{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQFYCV3CWUNRQWB6JZL635TN3O","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":"206cc933bebce48892225a125ee841abb0ea7885524c801324c1fe5154d746c8","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T00:31:49Z","title_canon_sha256":"7c8c270ce8c380e03592a771582e4c732b059f5947f7f01277d7d18c284abdda"},"schema_version":"1.0","source":{"id":"2402.04492","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04492","created_at":"2026-07-05T08:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04492v2","created_at":"2026-07-05T08:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04492","created_at":"2026-07-05T08:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"CQFYCV3CWUNR","created_at":"2026-07-05T08:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"CQFYCV3CWUNRQWB6","created_at":"2026-07-05T08:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"CQFYCV3C","created_at":"2026-07-05T08:52:29Z"}],"graph_snapshots":[{"event_id":"sha256:395e9906125d27925983b41692000df3998c6a3430b94f7c10934b260170e893","target":"graph","created_at":"2026-07-05T08:52:29Z","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/2402.04492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Agam Bhatia, Ishan Gaur, Jirayu Burapacheep, Tristan Thrush","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T00:31:49Z","title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04492","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":"sha256:33bad113e05c7097e75431fd1d72830c99eddc50f69e7b09b0cb651bac62df4c","target":"record","created_at":"2026-07-05T08:52:29Z","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":"206cc933bebce48892225a125ee841abb0ea7885524c801324c1fe5154d746c8","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T00:31:49Z","title_canon_sha256":"7c8c270ce8c380e03592a771582e4c732b059f5947f7f01277d7d18c284abdda"},"schema_version":"1.0","source":{"id":"2402.04492","kind":"arxiv","version":2}},"canonical_sha256":"140b815762b51b18583e4e57edf66ddb9d74a056536665160bff5694ab496e4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"140b815762b51b18583e4e57edf66ddb9d74a056536665160bff5694ab496e4f","first_computed_at":"2026-07-05T08:52:29.042772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:29.042772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S/FcWXjYu55imAjoB5aFPnAHl8vFTElDx69KIk8gSLgYY9/PS7Mjar5zIunOp2Dg6JNiM3uKEGDM3ttKw32JDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:29.043184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04492","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33bad113e05c7097e75431fd1d72830c99eddc50f69e7b09b0cb651bac62df4c","sha256:395e9906125d27925983b41692000df3998c6a3430b94f7c10934b260170e893"],"state_sha256":"7ccbbf1c1bfa45590210daad0634de6c7ec9aa70e380fd5620cca11f84129866"}