{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3XTDQZNEWE4BLP7ZCJGIYR6AD","short_pith_number":"pith:B3XTDQZN","schema_version":"1.0","canonical_sha256":"0eef31c32d2589c0adffc89264623e00e57b103bcf16a1322fc513d24b06a710","source":{"kind":"arxiv","id":"2409.01389","version":2},"attestation_state":"computed","paper":{"title":"CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Ivana Be\\v{n}ov\\'a, Michal Gregor","submitted_at":"2024-09-02T17:39:26Z","abstract_excerpt":"How do vision-language (VL) transformer models ground verb phrases and do they integrate contextual and world knowledge in this process? We introduce the CV-Probes dataset, containing image-caption pairs involving verb phrases that require both social knowledge and visual context to interpret (e.g., \"beg\"), as well as pairs involving verb phrases that can be grounded based on information directly available in the image (e.g., \"sit\"). We show that VL models struggle to ground VPs that are strongly context-dependent. Further analysis using explainable AI techniques shows that such models may not"},"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":"2409.01389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T17:39:26Z","cross_cats_sorted":[],"title_canon_sha256":"e0b0974fb75d2e31b90271a2f376c30b70a8a80044874d64aa0b2236530309d3","abstract_canon_sha256":"6bfcf6d48f85b1545b7494d9c010bb99102b62f7b46523d5d95af556e0549640"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:21.790324Z","signature_b64":"99TqXd0a8P1jk6h4YbS7R7qMO/KkIGavyCC0aVLMbsXHl5IzFsavbz+CTyZ8kxXmokEAxxZDEBZP8lRNDaZDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eef31c32d2589c0adffc89264623e00e57b103bcf16a1322fc513d24b06a710","last_reissued_at":"2026-07-05T11:36:21.789672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:21.789672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Ivana Be\\v{n}ov\\'a, Michal Gregor","submitted_at":"2024-09-02T17:39:26Z","abstract_excerpt":"How do vision-language (VL) transformer models ground verb phrases and do they integrate contextual and world knowledge in this process? We introduce the CV-Probes dataset, containing image-caption pairs involving verb phrases that require both social knowledge and visual context to interpret (e.g., \"beg\"), as well as pairs involving verb phrases that can be grounded based on information directly available in the image (e.g., \"sit\"). We show that VL models struggle to ground VPs that are strongly context-dependent. Further analysis using explainable AI techniques shows that such models may not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01389","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/2409.01389/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":"2409.01389","created_at":"2026-07-05T11:36:21.789757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01389v2","created_at":"2026-07-05T11:36:21.789757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01389","created_at":"2026-07-05T11:36:21.789757+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3XTDQZNEWE4","created_at":"2026-07-05T11:36:21.789757+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3XTDQZNEWE4BLP7","created_at":"2026-07-05T11:36:21.789757+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3XTDQZN","created_at":"2026-07-05T11:36:21.789757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08227","citing_title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD","json":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD.json","graph_json":"https://pith.science/api/pith-number/B3XTDQZNEWE4BLP7ZCJGIYR6AD/graph.json","events_json":"https://pith.science/api/pith-number/B3XTDQZNEWE4BLP7ZCJGIYR6AD/events.json","paper":"https://pith.science/paper/B3XTDQZN"},"agent_actions":{"view_html":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD","download_json":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD.json","view_paper":"https://pith.science/paper/B3XTDQZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01389&json=true","fetch_graph":"https://pith.science/api/pith-number/B3XTDQZNEWE4BLP7ZCJGIYR6AD/graph.json","fetch_events":"https://pith.science/api/pith-number/B3XTDQZNEWE4BLP7ZCJGIYR6AD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD/action/storage_attestation","attest_author":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD/action/author_attestation","sign_citation":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD/action/citation_signature","submit_replication":"https://pith.science/pith/B3XTDQZNEWE4BLP7ZCJGIYR6AD/action/replication_record"}},"created_at":"2026-07-05T11:36:21.789757+00:00","updated_at":"2026-07-05T11:36:21.789757+00:00"}