{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:74YWRKKF77HVGOKC6VZ4IWZIQY","short_pith_number":"pith:74YWRKKF","schema_version":"1.0","canonical_sha256":"ff3168a945ffcf533942f573c45b28861cf50a1dde8f753dec0a1d8aa0f467e2","source":{"kind":"arxiv","id":"2111.09531","version":1},"attestation_state":"computed","paper":{"title":"Triple Attention Network architecture for MovieQA","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Ankit Shah, Shijie Wu, Tzu-Hsiang Lin","submitted_at":"2021-11-18T05:45:23Z","abstract_excerpt":"Movie question answering, or MovieQA is a multimedia related task wherein one is provided with a video, the subtitle information, a question and candidate answers for it. The task is to predict the correct answer for the question using the components of the multimedia - namely video/images, audio and text. Traditionally, MovieQA is done using the image and text component of the multimedia. In this paper, we propose a novel network with triple-attention architecture for the inclusion of audio in the Movie QA task. This architecture is fashioned after a traditional dual attention network focused"},"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":"2111.09531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MM","submitted_at":"2021-11-18T05:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"a3fb70ac0624b8af16f62c5a6dee5045294b1b150b37358e73ff79c5dacbc6eb","abstract_canon_sha256":"cb00df2443209f0f9e12d3c55aaa7213d1a45e4cd38a8bc6f7adbb5a78c09104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:12.582493Z","signature_b64":"KHvq+ZibbspsnvKGdqGotfQgXOmTWL8F546LCM0G31eckXf54a7weGv4KOMjeOhZxdfOKMdv/EoWwKk8VaDJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff3168a945ffcf533942f573c45b28861cf50a1dde8f753dec0a1d8aa0f467e2","last_reissued_at":"2026-07-05T03:33:12.581995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:12.581995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triple Attention Network architecture for MovieQA","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Ankit Shah, Shijie Wu, Tzu-Hsiang Lin","submitted_at":"2021-11-18T05:45:23Z","abstract_excerpt":"Movie question answering, or MovieQA is a multimedia related task wherein one is provided with a video, the subtitle information, a question and candidate answers for it. The task is to predict the correct answer for the question using the components of the multimedia - namely video/images, audio and text. Traditionally, MovieQA is done using the image and text component of the multimedia. In this paper, we propose a novel network with triple-attention architecture for the inclusion of audio in the Movie QA task. This architecture is fashioned after a traditional dual attention network focused"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09531","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/2111.09531/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":"2111.09531","created_at":"2026-07-05T03:33:12.582055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09531v1","created_at":"2026-07-05T03:33:12.582055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09531","created_at":"2026-07-05T03:33:12.582055+00:00"},{"alias_kind":"pith_short_12","alias_value":"74YWRKKF77HV","created_at":"2026-07-05T03:33:12.582055+00:00"},{"alias_kind":"pith_short_16","alias_value":"74YWRKKF77HVGOKC","created_at":"2026-07-05T03:33:12.582055+00:00"},{"alias_kind":"pith_short_8","alias_value":"74YWRKKF","created_at":"2026-07-05T03:33:12.582055+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/74YWRKKF77HVGOKC6VZ4IWZIQY","json":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY.json","graph_json":"https://pith.science/api/pith-number/74YWRKKF77HVGOKC6VZ4IWZIQY/graph.json","events_json":"https://pith.science/api/pith-number/74YWRKKF77HVGOKC6VZ4IWZIQY/events.json","paper":"https://pith.science/paper/74YWRKKF"},"agent_actions":{"view_html":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY","download_json":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY.json","view_paper":"https://pith.science/paper/74YWRKKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09531&json=true","fetch_graph":"https://pith.science/api/pith-number/74YWRKKF77HVGOKC6VZ4IWZIQY/graph.json","fetch_events":"https://pith.science/api/pith-number/74YWRKKF77HVGOKC6VZ4IWZIQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY/action/storage_attestation","attest_author":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY/action/author_attestation","sign_citation":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY/action/citation_signature","submit_replication":"https://pith.science/pith/74YWRKKF77HVGOKC6VZ4IWZIQY/action/replication_record"}},"created_at":"2026-07-05T03:33:12.582055+00:00","updated_at":"2026-07-05T03:33:12.582055+00:00"}