{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CHYJIZAMIHLY4M5IIN4UYVIO7G","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":"a2d99304960260a10703b4fdd7ec5630b250d16eda79f94902403842e55f7dce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T12:24:07Z","title_canon_sha256":"523daff025ea0d1851b69f1a6de6d669a645ec3352ccd8f5853d523ef9526a5d"},"schema_version":"1.0","source":{"id":"2307.12732","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12732","created_at":"2026-07-05T08:16:21Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12732v2","created_at":"2026-07-05T08:16:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12732","created_at":"2026-07-05T08:16:21Z"},{"alias_kind":"pith_short_12","alias_value":"CHYJIZAMIHLY","created_at":"2026-07-05T08:16:21Z"},{"alias_kind":"pith_short_16","alias_value":"CHYJIZAMIHLY4M5I","created_at":"2026-07-05T08:16:21Z"},{"alias_kind":"pith_short_8","alias_value":"CHYJIZAM","created_at":"2026-07-05T08:16:21Z"}],"graph_snapshots":[{"event_id":"sha256:ec5133055a93dfa5be2f74103d33e213752d9d7111b4198602dcae98916b3820","target":"graph","created_at":"2026-07-05T08:16:21Z","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/2307.12732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has become a promising language-supervised visual pre-training framework. This paper aims to distill small CLIP models supervised by a large teacher CLIP model. We propose several distillation strategies, including relation, feature, gradient and contrastive paradigms, to examine the effectiveness of CLIP-Knowledge Distillation (KD). We show that a simple feature mimicry with Mean Squared Error loss works surprisingly well. Moreover, interactive contrastive learning across teacher and student encoders is also effective in performance improvement. ","authors_text":"Boyu Diao, Chuanguang Yang, Han Yang, Junyu Bi, Libo Huang, Xinqiang Yu, Yongjun Xu, Zhulin An","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T12:24:07Z","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12732","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:eaef5921e778fa5d611358a238a9f6b96909e21879cc797e96fd85c7234661ff","target":"record","created_at":"2026-07-05T08:16:21Z","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":"a2d99304960260a10703b4fdd7ec5630b250d16eda79f94902403842e55f7dce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T12:24:07Z","title_canon_sha256":"523daff025ea0d1851b69f1a6de6d669a645ec3352ccd8f5853d523ef9526a5d"},"schema_version":"1.0","source":{"id":"2307.12732","kind":"arxiv","version":2}},"canonical_sha256":"11f094640c41d78e33a843794c550ef9b047a9d5d149b2811b04323b710535d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11f094640c41d78e33a843794c550ef9b047a9d5d149b2811b04323b710535d9","first_computed_at":"2026-07-05T08:16:21.657709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:21.657709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ULQwZdZeObydpzmZFMUJNBg3H79CxKquSK8hrx+YGrHzLZ9MvpDC0xMDOQLFFGUhvnyWc8pEP9LwylPkjoWnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:21.658187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12732","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaef5921e778fa5d611358a238a9f6b96909e21879cc797e96fd85c7234661ff","sha256:ec5133055a93dfa5be2f74103d33e213752d9d7111b4198602dcae98916b3820"],"state_sha256":"6162809201fc336a9ed7a7408068099e2c45cde908dc3193f6670fb9d0291cfc"}