{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B6VR662N6DWMXPRGHZB6H5I6ZF","short_pith_number":"pith:B6VR662N","schema_version":"1.0","canonical_sha256":"0fab1f7b4df0eccbbe263e43e3f51ec96bf64db60873464a71b1eaf82a8cd257","source":{"kind":"arxiv","id":"1908.01665","version":2},"attestation_state":"computed","paper":{"title":"Predicting Actions to Help Predict Translations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Josiah Wang, Julia Ive, Lucia Specia, Pranava Madhyastha, Zixiu Wu","submitted_at":"2019-08-05T14:56:01Z","abstract_excerpt":"We address the task of text translation on the How2 dataset using a state of the art transformer-based multimodal approach. The question we ask ourselves is whether visual features can support the translation process, in particular, given that this is a dataset extracted from videos, we focus on the translation of actions, which we believe are poorly captured in current static image-text datasets currently used for multimodal translation. For that purpose, we extract different types of action features from the videos and carefully investigate how helpful this visual information is by testing w"},"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":"1908.01665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-05T14:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"fc448c1e8e3324dfc569c2058138c3aaee85e4fb2eae3cffc0e365bb654da66a","abstract_canon_sha256":"355c782a583e3ff572f2dce77bcd765b74b0d9013073843096994647eb775c54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:10.542280Z","signature_b64":"sZ68sXOJmNP/dtgcBpW7SYy21sDpXQ05KpkQP5HxZEd+QG9umWIa2IuTECZP1G/S14fBKfloR1nMLCEfqxs0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fab1f7b4df0eccbbe263e43e3f51ec96bf64db60873464a71b1eaf82a8cd257","last_reissued_at":"2026-07-04T23:58:10.541922Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:10.541922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Actions to Help Predict Translations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Josiah Wang, Julia Ive, Lucia Specia, Pranava Madhyastha, Zixiu Wu","submitted_at":"2019-08-05T14:56:01Z","abstract_excerpt":"We address the task of text translation on the How2 dataset using a state of the art transformer-based multimodal approach. The question we ask ourselves is whether visual features can support the translation process, in particular, given that this is a dataset extracted from videos, we focus on the translation of actions, which we believe are poorly captured in current static image-text datasets currently used for multimodal translation. For that purpose, we extract different types of action features from the videos and carefully investigate how helpful this visual information is by testing w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01665","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/1908.01665/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":"1908.01665","created_at":"2026-07-04T23:58:10.541977+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01665v2","created_at":"2026-07-04T23:58:10.541977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01665","created_at":"2026-07-04T23:58:10.541977+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6VR662N6DWM","created_at":"2026-07-04T23:58:10.541977+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6VR662N6DWMXPRG","created_at":"2026-07-04T23:58:10.541977+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6VR662N","created_at":"2026-07-04T23:58:10.541977+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/B6VR662N6DWMXPRGHZB6H5I6ZF","json":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF.json","graph_json":"https://pith.science/api/pith-number/B6VR662N6DWMXPRGHZB6H5I6ZF/graph.json","events_json":"https://pith.science/api/pith-number/B6VR662N6DWMXPRGHZB6H5I6ZF/events.json","paper":"https://pith.science/paper/B6VR662N"},"agent_actions":{"view_html":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF","download_json":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF.json","view_paper":"https://pith.science/paper/B6VR662N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01665&json=true","fetch_graph":"https://pith.science/api/pith-number/B6VR662N6DWMXPRGHZB6H5I6ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/B6VR662N6DWMXPRGHZB6H5I6ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF/action/storage_attestation","attest_author":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF/action/author_attestation","sign_citation":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF/action/citation_signature","submit_replication":"https://pith.science/pith/B6VR662N6DWMXPRGHZB6H5I6ZF/action/replication_record"}},"created_at":"2026-07-04T23:58:10.541977+00:00","updated_at":"2026-07-04T23:58:10.541977+00:00"}