{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:L6X3QJ3QWKYAUB3A7YWETBTMMO","short_pith_number":"pith:L6X3QJ3Q","canonical_record":{"source":{"id":"2303.15265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T14:54:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2e2dfd926018880d0e9126a1df954fbeb490e82bdb54384d0e70fea80c46be8","abstract_canon_sha256":"f9323b20209f783a4beeaa2bed23bc9a43b65a70f541c4e46f3c3f367c31bf4d"},"schema_version":"1.0"},"canonical_sha256":"5fafb82770b2b00a0760fe2c49866c63b00c7148d9bbdf29e3f01ea61b589ed5","source":{"kind":"arxiv","id":"2303.15265","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15265","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15265v1","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15265","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"L6X3QJ3QWKYA","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"pith_short_16","alias_value":"L6X3QJ3QWKYAUB3A","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"pith_short_8","alias_value":"L6X3QJ3Q","created_at":"2026-07-05T05:55:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:L6X3QJ3QWKYAUB3A7YWETBTMMO","target":"record","payload":{"canonical_record":{"source":{"id":"2303.15265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T14:54:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2e2dfd926018880d0e9126a1df954fbeb490e82bdb54384d0e70fea80c46be8","abstract_canon_sha256":"f9323b20209f783a4beeaa2bed23bc9a43b65a70f541c4e46f3c3f367c31bf4d"},"schema_version":"1.0"},"canonical_sha256":"5fafb82770b2b00a0760fe2c49866c63b00c7148d9bbdf29e3f01ea61b589ed5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:03.111105Z","signature_b64":"G6KcjQe8w4TQ0xoITmPJ1E1TBZUD4l7JxtnjCzsW3KpU57/LL6WU32ai21Y+/6Va95/Y0pzedOrA0iseCY5iBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fafb82770b2b00a0760fe2c49866c63b00c7148d9bbdf29e3f01ea61b589ed5","last_reissued_at":"2026-07-05T05:55:03.110652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:03.110652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.15265","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMI36I6qFSzbddWZxEIg6NsaPzp/y7DWp4igr12RIeoDIVlbR8Q2T22YBAyARSH4mk2qDgYDD3XMmNwF4L/RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:57:31.627301Z"},"content_sha256":"cfabdd9cadc004530b258b2a8bc1c2a1d6f7b25d354e523b8551731975226672","schema_version":"1.0","event_id":"sha256:cfabdd9cadc004530b258b2a8bc1c2a1d6f7b25d354e523b8551731975226672"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:L6X3QJ3QWKYAUB3A7YWETBTMMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Jones, Isaac Caswell, Ishank Saxena, Orhan Firat","submitted_at":"2023-03-27T14:54:43Z","abstract_excerpt":"Neural machine translation (NMT) has progressed rapidly over the past several years, and modern models are able to achieve relatively high quality using only monolingual text data, an approach dubbed Unsupervised Machine Translation (UNMT). However, these models still struggle in a variety of ways, including aspects of translation that for a human are the easiest - for instance, correctly translating common nouns. This work explores a cheap and abundant resource to combat this problem: bilingual lexica. We test the efficacy of bilingual lexica in a real-world set-up, on 200-language translatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15265","kind":"arxiv","version":1},"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/2303.15265/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":"2026-07-05T05:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wa5cYvPr7Y2ub+VlEC9KZJyyn/CVaKFPi+od6wn7EcUa6zMa/UuQChzvx0G1lrHK0oBCkdVyieem/Pd/idHhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:57:31.628154Z"},"content_sha256":"cc5c09f4e473ae59cd1f46f3e5946509f8bd39031a317e22eeff92c4b8362d1e","schema_version":"1.0","event_id":"sha256:cc5c09f4e473ae59cd1f46f3e5946509f8bd39031a317e22eeff92c4b8362d1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO/bundle.json","state_url":"https://pith.science/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO/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":"2026-08-09T23:57:31Z","links":{"resolver":"https://pith.science/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO","bundle":"https://pith.science/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO/bundle.json","state":"https://pith.science/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6X3QJ3QWKYAUB3A7YWETBTMMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L6X3QJ3QWKYAUB3A7YWETBTMMO","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":"f9323b20209f783a4beeaa2bed23bc9a43b65a70f541c4e46f3c3f367c31bf4d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T14:54:43Z","title_canon_sha256":"d2e2dfd926018880d0e9126a1df954fbeb490e82bdb54384d0e70fea80c46be8"},"schema_version":"1.0","source":{"id":"2303.15265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15265","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15265v1","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15265","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"L6X3QJ3QWKYA","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"pith_short_16","alias_value":"L6X3QJ3QWKYAUB3A","created_at":"2026-07-05T05:55:03Z"},{"alias_kind":"pith_short_8","alias_value":"L6X3QJ3Q","created_at":"2026-07-05T05:55:03Z"}],"graph_snapshots":[{"event_id":"sha256:cc5c09f4e473ae59cd1f46f3e5946509f8bd39031a317e22eeff92c4b8362d1e","target":"graph","created_at":"2026-07-05T05:55:03Z","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/2303.15265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural machine translation (NMT) has progressed rapidly over the past several years, and modern models are able to achieve relatively high quality using only monolingual text data, an approach dubbed Unsupervised Machine Translation (UNMT). However, these models still struggle in a variety of ways, including aspects of translation that for a human are the easiest - for instance, correctly translating common nouns. This work explores a cheap and abundant resource to combat this problem: bilingual lexica. We test the efficacy of bilingual lexica in a real-world set-up, on 200-language translatio","authors_text":"Alex Jones, Isaac Caswell, Ishank Saxena, Orhan Firat","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T14:54:43Z","title":"Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15265","kind":"arxiv","version":1},"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:cfabdd9cadc004530b258b2a8bc1c2a1d6f7b25d354e523b8551731975226672","target":"record","created_at":"2026-07-05T05:55:03Z","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":"f9323b20209f783a4beeaa2bed23bc9a43b65a70f541c4e46f3c3f367c31bf4d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T14:54:43Z","title_canon_sha256":"d2e2dfd926018880d0e9126a1df954fbeb490e82bdb54384d0e70fea80c46be8"},"schema_version":"1.0","source":{"id":"2303.15265","kind":"arxiv","version":1}},"canonical_sha256":"5fafb82770b2b00a0760fe2c49866c63b00c7148d9bbdf29e3f01ea61b589ed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fafb82770b2b00a0760fe2c49866c63b00c7148d9bbdf29e3f01ea61b589ed5","first_computed_at":"2026-07-05T05:55:03.110652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:03.110652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G6KcjQe8w4TQ0xoITmPJ1E1TBZUD4l7JxtnjCzsW3KpU57/LL6WU32ai21Y+/6Va95/Y0pzedOrA0iseCY5iBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:03.111105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfabdd9cadc004530b258b2a8bc1c2a1d6f7b25d354e523b8551731975226672","sha256:cc5c09f4e473ae59cd1f46f3e5946509f8bd39031a317e22eeff92c4b8362d1e"],"state_sha256":"95a2392cc1151f4c549c044f8370dda8ae73d3befb55cff9917decc335844702"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WA89Dex4dwtylFoYy94svmZe7uy4WyAtwxDdicXTQQuqqpRavMxl/3EUUFdXd2bVq924U0/6DADwR3IAxu3WCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:57:31.634260Z","bundle_sha256":"4082ef395e000c95bbb23db505d3ada7673151dbb43cf4501213e11ac339b167"}}