{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V54T3C6Q6EDQ7FOW2CW7NSWQ4R","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":"b3eeeed8b94d664b10bfa2b2fffc19e9a344c36e81f6c027ca8e75557aecf7c0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T15:34:20Z","title_canon_sha256":"ce4f31aaf3beb655da43f16dc3b7d15b66f3a4f0e103c4e3e0fd02dcbc9304ad"},"schema_version":"1.0","source":{"id":"2305.07558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07558","created_at":"2026-07-05T06:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07558v1","created_at":"2026-07-05T06:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07558","created_at":"2026-07-05T06:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"V54T3C6Q6EDQ","created_at":"2026-07-05T06:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"V54T3C6Q6EDQ7FOW","created_at":"2026-07-05T06:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"V54T3C6Q","created_at":"2026-07-05T06:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:7d49508d9553f9a46a9896ff2a98674e04fe069f0933a4013b15d1ab6048b6de","target":"graph","created_at":"2026-07-05T06:09:37Z","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/2305.07558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack \"fine-grained\" understanding, such as the ability to recognise relationships, verbs, and numbers in images. This has resulted in an increased interest in the community to either develop new benchmarks or models for such capabilities. To better understand and quantify progress in this direction, we investigate four competitive V&L models on four fine-grained benchmarks. Through our analysis, we find that X-","authors_text":"Aida Nematzadeh, Aishwarya Agrawal, Emanuele Bugliarello, Laurent Sartran, Lisa Anne Hendricks","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T15:34:20Z","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07558","kind":"arxiv","version":1},"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":"sha256:5f4c2a6303e38feea6d5f114fa833950cbee4ab183e70657ed4fa327dfac7e2d","target":"record","created_at":"2026-07-05T06:09:37Z","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":"b3eeeed8b94d664b10bfa2b2fffc19e9a344c36e81f6c027ca8e75557aecf7c0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T15:34:20Z","title_canon_sha256":"ce4f31aaf3beb655da43f16dc3b7d15b66f3a4f0e103c4e3e0fd02dcbc9304ad"},"schema_version":"1.0","source":{"id":"2305.07558","kind":"arxiv","version":1}},"canonical_sha256":"af793d8bd0f1070f95d6d0adf6cad0e46978c955770498afad8b262b1f9bd8aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af793d8bd0f1070f95d6d0adf6cad0e46978c955770498afad8b262b1f9bd8aa","first_computed_at":"2026-07-05T06:09:37.696382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:37.696382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xlzXttUFsb8oDMwghP3uv50407L2MgNQFLW+gOHJqmuNOUTVzPZ52+Wwf/4JbuVK2EWQAdoNG/TIT4Ifv2UEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:37.696835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f4c2a6303e38feea6d5f114fa833950cbee4ab183e70657ed4fa327dfac7e2d","sha256:7d49508d9553f9a46a9896ff2a98674e04fe069f0933a4013b15d1ab6048b6de"],"state_sha256":"b77054db68ebeb00cdcb8b99693938d74ebc3099eee5f3a1db4a19adb61b4bae"}