{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HOLCV2DI7ZHFCVN2BDWG2WQOFK","short_pith_number":"pith:HOLCV2DI","schema_version":"1.0","canonical_sha256":"3b962ae868fe4e5155ba08ec6d5a0e2a92f3fe7bbe1891f528f74bb1116d73cf","source":{"kind":"arxiv","id":"2304.06708","version":1},"attestation_state":"computed","paper":{"title":"Verbs in Action: Improving verb understanding in video-language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Cordelia Schmid, Liliane Momeni, Mathilde Caron","submitted_at":"2023-04-13T17:57:01Z","abstract_excerpt":"Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently, state-of-the-art video-language models based on CLIP have been shown to have limited verb understanding and to rely extensively on nouns, restricting their performance in real-world video applications that require action and temporal understanding. In this work, we improve verb understanding for CLIP-based video-language models by proposing a new Verb-Focused Contrastive (VFC) framework. This consists of two main components: (1) leveraging pretrained"},"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":"2304.06708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:57:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b748684eee658421a2597ed86feeef2639fbfbd3cdf22c339e99ae6b863bf40e","abstract_canon_sha256":"d78e8433603ab6164ff7bdc950e513ed35e351ab9369dc42197e439f7ee4677f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:52.919098Z","signature_b64":"uxXGfCxVIQWsZQaYNpknyF8NlDOxJ3w0GzIkLIPevPcKSP52OIwawMIKbxg5cQ+3meMf5tqbJyOvXr1CX09lDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b962ae868fe4e5155ba08ec6d5a0e2a92f3fe7bbe1891f528f74bb1116d73cf","last_reissued_at":"2026-07-05T06:00:52.918681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:52.918681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verbs in Action: Improving verb understanding in video-language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Cordelia Schmid, Liliane Momeni, Mathilde Caron","submitted_at":"2023-04-13T17:57:01Z","abstract_excerpt":"Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently, state-of-the-art video-language models based on CLIP have been shown to have limited verb understanding and to rely extensively on nouns, restricting their performance in real-world video applications that require action and temporal understanding. In this work, we improve verb understanding for CLIP-based video-language models by proposing a new Verb-Focused Contrastive (VFC) framework. This consists of two main components: (1) leveraging pretrained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06708","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/2304.06708/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":"2304.06708","created_at":"2026-07-05T06:00:52.918736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06708v1","created_at":"2026-07-05T06:00:52.918736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06708","created_at":"2026-07-05T06:00:52.918736+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOLCV2DI7ZHF","created_at":"2026-07-05T06:00:52.918736+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOLCV2DI7ZHFCVN2","created_at":"2026-07-05T06:00:52.918736+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOLCV2DI","created_at":"2026-07-05T06:00:52.918736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09353","citing_title":"Causal Graphical Models for Vision-Language Compositional Understanding","ref_index":1993,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK","json":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK.json","graph_json":"https://pith.science/api/pith-number/HOLCV2DI7ZHFCVN2BDWG2WQOFK/graph.json","events_json":"https://pith.science/api/pith-number/HOLCV2DI7ZHFCVN2BDWG2WQOFK/events.json","paper":"https://pith.science/paper/HOLCV2DI"},"agent_actions":{"view_html":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK","download_json":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK.json","view_paper":"https://pith.science/paper/HOLCV2DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06708&json=true","fetch_graph":"https://pith.science/api/pith-number/HOLCV2DI7ZHFCVN2BDWG2WQOFK/graph.json","fetch_events":"https://pith.science/api/pith-number/HOLCV2DI7ZHFCVN2BDWG2WQOFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK/action/storage_attestation","attest_author":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK/action/author_attestation","sign_citation":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK/action/citation_signature","submit_replication":"https://pith.science/pith/HOLCV2DI7ZHFCVN2BDWG2WQOFK/action/replication_record"}},"created_at":"2026-07-05T06:00:52.918736+00:00","updated_at":"2026-07-05T06:00:52.918736+00:00"}