{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PHWKHEPUV5XPAIBVYXYWHKFUIU","short_pith_number":"pith:PHWKHEPU","schema_version":"1.0","canonical_sha256":"79eca391f4af6ef02035c5f163a8b44538c236916e72b2a8f47adfa305d6c141","source":{"kind":"arxiv","id":"2407.13094","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Christian H\\\"ane, Huiyu Wang, Kai Li, Moustafa Meshry, Qihao Liu, Wufei Ma, Zhongshi Jiang","submitted_at":"2024-07-18T01:55:48Z","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"},"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":"2407.13094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T01:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"76010f72c5bfa69d04122857dac4b97524734299dbb8748725948307cbcbf869","abstract_canon_sha256":"487da93d568507dee649697e3a85aae51c5c362f4bafbac388b5e3cbb3bd5da1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:33.420971Z","signature_b64":"1kLXW7Fm8iBroJF0EpFaFJaUzkOp+2uflpTOb1px+LqJTG5KrTwAJWs3YQJfBeGmXo2i/DIXyD1o2724GO01Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79eca391f4af6ef02035c5f163a8b44538c236916e72b2a8f47adfa305d6c141","last_reissued_at":"2026-07-05T08:45:33.420497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:33.420497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Christian H\\\"ane, Huiyu Wang, Kai Li, Moustafa Meshry, Qihao Liu, Wufei Ma, Zhongshi Jiang","submitted_at":"2024-07-18T01:55:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13094","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/2407.13094/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":"2407.13094","created_at":"2026-07-05T08:45:33.420556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13094v1","created_at":"2026-07-05T08:45:33.420556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13094","created_at":"2026-07-05T08:45:33.420556+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHWKHEPUV5XP","created_at":"2026-07-05T08:45:33.420556+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHWKHEPUV5XPAIBV","created_at":"2026-07-05T08:45:33.420556+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHWKHEPU","created_at":"2026-07-05T08:45:33.420556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU","json":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU.json","graph_json":"https://pith.science/api/pith-number/PHWKHEPUV5XPAIBVYXYWHKFUIU/graph.json","events_json":"https://pith.science/api/pith-number/PHWKHEPUV5XPAIBVYXYWHKFUIU/events.json","paper":"https://pith.science/paper/PHWKHEPU"},"agent_actions":{"view_html":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU","download_json":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU.json","view_paper":"https://pith.science/paper/PHWKHEPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13094&json=true","fetch_graph":"https://pith.science/api/pith-number/PHWKHEPUV5XPAIBVYXYWHKFUIU/graph.json","fetch_events":"https://pith.science/api/pith-number/PHWKHEPUV5XPAIBVYXYWHKFUIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU/action/storage_attestation","attest_author":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU/action/author_attestation","sign_citation":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU/action/citation_signature","submit_replication":"https://pith.science/pith/PHWKHEPUV5XPAIBVYXYWHKFUIU/action/replication_record"}},"created_at":"2026-07-05T08:45:33.420556+00:00","updated_at":"2026-07-05T08:45:33.420556+00:00"}