{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LWHOPUTQ3WL62G6TWCR3QS5FOD","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":"161d48d9b79c0bd40f9b07976c715ecbf85c60c695d94ad32658ba9b1a03e78e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-24T19:30:38Z","title_canon_sha256":"fe8f5ccfa47baf752c83ef7037273aa5d230219a34cdb62454b6a7e5d0196b02"},"schema_version":"1.0","source":{"id":"2004.11954","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.11954","created_at":"2026-07-05T00:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"2004.11954v2","created_at":"2026-07-05T00:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11954","created_at":"2026-07-05T00:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"LWHOPUTQ3WL6","created_at":"2026-07-05T00:59:03Z"},{"alias_kind":"pith_short_16","alias_value":"LWHOPUTQ3WL62G6T","created_at":"2026-07-05T00:59:03Z"},{"alias_kind":"pith_short_8","alias_value":"LWHOPUTQ","created_at":"2026-07-05T00:59:03Z"}],"graph_snapshots":[{"event_id":"sha256:17df40e5b2230f3b17cc87f1c9ff53b2adc953de7333c8286da0cdf06989b4a0","target":"graph","created_at":"2026-07-05T00:59:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.11954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aman Madaan, Antonios Anastasopoulos, Graham Neubig, Shruti Rijhwani, Yiming Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-24T19:30:38Z","title":"Practical Comparable Data Collection for Low-Resource Languages via Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11954","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":"sha256:8b225e52201b0bcb78606f0bea1c5eb21b38b15550863f8ad33aed94104775d9","target":"record","created_at":"2026-07-05T00:59:03Z","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":"161d48d9b79c0bd40f9b07976c715ecbf85c60c695d94ad32658ba9b1a03e78e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-24T19:30:38Z","title_canon_sha256":"fe8f5ccfa47baf752c83ef7037273aa5d230219a34cdb62454b6a7e5d0196b02"},"schema_version":"1.0","source":{"id":"2004.11954","kind":"arxiv","version":2}},"canonical_sha256":"5d8ee7d270dd97ed1bd3b0a3b84ba570e4805fc4ad0e2d1ae14cf46ef6ee225f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d8ee7d270dd97ed1bd3b0a3b84ba570e4805fc4ad0e2d1ae14cf46ef6ee225f","first_computed_at":"2026-07-05T00:59:03.598333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:03.598333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rzx889d05Ni0AqJb2KMNs1PFtQ+8XdvproEK7ePJEpO3/0JQ/Kfa/mV3pyMXH3o40L/TdNkGyd+CyYKaiNqRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:03.598751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.11954","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b225e52201b0bcb78606f0bea1c5eb21b38b15550863f8ad33aed94104775d9","sha256:17df40e5b2230f3b17cc87f1c9ff53b2adc953de7333c8286da0cdf06989b4a0"],"state_sha256":"093f9f3878d023c3f8e49bab25c0e54d30ed60730f4140022fca0bb01bb01661"}