{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BDWI23ED5U3KII67S2K7SGI7TH","short_pith_number":"pith:BDWI23ED","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"},"canonical_sha256":"08ec8d6c83ed36a423df9695f9191f99d764924578e55fb624418900fcdf9618","source":{"kind":"arxiv","id":"1811.00347","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00347","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00347v2","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00347","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"pith_short_12","alias_value":"BDWI23ED5U3K","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"BDWI23ED5U3KII67","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"BDWI23ED","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BDWI23ED5U3KII67S2K7SGI7TH","target":"record","payload":{"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"},"canonical_sha256":"08ec8d6c83ed36a423df9695f9191f99d764924578e55fb624418900fcdf9618","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"},"source_kind":"arxiv","source_id":"1811.00347","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RPWT+YVIciwK5BxholXDM3eP8kc4joiJe9515AjXmcloCXv6eCjpYQHjCxWgcq1TMWUAxQzcDO5bq6PBL8SGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:36:18.325394Z"},"content_sha256":"1a9b2fdccb80d6e32b3079c0f9391a243e2ba9387ff27753488556e590c4ecb9","schema_version":"1.0","event_id":"sha256:1a9b2fdccb80d6e32b3079c0f9391a243e2ba9387ff27753488556e590c4ecb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BDWI23ED5U3KII67S2K7SGI7TH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVVqC+JkrxtcUYSNBL1Pfy5fD2KHUhv3TThzBgW0lrCArG/cNtxncgR4mPUIJ9mXivwSHujF8RvPEmakfa/qCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:36:18.325998Z"},"content_sha256":"ece272948df662f898ae71549b745ee1f8dd31023c58a1c3d636d1aee1a29553","schema_version":"1.0","event_id":"sha256:ece272948df662f898ae71549b745ee1f8dd31023c58a1c3d636d1aee1a29553"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/bundle.json","state_url":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BDWI23ED5U3KII67S2K7SGI7TH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-18T20:36:18Z","links":{"resolver":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH","bundle":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/bundle.json","state":"https://pith.science/pith/BDWI23ED5U3KII67S2K7SGI7TH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BDWI23ED5U3KII67S2K7SGI7TH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BDWI23ED5U3KII67S2K7SGI7TH","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":"00659c605599edbc9ee34e42e3a8f92f5557e2f3685078c8528f22cb3575aeea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T12:47:11Z","title_canon_sha256":"8014a24209258b691b66a54970be36ffc3cdfa719a6e59b9e0ba2f82d54b7395"},"schema_version":"1.0","source":{"id":"1811.00347","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00347","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00347v2","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00347","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"pith_short_12","alias_value":"BDWI23ED5U3K","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"BDWI23ED5U3KII67","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"BDWI23ED","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:ece272948df662f898ae71549b745ee1f8dd31023c58a1c3d636d1aee1a29553","target":"graph","created_at":"2026-05-17T23:58:52Z","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"},"paper":{"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.","authors_text":"Desmond Elliott, Florian Metze, Lo\\\"ic Barrault, Lucia Specia, Ozan Caglayan, Ramon Sanabria, Shruti Palaskar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T12:47:11Z","title":"How2: A Large-scale Dataset for Multimodal Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00347","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":"sha256:1a9b2fdccb80d6e32b3079c0f9391a243e2ba9387ff27753488556e590c4ecb9","target":"record","created_at":"2026-05-17T23:58:52Z","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":"00659c605599edbc9ee34e42e3a8f92f5557e2f3685078c8528f22cb3575aeea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T12:47:11Z","title_canon_sha256":"8014a24209258b691b66a54970be36ffc3cdfa719a6e59b9e0ba2f82d54b7395"},"schema_version":"1.0","source":{"id":"1811.00347","kind":"arxiv","version":2}},"canonical_sha256":"08ec8d6c83ed36a423df9695f9191f99d764924578e55fb624418900fcdf9618","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08ec8d6c83ed36a423df9695f9191f99d764924578e55fb624418900fcdf9618","first_computed_at":"2026-05-17T23:58:52.425061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:52.425061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6sQPIiY5DCi+lO6GJKYCAmJv94AQfHD9WDUiVikrXsP/MsetgCUPIidkd36AeY/XQlp5q3Nh1SwS7j95F4LNBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:52.425591Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00347","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a9b2fdccb80d6e32b3079c0f9391a243e2ba9387ff27753488556e590c4ecb9","sha256:ece272948df662f898ae71549b745ee1f8dd31023c58a1c3d636d1aee1a29553"],"state_sha256":"0df8e1f179685b4964e6d2370f4b9f93345d566dce81d6da0433b4f101698cb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pvkwrdAtJTmlpVOi5tXRpSnD6dw3YtDItO8R2EwSFFAG6simsPbPnXmo6FErdGc3OTlp0H+m+SRRxsVdxGdrAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T20:36:18.327932Z","bundle_sha256":"36107e98c621b0d0c79568141f47a7f0247ef2c16fac56da00c874eb38d6ffbc"}}