWYU","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"BPHR6WNDSWYU546T","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"BPHR6WND","created_at":"2026-07-05T07:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:4a820cdb203eca438a541e81bc367617af51e0c21a5c8d7ddfae8f93885bb685","target":"graph","created_at":"2026-07-05T07:24:02Z","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/2312.03818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the details, even those irrelevant to specific tasks. However, for a finer understanding and controlled editing of images, it becomes crucial to focus on specific regions of interest, which can be indicated as points, masks, or boxes by humans or perception models. To fulfill the requirements, we introduce Alpha-CLIP, an enhanced version of CLIP with an auxiliary ","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Shu Kong, Tong Wu, Ye Fang, Yuanjun Xiong, Yuhang Zang, Zeyi Sun","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:30Z","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03818","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:c99d67572edb9aa0cf63af38f01e28fbf6c06280696667d674d3ec68c1c0eed2","target":"record","created_at":"2026-07-05T07:24:02Z","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":"5ba28c24ef036c7f28c3c420b3bdc28ff50966317d395f44948c687c58e2eeba","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:30Z","title_canon_sha256":"b3a3fd8e37b4f0ce5426ed39c1134208f7a1a396f08680b7cf1b429fb6b01244"},"schema_version":"1.0","source":{"id":"2312.03818","kind":"arxiv","version":2}},"canonical_sha256":"0bcf1f59a395b14ef3d39204c1137c8ffeaa8308790cbe6abbfde15fb1e506f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bcf1f59a395b14ef3d39204c1137c8ffeaa8308790cbe6abbfde15fb1e506f5","first_computed_at":"2026-07-05T07:24:02.777852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:02.777852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bwvIYCOCqbLsoniv5LCnCkzyZZK24RNOTBlIvKanfuON0mA7/iT+uganQkr4gJII2xXvVCjbKObJSaqLkZ/DAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:02.778290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c99d67572edb9aa0cf63af38f01e28fbf6c06280696667d674d3ec68c1c0eed2","sha256:4a820cdb203eca438a541e81bc367617af51e0c21a5c8d7ddfae8f93885bb685"],"state_sha256":"7d08c780969b98cc1a6fe53c9151ef3f2429af570544d2a2860afec543cc891d"}