{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GAJLVPIM4IS67KUL7XFAGUJFUA","short_pith_number":"pith:GAJLVPIM","schema_version":"1.0","canonical_sha256":"3012babd0ce225efaa8bfdca035125a0153d01c0962dd1ecf28660d456e34a8a","source":{"kind":"arxiv","id":"2112.07566","version":2},"attestation_state":"computed","paper":{"title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Anette Frank, Iacer Calixto, Letitia Parcalabescu, Lilitta Muradjan, Michele Cafagna","submitted_at":"2021-12-14T17:15:04Z","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"},"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":"2112.07566","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:15:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"12f51d2b8b8bd35ff6755fa69592a4e74424db1b24a36af52f0325f55bb54d46","abstract_canon_sha256":"b9f18c8b4dba47538574c3fba9e03f7d9f9937a0074a0afab306e067c763a4f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:28.901536Z","signature_b64":"xamkrql0KdUCKv6sJ5COYhUXE+Maz+LAwMp6lMKsXYh86EgNu9ME6YFU/NzB02RWwYgJxI2Lq2Uc7fOzOnGhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3012babd0ce225efaa8bfdca035125a0153d01c0962dd1ecf28660d456e34a8a","last_reissued_at":"2026-07-05T07:43:28.901056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:28.901056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Anette Frank, Iacer Calixto, Letitia Parcalabescu, Lilitta Muradjan, Michele Cafagna","submitted_at":"2021-12-14T17:15:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07566","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/2112.07566/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":"2112.07566","created_at":"2026-07-05T07:43:28.901125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07566v2","created_at":"2026-07-05T07:43:28.901125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07566","created_at":"2026-07-05T07:43:28.901125+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAJLVPIM4IS6","created_at":"2026-07-05T07:43:28.901125+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAJLVPIM4IS67KUL","created_at":"2026-07-05T07:43:28.901125+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAJLVPIM","created_at":"2026-07-05T07:43:28.901125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13288","citing_title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23137","citing_title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA","json":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA.json","graph_json":"https://pith.science/api/pith-number/GAJLVPIM4IS67KUL7XFAGUJFUA/graph.json","events_json":"https://pith.science/api/pith-number/GAJLVPIM4IS67KUL7XFAGUJFUA/events.json","paper":"https://pith.science/paper/GAJLVPIM"},"agent_actions":{"view_html":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA","download_json":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA.json","view_paper":"https://pith.science/paper/GAJLVPIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07566&json=true","fetch_graph":"https://pith.science/api/pith-number/GAJLVPIM4IS67KUL7XFAGUJFUA/graph.json","fetch_events":"https://pith.science/api/pith-number/GAJLVPIM4IS67KUL7XFAGUJFUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA/action/storage_attestation","attest_author":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA/action/author_attestation","sign_citation":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA/action/citation_signature","submit_replication":"https://pith.science/pith/GAJLVPIM4IS67KUL7XFAGUJFUA/action/replication_record"}},"created_at":"2026-07-05T07:43:28.901125+00:00","updated_at":"2026-07-05T07:43:28.901125+00:00"}