{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GPBZCCIC4IFYKAT5A7BZL5V2S4","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":"eff613e5333b306ca6d38080360731eff95d4c11351d6b004f99a2737d286440","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T02:13:13Z","title_canon_sha256":"1b7bc6719611a30ce37f9a94c22e85ac8cdaff303cda705f88ced4de363bbb01"},"schema_version":"1.0","source":{"id":"2311.07022","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07022","created_at":"2026-07-05T07:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07022v1","created_at":"2026-07-05T07:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07022","created_at":"2026-07-05T07:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"GPBZCCIC4IFY","created_at":"2026-07-05T07:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"GPBZCCIC4IFYKAT5","created_at":"2026-07-05T07:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"GPBZCCIC","created_at":"2026-07-05T07:12:07Z"}],"graph_snapshots":[{"event_id":"sha256:e447a637f045eaed0b38702e22f66fbc73e9cbec2ac36c0c466b8d44ead8e100","target":"graph","created_at":"2026-07-05T07:12:07Z","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/2311.07022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we present ViLMA (Video Language Model Assessment), a task-agnostic benchmark that places the assessment of fine-grained capabilities of these models on a firm footing. Task-based evaluations, while valuable, fail to capture the complexities and specific temporal aspects of moving images that VidLMs need to process. Through carefully curated counterfactuals, Vi","authors_text":"Albert Gatt, Andrea Pedrotti, Anette Frank, Aykut Erdem, Emre Can Acikgoz, Erkut Erdem, Iacer Calixto, Ilker Kesen, Letitia Parcalabescu, Michele Cafagna, Mustafa Dogan","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T02:13:13Z","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07022","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":"sha256:28b5ba2448b1fe97ecfd3a780c1deeff92c786033e3a90042620b86a9eb79584","target":"record","created_at":"2026-07-05T07:12:07Z","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":"eff613e5333b306ca6d38080360731eff95d4c11351d6b004f99a2737d286440","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T02:13:13Z","title_canon_sha256":"1b7bc6719611a30ce37f9a94c22e85ac8cdaff303cda705f88ced4de363bbb01"},"schema_version":"1.0","source":{"id":"2311.07022","kind":"arxiv","version":1}},"canonical_sha256":"33c3910902e20b85027d07c395f6ba9706d236f106d39898b44f8ffe834d6168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33c3910902e20b85027d07c395f6ba9706d236f106d39898b44f8ffe834d6168","first_computed_at":"2026-07-05T07:12:07.032059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:07.032059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"299SJAC0VQsD/juk4TawD1z/uz43OV0xyfRVUo0k7y0+IFH+KTRrnuI3B0ssRMuaI73QCxOczcxAQkd+0maBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:07.032484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07022","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28b5ba2448b1fe97ecfd3a780c1deeff92c786033e3a90042620b86a9eb79584","sha256:e447a637f045eaed0b38702e22f66fbc73e9cbec2ac36c0c466b8d44ead8e100"],"state_sha256":"f81685f2b5ea4cf09f1e0ec10664bee5b2989afbfd0612c2a53344af1daa4803"}