{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6HXEEPZ2N4L4TWNRLF2OIBOLHG","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":"d77e0bb954cd3e72ba59425a8c69d3f1d38b2c91eb7061f50dca6631edb23449","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:59:38Z","title_canon_sha256":"95dd9876129bdf4d1d92379d2b417dc9a27787d6e2730635588575e5369535e2"},"schema_version":"1.0","source":{"id":"2204.03647","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03647","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03647v1","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03647","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"6HXEEPZ2N4L4","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"6HXEEPZ2N4L4TWNR","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"6HXEEPZ2","created_at":"2026-07-05T04:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:03b657395abf3e21e3594bc9a8975d41a9d84f80ebff2e827479284a000e270a","target":"graph","created_at":"2026-07-05T04:12:32Z","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/2204.03647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised or weakly supervised methods for phrase localization (textual grounding) either rely on human annotations or some other supervised models, e.g., object detectors. Obtaining these annotations is labor-intensive and may be difficult to scale in practice. We propose to leverage recent advances in contrastive language-vision models, CLIP, pre-trained on image and caption pairs collected from the internet. In its original form, CLIP only outputs an image-level embedding without any spatial resolution. We adapt CLIP to generate high-resolution spatial feature maps. Importantly, we can ext","authors_text":"Greg Shakhnarovich, Jiahao Li, Raymond A. Yeh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:59:38Z","title":"Adapting CLIP For Phrase Localization Without Further Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03647","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":"sha256:484a8e2fd1f66784a434bcbe3f7a57484fdab3065c436155c26a5fd8291cb8b8","target":"record","created_at":"2026-07-05T04:12:32Z","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":"d77e0bb954cd3e72ba59425a8c69d3f1d38b2c91eb7061f50dca6631edb23449","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:59:38Z","title_canon_sha256":"95dd9876129bdf4d1d92379d2b417dc9a27787d6e2730635588575e5369535e2"},"schema_version":"1.0","source":{"id":"2204.03647","kind":"arxiv","version":1}},"canonical_sha256":"f1ee423f3a6f17c9d9b15974e405cb3982733085a2a5e77334cf77a1d934f777","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1ee423f3a6f17c9d9b15974e405cb3982733085a2a5e77334cf77a1d934f777","first_computed_at":"2026-07-05T04:12:32.618641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:32.618641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DG1Dgy50TNLjeGqJP0YnH52VkYj4bBAeb/WGa9j8tLflJFf458u2iOZMkuStBFTbk9iaseY+VV7SqrFKp7JRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:32.619015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03647","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:484a8e2fd1f66784a434bcbe3f7a57484fdab3065c436155c26a5fd8291cb8b8","sha256:03b657395abf3e21e3594bc9a8975d41a9d84f80ebff2e827479284a000e270a"],"state_sha256":"81177210ae24892c8f4e96a477508a7137ca89335afe58ceeb40856a0aa059a4"}