{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZRDTYVKGGLZPHAKXIPKS7CQJZ","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":"e61625fc81d8fb60a07da46f69a809f41ffaf373eeea7abd9e7c99fd0ad37a90","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-10T15:19:40Z","title_canon_sha256":"d5e1eec2da1fecaa34e02a84efe55c84f63eba33c462fc3da6eb28282b4c6a6d"},"schema_version":"1.0","source":{"id":"2409.06579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06579","created_at":"2026-07-05T09:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06579v1","created_at":"2026-07-05T09:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06579","created_at":"2026-07-05T09:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"LZRDTYVKGGLZ","created_at":"2026-07-05T09:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"LZRDTYVKGGLZPHAK","created_at":"2026-07-05T09:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"LZRDTYVK","created_at":"2026-07-05T09:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:d69090d8bf04fdc7a7a78014c306a66fe8f734e825a66d6131d0c3feaf42455a","target":"graph","created_at":"2026-07-05T09:05:26Z","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/2409.06579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP is one of the most popular foundational models and is heavily used for many vision-language tasks. However, little is known about the inner workings of CLIP. To bridge this gap we propose a study to quantify the interpretability in CLIP like models. We conduct this study on six different CLIP models from OpenAI and OpenCLIP which vary by size, type of pre-training data and patch size. Our approach begins with using the TEXTSPAN algorithm and in-context learning to break down individual attention heads into specific properties. We then evaluate how easily these heads can be interpreted usi","authors_text":"Avinash Madasu, Phillip Howard, Vasudev Lal, Yossi Gandelsman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-10T15:19:40Z","title":"Quantifying and Enabling the Interpretability of CLIP-like Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06579","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:d6c649a92d96d7d8de48c8468f7f659fc90f0c9fa6daa2afcad5f8b80550183e","target":"record","created_at":"2026-07-05T09:05:26Z","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":"e61625fc81d8fb60a07da46f69a809f41ffaf373eeea7abd9e7c99fd0ad37a90","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-10T15:19:40Z","title_canon_sha256":"d5e1eec2da1fecaa34e02a84efe55c84f63eba33c462fc3da6eb28282b4c6a6d"},"schema_version":"1.0","source":{"id":"2409.06579","kind":"arxiv","version":1}},"canonical_sha256":"5e6239e2aa3197979c0aba1ea97c504e72812bfc1f9d67d28bc3a929cd33c92c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e6239e2aa3197979c0aba1ea97c504e72812bfc1f9d67d28bc3a929cd33c92c","first_computed_at":"2026-07-05T09:05:26.584289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:26.584289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4GMdZhFH8Tnt9YkwG5dBzmGg1pO0VjYOK66BQiUD/yZ4xxGmwPZjYn+3Mw0i1zRhq0LhpVSRdvc/3gC4HpDRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:26.584687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6c649a92d96d7d8de48c8468f7f659fc90f0c9fa6daa2afcad5f8b80550183e","sha256:d69090d8bf04fdc7a7a78014c306a66fe8f734e825a66d6131d0c3feaf42455a"],"state_sha256":"2f453ee2d22cf61a1271d9dd7d852e0a93b68c26f34511607f33b6abf56c4d1e"}