{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GAJLVPIM4IS67KUL7XFAGUJFUA","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":"b9f18c8b4dba47538574c3fba9e03f7d9f9937a0074a0afab306e067c763a4f9","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:15:04Z","title_canon_sha256":"12f51d2b8b8bd35ff6755fa69592a4e74424db1b24a36af52f0325f55bb54d46"},"schema_version":"1.0","source":{"id":"2112.07566","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07566","created_at":"2026-07-05T07:43:28Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07566v2","created_at":"2026-07-05T07:43:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07566","created_at":"2026-07-05T07:43:28Z"},{"alias_kind":"pith_short_12","alias_value":"GAJLVPIM4IS6","created_at":"2026-07-05T07:43:28Z"},{"alias_kind":"pith_short_16","alias_value":"GAJLVPIM4IS67KUL","created_at":"2026-07-05T07:43:28Z"},{"alias_kind":"pith_short_8","alias_value":"GAJLVPIM","created_at":"2026-07-05T07:43:28Z"}],"graph_snapshots":[{"event_id":"sha256:d9758b4191bff219adf45a2f87841d18d42223571597a64d098aea03b3ed97db","target":"graph","created_at":"2026-07-05T07:43:28Z","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/2112.07566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena. VALSE offers a suite of six tests covering various linguistic constructs. Solving these requires models to ground linguistic phenomena in the visual modality, allowing more fine-grained evaluations than hitherto possible. We build VALSE using methods that support the construction of valid foils, and report results from evaluating five widely-used V&L mo","authors_text":"Albert Gatt, Anette Frank, Iacer Calixto, Letitia Parcalabescu, Lilitta Muradjan, Michele Cafagna","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:15:04Z","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07566","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:e26c154139af5ef5dd6fac5a6d5a9d144a97b8f1f6d6e3247d5678f5ac2e31c2","target":"record","created_at":"2026-07-05T07:43:28Z","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":"b9f18c8b4dba47538574c3fba9e03f7d9f9937a0074a0afab306e067c763a4f9","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:15:04Z","title_canon_sha256":"12f51d2b8b8bd35ff6755fa69592a4e74424db1b24a36af52f0325f55bb54d46"},"schema_version":"1.0","source":{"id":"2112.07566","kind":"arxiv","version":2}},"canonical_sha256":"3012babd0ce225efaa8bfdca035125a0153d01c0962dd1ecf28660d456e34a8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3012babd0ce225efaa8bfdca035125a0153d01c0962dd1ecf28660d456e34a8a","first_computed_at":"2026-07-05T07:43:28.901056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:28.901056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xamkrql0KdUCKv6sJ5COYhUXE+Maz+LAwMp6lMKsXYh86EgNu9ME6YFU/NzB02RWwYgJxI2Lq2Uc7fOzOnGhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:28.901536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07566","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e26c154139af5ef5dd6fac5a6d5a9d144a97b8f1f6d6e3247d5678f5ac2e31c2","sha256:d9758b4191bff219adf45a2f87841d18d42223571597a64d098aea03b3ed97db"],"state_sha256":"5e62d4502c58a749d623cb978778bc59c446be40fd989499dd9f6fa2244c86b2"}