{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q4SSTJJK3U2VUK3XE6CESRKTFN","short_pith_number":"pith:Q4SSTJJK","schema_version":"1.0","canonical_sha256":"872529a52add355a2b7727844945532b46ffce3314951a2c648456eb54bdac2c","source":{"kind":"arxiv","id":"2106.09141","version":1},"attestation_state":"computed","paper":{"title":"Probing Image-Language Transformers for Verb Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aida Nematzadeh, Lisa Anne Hendricks","submitted_at":"2021-06-16T21:36:36Z","abstract_excerpt":"Multimodal image-language transformers have achieved impressive results on a variety of tasks that rely on fine-tuning (e.g., visual question answering and image retrieval). We are interested in shedding light on the quality of their pretrained representations -- in particular, if these models can distinguish different types of verbs or if they rely solely on nouns in a given sentence. To do so, we collect a dataset of image-sentence pairs (in English) consisting of 421 verbs that are either visual or commonly found in the pretraining data (i.e., the Conceptual Captions dataset). We use this d"},"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":"2106.09141","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-16T21:36:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4207546557f7e65bb498b512d063eb52ea57f9f27c0ee0ea704e60c8605dc062","abstract_canon_sha256":"d77c18186fcbf7b0db69d55f84e85ca3d2f2b63bba08751dada36f7c58590ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:12.769538Z","signature_b64":"ekykj5U6gFo19vKz1yBCf1++Px2//M7XUz+vab+tWYSfj3f5c00zBW8/43vxoi5atRCn6tBGOp/NSeRm8IMqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872529a52add355a2b7727844945532b46ffce3314951a2c648456eb54bdac2c","last_reissued_at":"2026-07-05T02:50:12.769122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:12.769122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Image-Language Transformers for Verb Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aida Nematzadeh, Lisa Anne Hendricks","submitted_at":"2021-06-16T21:36:36Z","abstract_excerpt":"Multimodal image-language transformers have achieved impressive results on a variety of tasks that rely on fine-tuning (e.g., visual question answering and image retrieval). We are interested in shedding light on the quality of their pretrained representations -- in particular, if these models can distinguish different types of verbs or if they rely solely on nouns in a given sentence. To do so, we collect a dataset of image-sentence pairs (in English) consisting of 421 verbs that are either visual or commonly found in the pretraining data (i.e., the Conceptual Captions dataset). We use this d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09141","kind":"arxiv","version":1},"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/2106.09141/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":"2106.09141","created_at":"2026-07-05T02:50:12.769180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09141v1","created_at":"2026-07-05T02:50:12.769180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09141","created_at":"2026-07-05T02:50:12.769180+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4SSTJJK3U2V","created_at":"2026-07-05T02:50:12.769180+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4SSTJJK3U2VUK3X","created_at":"2026-07-05T02:50:12.769180+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4SSTJJK","created_at":"2026-07-05T02:50:12.769180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.14837","citing_title":"V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06157","citing_title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN","json":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN.json","graph_json":"https://pith.science/api/pith-number/Q4SSTJJK3U2VUK3XE6CESRKTFN/graph.json","events_json":"https://pith.science/api/pith-number/Q4SSTJJK3U2VUK3XE6CESRKTFN/events.json","paper":"https://pith.science/paper/Q4SSTJJK"},"agent_actions":{"view_html":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN","download_json":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN.json","view_paper":"https://pith.science/paper/Q4SSTJJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09141&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4SSTJJK3U2VUK3XE6CESRKTFN/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4SSTJJK3U2VUK3XE6CESRKTFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN/action/storage_attestation","attest_author":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN/action/author_attestation","sign_citation":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN/action/citation_signature","submit_replication":"https://pith.science/pith/Q4SSTJJK3U2VUK3XE6CESRKTFN/action/replication_record"}},"created_at":"2026-07-05T02:50:12.769180+00:00","updated_at":"2026-07-05T02:50:12.769180+00:00"}