{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QVH4VBR5RMJX223ZM3DMAQC6YU","short_pith_number":"pith:QVH4VBR5","schema_version":"1.0","canonical_sha256":"854fca863d8b137d6b7966c6c0405ec50e78a13c288d451623ea3436b2ded182","source":{"kind":"arxiv","id":"2403.11497","version":2},"attestation_state":"computed","paper":{"title":"A Sober Look at the Robustness of CLIPs to Spurious Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Han, Ludwig Schmidt, Qizhou Wang, Tong Zhang, Yong Lin, Yongqiang Chen","submitted_at":"2024-03-18T06:04:02Z","abstract_excerpt":"Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet. However, existing test datasets are typically curated based on ImageNet-trained models, which aim to capture the spurious features inherited in ImageNet. Benchmarking CLIP models based on the ImageNet-oriented spurious features may not be sufficient to reflect the extent to which CLIP models are robust to spurious correlations within CLIP training data, e.g., LAION. To this end, we craft a new challenging dataset named CounterAnimal designed to reveal"},"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":"2403.11497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T06:04:02Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"27990f729fb12fb4fc734d923bca3257ea428e83441c90e5c29e1bffda0ad342","abstract_canon_sha256":"4b9afc8826d6bdc571bce1facc1f042e1212ee40aecf856de738dca86fe3f5e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:10.987641Z","signature_b64":"HjJ3F4NRgEkRCBJf4bHngWqHt0cJljz8rAakEF/NWrZQjbLRGVmins/JRCDKplmQroA54AO/rWpcAuKbdTalDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854fca863d8b137d6b7966c6c0405ec50e78a13c288d451623ea3436b2ded182","last_reissued_at":"2026-07-05T09:30:10.986074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:10.986074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sober Look at the Robustness of CLIPs to Spurious Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Han, Ludwig Schmidt, Qizhou Wang, Tong Zhang, Yong Lin, Yongqiang Chen","submitted_at":"2024-03-18T06:04:02Z","abstract_excerpt":"Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet. However, existing test datasets are typically curated based on ImageNet-trained models, which aim to capture the spurious features inherited in ImageNet. Benchmarking CLIP models based on the ImageNet-oriented spurious features may not be sufficient to reflect the extent to which CLIP models are robust to spurious correlations within CLIP training data, e.g., LAION. To this end, we craft a new challenging dataset named CounterAnimal designed to reveal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11497","kind":"arxiv","version":2},"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/2403.11497/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":"2403.11497","created_at":"2026-07-05T09:30:10.987200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11497v2","created_at":"2026-07-05T09:30:10.987200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11497","created_at":"2026-07-05T09:30:10.987200+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVH4VBR5RMJX","created_at":"2026-07-05T09:30:10.987200+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVH4VBR5RMJX223Z","created_at":"2026-07-05T09:30:10.987200+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVH4VBR5","created_at":"2026-07-05T09:30:10.987200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU","json":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU.json","graph_json":"https://pith.science/api/pith-number/QVH4VBR5RMJX223ZM3DMAQC6YU/graph.json","events_json":"https://pith.science/api/pith-number/QVH4VBR5RMJX223ZM3DMAQC6YU/events.json","paper":"https://pith.science/paper/QVH4VBR5"},"agent_actions":{"view_html":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU","download_json":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU.json","view_paper":"https://pith.science/paper/QVH4VBR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11497&json=true","fetch_graph":"https://pith.science/api/pith-number/QVH4VBR5RMJX223ZM3DMAQC6YU/graph.json","fetch_events":"https://pith.science/api/pith-number/QVH4VBR5RMJX223ZM3DMAQC6YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU/action/storage_attestation","attest_author":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU/action/author_attestation","sign_citation":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU/action/citation_signature","submit_replication":"https://pith.science/pith/QVH4VBR5RMJX223ZM3DMAQC6YU/action/replication_record"}},"created_at":"2026-07-05T09:30:10.987200+00:00","updated_at":"2026-07-05T09:30:10.987200+00:00"}