{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LWHOPUTQ3WL62G6TWCR3QS5FOD","short_pith_number":"pith:LWHOPUTQ","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"},"canonical_sha256":"5d8ee7d270dd97ed1bd3b0a3b84ba570e4805fc4ad0e2d1ae14cf46ef6ee225f","source":{"kind":"arxiv","id":"2004.11954","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LWHOPUTQ3WL62G6TWCR3QS5FOD","target":"record","payload":{"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"},"canonical_sha256":"5d8ee7d270dd97ed1bd3b0a3b84ba570e4805fc4ad0e2d1ae14cf46ef6ee225f","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"},"source_kind":"arxiv","source_id":"2004.11954","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":"2026-07-05T00:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTIxoQ5dJPZ+R5HueQaX42PH9q/UZyszw74U0on/+7qijw+NYItWyeVIGjbcKppd8LQcfBvtTsgRkS4OpA0SDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:11:46.412440Z"},"content_sha256":"8b225e52201b0bcb78606f0bea1c5eb21b38b15550863f8ad33aed94104775d9","schema_version":"1.0","event_id":"sha256:8b225e52201b0bcb78606f0bea1c5eb21b38b15550863f8ad33aed94104775d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LWHOPUTQ3WL62G6TWCR3QS5FOD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9uxRwesMFjPx/OSIZTKdnNy3sj8Z9c0tP2HmFMQSJewIfjdjYoMSFXGCfM2NwzHFW+b/AbwSGxDEM/VYOQeMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:11:46.413355Z"},"content_sha256":"17df40e5b2230f3b17cc87f1c9ff53b2adc953de7333c8286da0cdf06989b4a0","schema_version":"1.0","event_id":"sha256:17df40e5b2230f3b17cc87f1c9ff53b2adc953de7333c8286da0cdf06989b4a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/bundle.json","state_url":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/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":"2026-08-18T19:11:46Z","links":{"resolver":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD","bundle":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/bundle.json","state":"https://pith.science/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWHOPUTQ3WL62G6TWCR3QS5FOD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjNawkTFzZS32zmZD3fzyjGsEafYzwTcoEtTs6zEXOjt+jld2BjvuWMPBcCfWBZIz+dpdAxcJEKu6YMRpq2kCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:11:46.420070Z","bundle_sha256":"60621f5ded719de20de7fe14f69f8b5ec2d78bf567a9ce5dd23587bb0f2755a9"}}