{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SZM5DM7YSBFIXOUDN4OIM4T64H","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":"1e15f077b8339bce84a7f04b45a4a0061e4114799408adb99807f8b8317b9c8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T05:01:03Z","title_canon_sha256":"4099c05a304dc98544c9b1d5f46fb92b7df6e6406a8c40b6e0cc74f2bf5eba93"},"schema_version":"1.0","source":{"id":"2209.07046","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07046","created_at":"2026-07-05T05:19:36Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07046v2","created_at":"2026-07-05T05:19:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07046","created_at":"2026-07-05T05:19:36Z"},{"alias_kind":"pith_short_12","alias_value":"SZM5DM7YSBFI","created_at":"2026-07-05T05:19:36Z"},{"alias_kind":"pith_short_16","alias_value":"SZM5DM7YSBFIXOUD","created_at":"2026-07-05T05:19:36Z"},{"alias_kind":"pith_short_8","alias_value":"SZM5DM7Y","created_at":"2026-07-05T05:19:36Z"}],"graph_snapshots":[{"event_id":"sha256:07a8333cae2120cab28f97d5afaef6d806709e57bc6c675620fc9974caceb6ea","target":"graph","created_at":"2026-07-05T05:19:36Z","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/2209.07046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail, segmentation, retrieval, caption, and video. However, the visual explainability of CLIP is rarely studied, especially for the raw feature map. To provide visual explanations of its predictions, we propose the Image-Text Similarity Map (ITSM). Based on it, we surprisingly find that CLIP prefers the background regions than the foregrounds, and shows erroneous","authors_text":"Hang Xu, Hualiang Wang, Xiaomeng Li, Yi Li, Yiqun Duan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T05:01:03Z","title":"Exploring Visual Interpretability for Contrastive Language-Image Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07046","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":"sha256:3f1626f385f10ff92288a8b30abc87ab8e9df41e90e32809b93d3ce8e4e6f5e0","target":"record","created_at":"2026-07-05T05:19:36Z","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":"1e15f077b8339bce84a7f04b45a4a0061e4114799408adb99807f8b8317b9c8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T05:01:03Z","title_canon_sha256":"4099c05a304dc98544c9b1d5f46fb92b7df6e6406a8c40b6e0cc74f2bf5eba93"},"schema_version":"1.0","source":{"id":"2209.07046","kind":"arxiv","version":2}},"canonical_sha256":"9659d1b3f8904a8bba836f1c86727ee1ee8814592a3027cada69bd606a78131d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9659d1b3f8904a8bba836f1c86727ee1ee8814592a3027cada69bd606a78131d","first_computed_at":"2026-07-05T05:19:36.628995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:36.628995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YHgw1v3pAMITtAVp4g1Lr4VWtWUydVUB3Oq7wtnzVLJEmT2EjDnlhMNky4ZwpCqFDqznbAGG7uISlRJtUCtkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:36.629476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07046","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f1626f385f10ff92288a8b30abc87ab8e9df41e90e32809b93d3ce8e4e6f5e0","sha256:07a8333cae2120cab28f97d5afaef6d806709e57bc6c675620fc9974caceb6ea"],"state_sha256":"c0a6fb81f6221fb55a77c34f94fd65ec19d7f4b8cd4e937c3d7e74fd75bbe241"}