{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QE5KZCD7WW6LPKZD4G4GVXHG46","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":"1c97843972f79638c744310e5690f52532eb263e5d0d72ae27a2cd3b5ae10d64","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-21T20:20:13Z","title_canon_sha256":"a4110da7b6ef234ad6867101f4c140ddc604aca5d0bae5c9da95cbc106178d08"},"schema_version":"1.0","source":{"id":"2310.14108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14108","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14108v1","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14108","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"QE5KZCD7WW6L","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"QE5KZCD7WW6LPKZD","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"QE5KZCD7","created_at":"2026-07-05T07:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:15ca73a505eae72cdd435b03345e5cce0435fb432c1935209ab3578f9d18d690","target":"graph","created_at":"2026-07-05T07:03:39Z","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/2310.14108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization capabilities. This paper studies the following question: Can we augment CLIP training with task-specific vision models from model zoos to improve its visual representations? Towards this end, we leverage open-source task-specific vision models to generate pseudo-labels for an uncurated and noisy image-text dataset. Subsequently, we train CLIP models on these pseud","authors_text":"Ali Farhadi, Fartash Faghri, Hadi Pouransari, Maxwell Horton, Mehrdad Farajtabar, Mohammad Rastegari, Mohammadreza Salehi, Oncel Tuzel, Raviteja Vemulapalli, Sachin Mehta","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-21T20:20:13Z","title":"CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14108","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":"sha256:6b3ae6de018281aefc25d1268428847521c426e010c15ed4c8668eaf0548f53b","target":"record","created_at":"2026-07-05T07:03:39Z","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":"1c97843972f79638c744310e5690f52532eb263e5d0d72ae27a2cd3b5ae10d64","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-21T20:20:13Z","title_canon_sha256":"a4110da7b6ef234ad6867101f4c140ddc604aca5d0bae5c9da95cbc106178d08"},"schema_version":"1.0","source":{"id":"2310.14108","kind":"arxiv","version":1}},"canonical_sha256":"813aac887fb5bcb7ab23e1b86adce6e7820cc320cde502617324e511aff236db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813aac887fb5bcb7ab23e1b86adce6e7820cc320cde502617324e511aff236db","first_computed_at":"2026-07-05T07:03:39.752581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:39.752581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HNziAFAv8GyG/jt1WXqmk8rBcypK7BbGlZV4Pi4/KWzQsEhpjWQHlyY4Qto/ePzmCmK8MWQhow2GqrjkeXWpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:39.752981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b3ae6de018281aefc25d1268428847521c426e010c15ed4c8668eaf0548f53b","sha256:15ca73a505eae72cdd435b03345e5cce0435fb432c1935209ab3578f9d18d690"],"state_sha256":"25d23bb5c3e27b84a1c870fe73eb86adc8d3b35838f0ad165b4c253122f094b2"}