{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:66P3ZLUZGD4WOMRBSUCWPJSORN","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":"b16cdab3160143b52c7e46349cb1cab81a1f8d4ed8026e9fa4e3bcfad0595146","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T13:10:11Z","title_canon_sha256":"9145cb4857bff0ab2776de182f0c05ac23e0fa40909b2a918956514d3a8556e8"},"schema_version":"1.0","source":{"id":"2307.09233","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09233","created_at":"2026-07-05T08:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09233v3","created_at":"2026-07-05T08:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09233","created_at":"2026-07-05T08:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"66P3ZLUZGD4W","created_at":"2026-07-05T08:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"66P3ZLUZGD4WOMRB","created_at":"2026-07-05T08:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"66P3ZLUZ","created_at":"2026-07-05T08:38:33Z"}],"graph_snapshots":[{"event_id":"sha256:73f0ab0476668f96acaed9adc2bc1da46f8ae0ef11cb6453eafef9b0b2530478","target":"graph","created_at":"2026-07-05T08:38:33Z","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/2307.09233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or object-relationships) where their performance is no better than random chance. To address this, we introduce SDS-CLIP, a lightweight and sample-efficient distillation method to enhance CLIP's compositional visio-linguistic reasoning. Our approach fine-tunes CLIP using a distillation objective borrowed from large text-to-image generative models like Stable-Diffusio","authors_text":"Daniela Massiceti, Maziar Sanjabi, Samyadeep Basu, Shell Xu Hu, Soheil Feizi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T13:10:11Z","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09233","kind":"arxiv","version":3},"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":"sha256:834160aa3031abd1c61352adbb1696591baef9791e6c99ba92148340ecffa10b","target":"record","created_at":"2026-07-05T08:38:33Z","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":"b16cdab3160143b52c7e46349cb1cab81a1f8d4ed8026e9fa4e3bcfad0595146","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T13:10:11Z","title_canon_sha256":"9145cb4857bff0ab2776de182f0c05ac23e0fa40909b2a918956514d3a8556e8"},"schema_version":"1.0","source":{"id":"2307.09233","kind":"arxiv","version":3}},"canonical_sha256":"f79fbcae9930f9673221950567a64e8b4dadb3167f769b175b55efe3f44bf4e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f79fbcae9930f9673221950567a64e8b4dadb3167f769b175b55efe3f44bf4e3","first_computed_at":"2026-07-05T08:38:33.562653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:33.562653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qonkk9kvaGSvYR5tnRkCJE6gLjjkOxcMMCgpqbeNlSRKER+d+bbtMUSDVfRscR0Yuus9vzARcKvVmEE/rpf+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:33.563149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.09233","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:834160aa3031abd1c61352adbb1696591baef9791e6c99ba92148340ecffa10b","sha256:73f0ab0476668f96acaed9adc2bc1da46f8ae0ef11cb6453eafef9b0b2530478"],"state_sha256":"c76d6777330f0a677cc3a9d9bb3476131177ed4f7622142016b958b4733b58d8"}