{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VVFTCPRPLNZKSMXRYMME3SEEST","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":"978d5fff34e6fce9323a57fc106436a8a4f8d4927401f9bec889915fa6d2665b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T17:47:52Z","title_canon_sha256":"d4a18d0a9b0c790d39536b431782584961b1e46720a2fd34d0ae92eb3893ce54"},"schema_version":"1.0","source":{"id":"2307.03166","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03166","created_at":"2026-07-05T09:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03166v3","created_at":"2026-07-05T09:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03166","created_at":"2026-07-05T09:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"VVFTCPRPLNZK","created_at":"2026-07-05T09:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"VVFTCPRPLNZKSMXR","created_at":"2026-07-05T09:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"VVFTCPRP","created_at":"2026-07-05T09:25:31Z"}],"graph_snapshots":[{"event_id":"sha256:adc96cd9f701bec2381c77403badd56f6f51c16c587e8546e075930213ae77b1","target":"graph","created_at":"2026-07-05T09:25:31Z","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/2307.03166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate the video understanding capabilities of existing foundation models (FMs) using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition,temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring an FM for downstream tasks. Furthermore, we jointly profile FMs' efficacy and efficiency when adapting to general video understanding tasks using cost measurements during both training and inference. Our main findings areas follows. First, task-specialized models signifi","authors_text":"Boqing Gong, Florian Schroff, Hao Zhou, Hartwig Adam, Huisheng Wang, Liangzhe Yuan, Long Zhao, Lu Jiang, Luke Friedman, Menglin Jia, Mikhail Sirotenko, Ming-Hsuan Yang, Nitesh Bharadwaj Gundavarapu, Ting Liu, Tobias Weyand, Xuan Yang, Yin Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T17:47:52Z","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03166","kind":"arxiv","version":3},"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":"sha256:0482861bd71ddee922c7d916d8be7ec4e5fc7be4ec04b896de92bcd1adc674d7","target":"record","created_at":"2026-07-05T09:25:31Z","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":"978d5fff34e6fce9323a57fc106436a8a4f8d4927401f9bec889915fa6d2665b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T17:47:52Z","title_canon_sha256":"d4a18d0a9b0c790d39536b431782584961b1e46720a2fd34d0ae92eb3893ce54"},"schema_version":"1.0","source":{"id":"2307.03166","kind":"arxiv","version":3}},"canonical_sha256":"ad4b313e2f5b72a932f1c3184dc88494ff5454997dbe38c978b4af79410818d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad4b313e2f5b72a932f1c3184dc88494ff5454997dbe38c978b4af79410818d3","first_computed_at":"2026-07-05T09:25:31.154867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:31.154867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M5V3Og8ARGO+OD6JNIeX9vcE+sWleiTSlNHyI5cLGmra3BDk9FaOa34fvjsJ++kL6AZ7ztDhqXGb/QyqyMs2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:31.155293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03166","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0482861bd71ddee922c7d916d8be7ec4e5fc7be4ec04b896de92bcd1adc674d7","sha256:adc96cd9f701bec2381c77403badd56f6f51c16c587e8546e075930213ae77b1"],"state_sha256":"41f3e35724bc900233e84591eb33e8c9da32a251bedd34e3e354da8a51e56850"}