{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PHWKHEPUV5XPAIBVYXYWHKFUIU","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":"487da93d568507dee649697e3a85aae51c5c362f4bafbac388b5e3cbb3bd5da1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T01:55:48Z","title_canon_sha256":"76010f72c5bfa69d04122857dac4b97524734299dbb8748725948307cbcbf869"},"schema_version":"1.0","source":{"id":"2407.13094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13094","created_at":"2026-07-05T08:45:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13094v1","created_at":"2026-07-05T08:45:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13094","created_at":"2026-07-05T08:45:33Z"},{"alias_kind":"pith_short_12","alias_value":"PHWKHEPUV5XP","created_at":"2026-07-05T08:45:33Z"},{"alias_kind":"pith_short_16","alias_value":"PHWKHEPUV5XPAIBV","created_at":"2026-07-05T08:45:33Z"},{"alias_kind":"pith_short_8","alias_value":"PHWKHEPU","created_at":"2026-07-05T08:45:33Z"}],"graph_snapshots":[{"event_id":"sha256:fadafaec19e926393ca4901fd12026a501983653f8266514436f1d15e828125e","target":"graph","created_at":"2026-07-05T08:45:33Z","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/2407.13094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video-text foundation models have demonstrated strong performance on a wide variety of downstream video understanding tasks. Can these video-text models genuinely understand the contents of natural videos? Standard video-text evaluations could be misleading as many questions can be inferred merely from the objects and contexts in a single frame or biases inherent in the datasets. In this paper, we aim to better assess the capabilities of current video-text models and understand their limitations. We propose a novel evaluation task for video-text understanding, namely retrieval from coun","authors_text":"Alan Yuille, Christian H\\\"ane, Huiyu Wang, Kai Li, Moustafa Meshry, Qihao Liu, Wufei Ma, Zhongshi Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T01:55:48Z","title":"Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13094","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":"sha256:943c3108d71e5cf80faa889e9c718f4be3dbbcf9d6116cf8a65eae09fd9f1f1e","target":"record","created_at":"2026-07-05T08:45:33Z","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":"487da93d568507dee649697e3a85aae51c5c362f4bafbac388b5e3cbb3bd5da1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T01:55:48Z","title_canon_sha256":"76010f72c5bfa69d04122857dac4b97524734299dbb8748725948307cbcbf869"},"schema_version":"1.0","source":{"id":"2407.13094","kind":"arxiv","version":1}},"canonical_sha256":"79eca391f4af6ef02035c5f163a8b44538c236916e72b2a8f47adfa305d6c141","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79eca391f4af6ef02035c5f163a8b44538c236916e72b2a8f47adfa305d6c141","first_computed_at":"2026-07-05T08:45:33.420497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:33.420497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1kLXW7Fm8iBroJF0EpFaFJaUzkOp+2uflpTOb1px+LqJTG5KrTwAJWs3YQJfBeGmXo2i/DIXyD1o2724GO01Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:33.420971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13094","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:943c3108d71e5cf80faa889e9c718f4be3dbbcf9d6116cf8a65eae09fd9f1f1e","sha256:fadafaec19e926393ca4901fd12026a501983653f8266514436f1d15e828125e"],"state_sha256":"a80377554b81484b07e34dad56f80496c97ca4062bb28b1ad2986cadc7b6d2b9"}