{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IL3BMEVDBSGN6YCJVKO6ANHSIC","short_pith_number":"pith:IL3BMEVD","schema_version":"1.0","canonical_sha256":"42f61612a30c8cdf6049aa9de034f240aa56e0df4ff83e5bb6e87d4b78a09586","source":{"kind":"arxiv","id":"2407.00592","version":1},"attestation_state":"computed","paper":{"title":"Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Ranjan, Daniel Wen, Karthik Bhat","submitted_at":"2024-06-30T05:23:11Z","abstract_excerpt":"Understanding the limitations and weaknesses of state-of-the-art models in artificial intelligence is crucial for their improvement and responsible application. In this research, we focus on CLIP, a model renowned for its integration of vision and language processing. Our objective is to uncover recurring problems and blind spots in CLIP's image comprehension. By delving into both the commonalities and disparities between CLIP and human image understanding, we augment our comprehension of these models' capabilities. Through our analysis, we reveal significant discrepancies in CLIP's interpreta"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.00592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T05:23:11Z","cross_cats_sorted":[],"title_canon_sha256":"b02d4d76d8445ee9aa7be0bf7f7c521b050073bbf6de414e38cecb27c32c1f19","abstract_canon_sha256":"4ee2ce2d9ed622cf779abab3a43596dba8338f5352c3f991c1d01a37a7303893"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:22.006806Z","signature_b64":"ijMYru3zGtc4j03tOpymXyxpRwxHnT42d6BSnB4Mplu49NPcu9V08ykTSGRQPw7c5PsQN9hsQBaaNg9oMp92Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42f61612a30c8cdf6049aa9de034f240aa56e0df4ff83e5bb6e87d4b78a09586","last_reissued_at":"2026-07-05T08:38:22.006378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:22.006378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Ranjan, Daniel Wen, Karthik Bhat","submitted_at":"2024-06-30T05:23:11Z","abstract_excerpt":"Understanding the limitations and weaknesses of state-of-the-art models in artificial intelligence is crucial for their improvement and responsible application. In this research, we focus on CLIP, a model renowned for its integration of vision and language processing. Our objective is to uncover recurring problems and blind spots in CLIP's image comprehension. By delving into both the commonalities and disparities between CLIP and human image understanding, we augment our comprehension of these models' capabilities. Through our analysis, we reveal significant discrepancies in CLIP's interpreta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00592","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.00592/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.00592","created_at":"2026-07-05T08:38:22.006439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00592v1","created_at":"2026-07-05T08:38:22.006439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00592","created_at":"2026-07-05T08:38:22.006439+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL3BMEVDBSGN","created_at":"2026-07-05T08:38:22.006439+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL3BMEVDBSGN6YCJ","created_at":"2026-07-05T08:38:22.006439+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL3BMEVD","created_at":"2026-07-05T08:38:22.006439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06775","citing_title":"Enhancing Performance of Explainable AI Models with Constrained Concept Refinement","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC","json":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC.json","graph_json":"https://pith.science/api/pith-number/IL3BMEVDBSGN6YCJVKO6ANHSIC/graph.json","events_json":"https://pith.science/api/pith-number/IL3BMEVDBSGN6YCJVKO6ANHSIC/events.json","paper":"https://pith.science/paper/IL3BMEVD"},"agent_actions":{"view_html":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC","download_json":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC.json","view_paper":"https://pith.science/paper/IL3BMEVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00592&json=true","fetch_graph":"https://pith.science/api/pith-number/IL3BMEVDBSGN6YCJVKO6ANHSIC/graph.json","fetch_events":"https://pith.science/api/pith-number/IL3BMEVDBSGN6YCJVKO6ANHSIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC/action/storage_attestation","attest_author":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC/action/author_attestation","sign_citation":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC/action/citation_signature","submit_replication":"https://pith.science/pith/IL3BMEVDBSGN6YCJVKO6ANHSIC/action/replication_record"}},"created_at":"2026-07-05T08:38:22.006439+00:00","updated_at":"2026-07-05T08:38:22.006439+00:00"}