{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UWKSCVD7IXQJDHOE2D7OUHJOQA","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":"2a854de5730b6eb5f7c2393a3e99392490f6884b8ad71b8d45c62058c7f6f9a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T11:47:09Z","title_canon_sha256":"10fa7c28762f8ed2eec563d9763428cd75d2024a086e87f891f9c5a26b1ada6d"},"schema_version":"1.0","source":{"id":"2112.00431","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00431","created_at":"2026-07-05T04:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00431v2","created_at":"2026-07-05T04:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00431","created_at":"2026-07-05T04:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"UWKSCVD7IXQJ","created_at":"2026-07-05T04:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"UWKSCVD7IXQJDHOE","created_at":"2026-07-05T04:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"UWKSCVD7","created_at":"2026-07-05T04:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:11cc74b5c7c60eb604a32ecafadcd5a9090dca9b0e84c898a603f778e89975d0","target":"graph","created_at":"2026-07-05T04:09:00Z","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/2112.00431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparison, limited effort has been made at assessing the fitness of these datasets for the video-language grounding task. Recent works have begun to discover significant limitations in these datasets, suggesting that state-of-the-art techniques commonly overfit to hidden dataset biases. In this work, we present MAD (Movie Audio Descriptions), a novel benchmark that departs from the paradigm of augmenting existing video data","authors_text":"Alejandro Pardo, Bernard Ghanem, Chen Zhao, Fabian Caba Heilbron, Juan Le\\'on Alc\\'azar, Mattia Soldan, Silvio Giancola","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T11:47:09Z","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00431","kind":"arxiv","version":2},"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:fe024f6aa64292dcf6c622ab24caf13788d12cce03607ebf5b7a37f342df38ce","target":"record","created_at":"2026-07-05T04:09:00Z","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":"2a854de5730b6eb5f7c2393a3e99392490f6884b8ad71b8d45c62058c7f6f9a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T11:47:09Z","title_canon_sha256":"10fa7c28762f8ed2eec563d9763428cd75d2024a086e87f891f9c5a26b1ada6d"},"schema_version":"1.0","source":{"id":"2112.00431","kind":"arxiv","version":2}},"canonical_sha256":"a59521547f45e0919dc4d0feea1d2e8029b0964329675f03340de8b759f13b11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a59521547f45e0919dc4d0feea1d2e8029b0964329675f03340de8b759f13b11","first_computed_at":"2026-07-05T04:09:00.194637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:00.194637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UEHV3SlkJnC+kG6t9xxhKJAf6WTmCqYa5BDx2I46SJcDK0yoi5KAu7ziV9mi068BJTKKRzH6su0nFbTnP+u9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:00.195112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00431","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe024f6aa64292dcf6c622ab24caf13788d12cce03607ebf5b7a37f342df38ce","sha256:11cc74b5c7c60eb604a32ecafadcd5a9090dca9b0e84c898a603f778e89975d0"],"state_sha256":"2cbf7bffaedb2d504f5526daf0d01a217db67c3ed3b65c79778857786bcefedc"}