{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HOLCV2DI7ZHFCVN2BDWG2WQOFK","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":"d78e8433603ab6164ff7bdc950e513ed35e351ab9369dc42197e439f7ee4677f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:57:01Z","title_canon_sha256":"b748684eee658421a2597ed86feeef2639fbfbd3cdf22c339e99ae6b863bf40e"},"schema_version":"1.0","source":{"id":"2304.06708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06708","created_at":"2026-07-05T06:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06708v1","created_at":"2026-07-05T06:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06708","created_at":"2026-07-05T06:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"HOLCV2DI7ZHF","created_at":"2026-07-05T06:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"HOLCV2DI7ZHFCVN2","created_at":"2026-07-05T06:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"HOLCV2DI","created_at":"2026-07-05T06:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:542fb5473e01263a1f6c3534f098ad56ace4a07939c1402376d3ff57e3d01629","target":"graph","created_at":"2026-07-05T06:00:52Z","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/2304.06708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrew Zisserman, Arsha Nagrani, Cordelia Schmid, Liliane Momeni, Mathilde Caron","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:57:01Z","title":"Verbs in Action: Improving verb understanding in video-language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06708","kind":"arxiv","version":1},"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":"sha256:1961bbd3148b030b60fd9f61baa5e14c33304abb08f94d3d376614b28f40005c","target":"record","created_at":"2026-07-05T06:00:52Z","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":"d78e8433603ab6164ff7bdc950e513ed35e351ab9369dc42197e439f7ee4677f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:57:01Z","title_canon_sha256":"b748684eee658421a2597ed86feeef2639fbfbd3cdf22c339e99ae6b863bf40e"},"schema_version":"1.0","source":{"id":"2304.06708","kind":"arxiv","version":1}},"canonical_sha256":"3b962ae868fe4e5155ba08ec6d5a0e2a92f3fe7bbe1891f528f74bb1116d73cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b962ae868fe4e5155ba08ec6d5a0e2a92f3fe7bbe1891f528f74bb1116d73cf","first_computed_at":"2026-07-05T06:00:52.918681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:52.918681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uxXGfCxVIQWsZQaYNpknyF8NlDOxJ3w0GzIkLIPevPcKSP52OIwawMIKbxg5cQ+3meMf5tqbJyOvXr1CX09lDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:52.919098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1961bbd3148b030b60fd9f61baa5e14c33304abb08f94d3d376614b28f40005c","sha256:542fb5473e01263a1f6c3534f098ad56ace4a07939c1402376d3ff57e3d01629"],"state_sha256":"d034e673144d0afaedd0a6935ea4f1f2a109963b32c808b9cb940ea7b7b66f87"}