{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LWHOPUTQ3WL62G6TWCR3QS5FOD","short_pith_number":"pith:LWHOPUTQ","schema_version":"1.0","canonical_sha256":"5d8ee7d270dd97ed1bd3b0a3b84ba570e4805fc4ad0e2d1ae14cf46ef6ee225f","source":{"kind":"arxiv","id":"2004.11954","version":2},"attestation_state":"computed","paper":{"title":"Practical Comparable Data Collection for Low-Resource Languages via Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Madaan, Antonios Anastasopoulos, Graham Neubig, Shruti Rijhwani, Yiming Yang","submitted_at":"2020-04-24T19:30:38Z","abstract_excerpt":"We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators. Our method involves using a carefully selected set of images as a pivot between the source and target languages by getting captions for such images in both languages independently. Human evaluations on the English-Hindi comparable corpora created with our method show that 81.1% of the pairs are acceptable translations, and only 2.47% of the pairs are not translations at all. We further establish the potential of the dataset collected through our approach by experimentin"},"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":"2004.11954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-24T19:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"fe8f5ccfa47baf752c83ef7037273aa5d230219a34cdb62454b6a7e5d0196b02","abstract_canon_sha256":"161d48d9b79c0bd40f9b07976c715ecbf85c60c695d94ad32658ba9b1a03e78e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:03.598751Z","signature_b64":"rzx889d05Ni0AqJb2KMNs1PFtQ+8XdvproEK7ePJEpO3/0JQ/Kfa/mV3pyMXH3o40L/TdNkGyd+CyYKaiNqRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d8ee7d270dd97ed1bd3b0a3b84ba570e4805fc4ad0e2d1ae14cf46ef6ee225f","last_reissued_at":"2026-07-05T00:59:03.598333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:03.598333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Comparable Data Collection for Low-Resource Languages via Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Madaan, Antonios Anastasopoulos, Graham Neubig, Shruti Rijhwani, Yiming Yang","submitted_at":"2020-04-24T19:30:38Z","abstract_excerpt":"We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators. Our method involves using a carefully selected set of images as a pivot between the source and target languages by getting captions for such images in both languages independently. Human evaluations on the English-Hindi comparable corpora created with our method show that 81.1% of the pairs are acceptable translations, and only 2.47% of the pairs are not translations at all. We further establish the potential of the dataset collected through our approach by experimentin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11954","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/2004.11954/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":"2004.11954","created_at":"2026-07-05T00:59:03.598384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.11954v2","created_at":"2026-07-05T00:59:03.598384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11954","created_at":"2026-07-05T00:59:03.598384+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWHOPUTQ3WL6","created_at":"2026-07-05T00:59:03.598384+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWHOPUTQ3WL62G6T","created_at":"2026-07-05T00:59:03.598384+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWHOPUTQ","created_at":"2026-07-05T00:59:03.598384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13453","citing_title":"LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD","json":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD.json","graph_json":"https://pith.science/api/pith-number/LWHOPUTQ3WL62G6TWCR3QS5FOD/graph.json","events_json":"https://pith.science/api/pith-number/LWHOPUTQ3WL62G6TWCR3QS5FOD/events.json","paper":"https://pith.science/paper/LWHOPUTQ"},"agent_actions":{"view_html":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD","download_json":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD.json","view_paper":"https://pith.science/paper/LWHOPUTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.11954&json=true","fetch_graph":"https://pith.science/api/pith-number/LWHOPUTQ3WL62G6TWCR3QS5FOD/graph.json","fetch_events":"https://pith.science/api/pith-number/LWHOPUTQ3WL62G6TWCR3QS5FOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/action/storage_attestation","attest_author":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/action/author_attestation","sign_citation":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/action/citation_signature","submit_replication":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/action/replication_record"}},"created_at":"2026-07-05T00:59:03.598384+00:00","updated_at":"2026-07-05T00:59:03.598384+00:00"}