{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EKOLYPL3XLWBPQNJ2H52NZKG2M","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":"a8130deda5d26ade485fb5c398f17684f10e64b0dce839e8c7321eeb0e9db264","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-22T21:27:12Z","title_canon_sha256":"1ec0fdae9480224b89ff31e9b575b33d82204429052833c73dab1186e2df6a32"},"schema_version":"1.0","source":{"id":"2212.12043","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12043","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12043v2","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12043","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"EKOLYPL3XLWB","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"EKOLYPL3XLWBPQNJ","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"EKOLYPL3","created_at":"2026-07-05T08:07:26Z"}],"graph_snapshots":[{"event_id":"sha256:33974b4ad55e39af60e454209a7f05529d0217e5e75e7bbbefe51c1aba810141","target":"graph","created_at":"2026-07-05T08:07:26Z","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/2212.12043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such performance does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). As a potential cause of the difficulty of applying these models to VQA and similar tasks, we report an interesting phenomenon of vision-language models, which we call the Concept Association Bias (CAB). We find that models with CAB tend to treat input as a bag of concepts and attempt to f","authors_text":"Ilker Yildirim, Yingtian Tang, Yoyo Zhang, Yutaro Yamada","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-22T21:27:12Z","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12043","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:b69205e34b17983919a4e761ca8c1e82e4cfd7611d82438d9eeaa3830a418e09","target":"record","created_at":"2026-07-05T08:07:26Z","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":"a8130deda5d26ade485fb5c398f17684f10e64b0dce839e8c7321eeb0e9db264","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-22T21:27:12Z","title_canon_sha256":"1ec0fdae9480224b89ff31e9b575b33d82204429052833c73dab1186e2df6a32"},"schema_version":"1.0","source":{"id":"2212.12043","kind":"arxiv","version":2}},"canonical_sha256":"229cbc3d7bbaec17c1a9d1fba6e546d3214d7fcda8e438cdc0917bfc8c74fc5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"229cbc3d7bbaec17c1a9d1fba6e546d3214d7fcda8e438cdc0917bfc8c74fc5c","first_computed_at":"2026-07-05T08:07:26.640109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:26.640109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KtZx2Jk3MkdDhJ080gZ4ccm4W8PjUlAK9u4Hphp0+ZGEdfLivJNsZpQpmJ73P3+6hXR55LiDes4dU1X2qz9uBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:26.640633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.12043","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b69205e34b17983919a4e761ca8c1e82e4cfd7611d82438d9eeaa3830a418e09","sha256:33974b4ad55e39af60e454209a7f05529d0217e5e75e7bbbefe51c1aba810141"],"state_sha256":"5e6e8b786280ebcdf26ef8aec87eff44d39924266ac25fabcec5d1e0188a9e56"}