{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQFYCV3CWUNRQWB6JZL635TN3O","short_pith_number":"pith:CQFYCV3C","schema_version":"1.0","canonical_sha256":"140b815762b51b18583e4e57edf66ddb9d74a056536665160bff5694ab496e4f","source":{"kind":"arxiv","id":"2402.04492","version":2},"attestation_state":"computed","paper":{"title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Agam Bhatia, Ishan Gaur, Jirayu Burapacheep, Tristan Thrush","submitted_at":"2024-02-07T00:31:49Z","abstract_excerpt":"This paper introduces the ColorSwap dataset, designed to assess and improve the proficiency of multimodal models in matching objects with their colors. The dataset is comprised of 2,000 unique image-caption pairs, grouped into 1,000 examples. Each example includes a caption-image pair, along with a ``color-swapped'' pair. We follow the Winoground schema: the two captions in an example have the same words, but the color words have been rearranged to modify different objects. The dataset was created through a novel blend of automated caption and image generation with humans in the loop. We evalu"},"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":"2402.04492","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T00:31:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7c8c270ce8c380e03592a771582e4c732b059f5947f7f01277d7d18c284abdda","abstract_canon_sha256":"206cc933bebce48892225a125ee841abb0ea7885524c801324c1fe5154d746c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:29.043184Z","signature_b64":"S/FcWXjYu55imAjoB5aFPnAHl8vFTElDx69KIk8gSLgYY9/PS7Mjar5zIunOp2Dg6JNiM3uKEGDM3ttKw32JDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"140b815762b51b18583e4e57edf66ddb9d74a056536665160bff5694ab496e4f","last_reissued_at":"2026-07-05T08:52:29.042772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:29.042772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Agam Bhatia, Ishan Gaur, Jirayu Burapacheep, Tristan Thrush","submitted_at":"2024-02-07T00:31:49Z","abstract_excerpt":"This paper introduces the ColorSwap dataset, designed to assess and improve the proficiency of multimodal models in matching objects with their colors. The dataset is comprised of 2,000 unique image-caption pairs, grouped into 1,000 examples. Each example includes a caption-image pair, along with a ``color-swapped'' pair. We follow the Winoground schema: the two captions in an example have the same words, but the color words have been rearranged to modify different objects. The dataset was created through a novel blend of automated caption and image generation with humans in the loop. We evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04492","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/2402.04492/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":"2402.04492","created_at":"2026-07-05T08:52:29.042829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04492v2","created_at":"2026-07-05T08:52:29.042829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04492","created_at":"2026-07-05T08:52:29.042829+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQFYCV3CWUNR","created_at":"2026-07-05T08:52:29.042829+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQFYCV3CWUNRQWB6","created_at":"2026-07-05T08:52:29.042829+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQFYCV3C","created_at":"2026-07-05T08:52:29.042829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.03247","citing_title":"Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07632","citing_title":"Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O","json":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O.json","graph_json":"https://pith.science/api/pith-number/CQFYCV3CWUNRQWB6JZL635TN3O/graph.json","events_json":"https://pith.science/api/pith-number/CQFYCV3CWUNRQWB6JZL635TN3O/events.json","paper":"https://pith.science/paper/CQFYCV3C"},"agent_actions":{"view_html":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O","download_json":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O.json","view_paper":"https://pith.science/paper/CQFYCV3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04492&json=true","fetch_graph":"https://pith.science/api/pith-number/CQFYCV3CWUNRQWB6JZL635TN3O/graph.json","fetch_events":"https://pith.science/api/pith-number/CQFYCV3CWUNRQWB6JZL635TN3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O/action/storage_attestation","attest_author":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O/action/author_attestation","sign_citation":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O/action/citation_signature","submit_replication":"https://pith.science/pith/CQFYCV3CWUNRQWB6JZL635TN3O/action/replication_record"}},"created_at":"2026-07-05T08:52:29.042829+00:00","updated_at":"2026-07-05T08:52:29.042829+00:00"}