{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BDWI23ED5U3KII67S2K7SGI7TH","short_pith_number":"pith:BDWI23ED","schema_version":"1.0","canonical_sha256":"08ec8d6c83ed36a423df9695f9191f99d764924578e55fb624418900fcdf9618","source":{"kind":"arxiv","id":"1811.00347","version":2},"attestation_state":"computed","paper":{"title":"How2: A Large-scale Dataset for Multimodal Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Florian Metze, Lo\\\"ic Barrault, Lucia Specia, Ozan Caglayan, Ramon Sanabria, Shruti Palaskar","submitted_at":"2018-11-01T12:47:11Z","abstract_excerpt":"In this paper, we introduce How2, a multimodal collection of instructional videos with English subtitles and crowdsourced Portuguese translations. We also present integrated sequence-to-sequence baselines for machine translation, automatic speech recognition, spoken language translation, and multimodal summarization. By making available data and code for several multimodal natural language tasks, we hope to stimulate more research on these and similar challenges, to obtain a deeper understanding of multimodality in language processing."},"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":"1811.00347","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T12:47:11Z","cross_cats_sorted":[],"title_canon_sha256":"8014a24209258b691b66a54970be36ffc3cdfa719a6e59b9e0ba2f82d54b7395","abstract_canon_sha256":"00659c605599edbc9ee34e42e3a8f92f5557e2f3685078c8528f22cb3575aeea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:52.425591Z","signature_b64":"6sQPIiY5DCi+lO6GJKYCAmJv94AQfHD9WDUiVikrXsP/MsetgCUPIidkd36AeY/XQlp5q3Nh1SwS7j95F4LNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ec8d6c83ed36a423df9695f9191f99d764924578e55fb624418900fcdf9618","last_reissued_at":"2026-05-17T23:58:52.425061Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:52.425061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How2: A Large-scale Dataset for Multimodal Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Florian Metze, Lo\\\"ic Barrault, Lucia Specia, Ozan Caglayan, Ramon Sanabria, Shruti Palaskar","submitted_at":"2018-11-01T12:47:11Z","abstract_excerpt":"In this paper, we introduce How2, a multimodal collection of instructional videos with English subtitles and crowdsourced Portuguese translations. We also present integrated sequence-to-sequence baselines for machine translation, automatic speech recognition, spoken language translation, and multimodal summarization. By making available data and code for several multimodal natural language tasks, we hope to stimulate more research on these and similar challenges, to obtain a deeper understanding of multimodality in language processing."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00347","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":""},"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":"1811.00347","created_at":"2026-05-17T23:58:52.425144+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00347v2","created_at":"2026-05-17T23:58:52.425144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00347","created_at":"2026-05-17T23:58:52.425144+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDWI23ED5U3K","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDWI23ED5U3KII67","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDWI23ED","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2312.06950","citing_title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2406.05615","citing_title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20638","citing_title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06789","citing_title":"Video-guided Machine Translation with Global Video Context","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH","json":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH.json","graph_json":"https://pith.science/api/pith-number/BDWI23ED5U3KII67S2K7SGI7TH/graph.json","events_json":"https://pith.science/api/pith-number/BDWI23ED5U3KII67S2K7SGI7TH/events.json","paper":"https://pith.science/paper/BDWI23ED"},"agent_actions":{"view_html":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH","download_json":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH.json","view_paper":"https://pith.science/paper/BDWI23ED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00347&json=true","fetch_graph":"https://pith.science/api/pith-number/BDWI23ED5U3KII67S2K7SGI7TH/graph.json","fetch_events":"https://pith.science/api/pith-number/BDWI23ED5U3KII67S2K7SGI7TH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/action/storage_attestation","attest_author":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/action/author_attestation","sign_citation":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/action/citation_signature","submit_replication":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/action/replication_record"}},"created_at":"2026-05-17T23:58:52.425144+00:00","updated_at":"2026-05-17T23:58:52.425144+00:00"}