{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UWKSCVD7IXQJDHOE2D7OUHJOQA","short_pith_number":"pith:UWKSCVD7","schema_version":"1.0","canonical_sha256":"a59521547f45e0919dc4d0feea1d2e8029b0964329675f03340de8b759f13b11","source":{"kind":"arxiv","id":"2112.00431","version":2},"attestation_state":"computed","paper":{"title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alejandro Pardo, Bernard Ghanem, Chen Zhao, Fabian Caba Heilbron, Juan Le\\'on Alc\\'azar, Mattia Soldan, Silvio Giancola","submitted_at":"2021-12-01T11:47:09Z","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"},"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":"2112.00431","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T11:47:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10fa7c28762f8ed2eec563d9763428cd75d2024a086e87f891f9c5a26b1ada6d","abstract_canon_sha256":"2a854de5730b6eb5f7c2393a3e99392490f6884b8ad71b8d45c62058c7f6f9a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:00.195112Z","signature_b64":"UEHV3SlkJnC+kG6t9xxhKJAf6WTmCqYa5BDx2I46SJcDK0yoi5KAu7ziV9mi068BJTKKRzH6su0nFbTnP+u9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a59521547f45e0919dc4d0feea1d2e8029b0964329675f03340de8b759f13b11","last_reissued_at":"2026-07-05T04:09:00.194637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:00.194637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alejandro Pardo, Bernard Ghanem, Chen Zhao, Fabian Caba Heilbron, Juan Le\\'on Alc\\'azar, Mattia Soldan, Silvio Giancola","submitted_at":"2021-12-01T11:47:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00431","kind":"arxiv","version":2},"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/2112.00431/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":"2112.00431","created_at":"2026-07-05T04:09:00.194699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00431v2","created_at":"2026-07-05T04:09:00.194699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00431","created_at":"2026-07-05T04:09:00.194699+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWKSCVD7IXQJ","created_at":"2026-07-05T04:09:00.194699+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWKSCVD7IXQJDHOE","created_at":"2026-07-05T04:09:00.194699+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWKSCVD7","created_at":"2026-07-05T04:09:00.194699+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/UWKSCVD7IXQJDHOE2D7OUHJOQA","json":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA.json","graph_json":"https://pith.science/api/pith-number/UWKSCVD7IXQJDHOE2D7OUHJOQA/graph.json","events_json":"https://pith.science/api/pith-number/UWKSCVD7IXQJDHOE2D7OUHJOQA/events.json","paper":"https://pith.science/paper/UWKSCVD7"},"agent_actions":{"view_html":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA","download_json":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA.json","view_paper":"https://pith.science/paper/UWKSCVD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00431&json=true","fetch_graph":"https://pith.science/api/pith-number/UWKSCVD7IXQJDHOE2D7OUHJOQA/graph.json","fetch_events":"https://pith.science/api/pith-number/UWKSCVD7IXQJDHOE2D7OUHJOQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA/action/storage_attestation","attest_author":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA/action/author_attestation","sign_citation":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA/action/citation_signature","submit_replication":"https://pith.science/pith/UWKSCVD7IXQJDHOE2D7OUHJOQA/action/replication_record"}},"created_at":"2026-07-05T04:09:00.194699+00:00","updated_at":"2026-07-05T04:09:00.194699+00:00"}