{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YI3DPXPKUTNTQLU7STMOI2PYQO","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":"88cee4681dc4373427406a2a3a2c412cc517c18e70de884ef3ca8928e37181f7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T05:00:18Z","title_canon_sha256":"3f4748725d1bd37ff8fe4ce5f5e70d6f3412d5ebaf6886d41158ec37ff825099"},"schema_version":"1.0","source":{"id":"2212.00281","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00281","created_at":"2026-07-05T07:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00281v2","created_at":"2026-07-05T07:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00281","created_at":"2026-07-05T07:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"YI3DPXPKUTNT","created_at":"2026-07-05T07:38:49Z"},{"alias_kind":"pith_short_16","alias_value":"YI3DPXPKUTNTQLU7","created_at":"2026-07-05T07:38:49Z"},{"alias_kind":"pith_short_8","alias_value":"YI3DPXPK","created_at":"2026-07-05T07:38:49Z"}],"graph_snapshots":[{"event_id":"sha256:0279eddcf140029452c7bf0d76c7427ae60b9777ddc0fda1e328ad45121a74c9","target":"graph","created_at":"2026-07-05T07:38:49Z","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/2212.00281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether this joint learning paradigm can help understand each individual modality. In this work, we conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models by probing a broad range of tasks, aiming to assess the quality of the learned representations in a nuanced manner. Interestingly, our empirical observations suggest that vision-and-language models are better at label prediction tasks like object and attribute prediction,","authors_text":"Alan Yuille, Benjamin Van Durme, Cihang Xie, Zhuowan Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T05:00:18Z","title":"Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00281","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:baf06da0bc8cc6c175e4dbd3934c26121ddbb6d1267cab7e4864354c3a8d6cf8","target":"record","created_at":"2026-07-05T07:38:49Z","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":"88cee4681dc4373427406a2a3a2c412cc517c18e70de884ef3ca8928e37181f7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T05:00:18Z","title_canon_sha256":"3f4748725d1bd37ff8fe4ce5f5e70d6f3412d5ebaf6886d41158ec37ff825099"},"schema_version":"1.0","source":{"id":"2212.00281","kind":"arxiv","version":2}},"canonical_sha256":"c23637ddeaa4db382e9f94d8e469f883ab292666b6d744733b19e733202c97a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c23637ddeaa4db382e9f94d8e469f883ab292666b6d744733b19e733202c97a3","first_computed_at":"2026-07-05T07:38:49.853901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:49.853901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lhGPJJk+Nf1KnEYnx2uCmm9zrqrW0UcXkJ6mhQii00c3Y6nghy0KRonOC4jtyOPJDbzOHzMMHYhGB97g4gwcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:49.854382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00281","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baf06da0bc8cc6c175e4dbd3934c26121ddbb6d1267cab7e4864354c3a8d6cf8","sha256:0279eddcf140029452c7bf0d76c7427ae60b9777ddc0fda1e328ad45121a74c9"],"state_sha256":"c139c664ff3b69cc816daf0fe640286b30701e04df8f145ebe96b83abe743de9"}