{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GZCWEVMY4JASX4JLD55FF3SPFJ","short_pith_number":"pith:GZCWEVMY","canonical_record":{"source":{"id":"2004.02071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T02:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"65850ca2105227f4245337b6fb0902d9229065f52e5a164584d12f542cd13c88","abstract_canon_sha256":"bfef49cf9a96a225abfd3c3e47601021fcf15831518d186d3ff8daff46e29d95"},"schema_version":"1.0"},"canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","source":{"kind":"arxiv","id":"2004.02071","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02071","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02071v1","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02071","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"GZCWEVMY4JAS","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"GZCWEVMY4JASX4JL","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"GZCWEVMY","created_at":"2026-07-05T00:52:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GZCWEVMY4JASX4JLD55FF3SPFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2004.02071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T02:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"65850ca2105227f4245337b6fb0902d9229065f52e5a164584d12f542cd13c88","abstract_canon_sha256":"bfef49cf9a96a225abfd3c3e47601021fcf15831518d186d3ff8daff46e29d95"},"schema_version":"1.0"},"canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:55.679403Z","signature_b64":"ApPcoh1QyZhmtWWKW+YYTkqUO/XhJfty2uYB5Iyp0lLW9yDSnEfAqETbtCZKdcjx+C6YX/CulgIM/KLsdQiUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","last_reissued_at":"2026-07-05T00:52:55.678970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:55.678970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.02071","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":"2026-07-05T00:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ODV5sisAnsvdZrUXQlRDuLoKp/EvJRE36MLoPlK4I9nXgEswm8JnjiT/MoNqhNz5JKcafxhaZHtdpId6BBnIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:21:32.641468Z"},"content_sha256":"d9b048fe90eb9bf3e10024be884a45f07620bb026c6f351a6115475a10667629","schema_version":"1.0","event_id":"sha256:d9b048fe90eb9bf3e10024be884a45f07620bb026c6f351a6115475a10667629"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GZCWEVMY4JASX4JLD55FF3SPFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mihir Kale, Sreyashi Nag, Swapnil Singhavi, Varun Lakshminarasimhan","submitted_at":"2020-04-05T02:14:14Z","abstract_excerpt":"We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of back-translation models is tied to the size of the available parallel corpora, this could adversely impact the synthetically generated sentences in a low resource setting. We propose a simple data augmentation technique to address both this shortcoming. We incorporate widely available bilingual dictionaries that yield word-by-word translations to generate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02071","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/2004.02071/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":"2026-07-05T00:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74VxSjO1rcaldQpaTSlzjmL2Dwnc3h3EF+HczgPNyz5Xi/04hA36Ji+S3KXoe5Yo+h2S2WTb0p8ZEiMcx3UhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:21:32.641956Z"},"content_sha256":"f7b2122fbc73eefd88fd2a709a4fd0e90f8a54df586cadb2b1439c178afa60e9","schema_version":"1.0","event_id":"sha256:f7b2122fbc73eefd88fd2a709a4fd0e90f8a54df586cadb2b1439c178afa60e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/bundle.json","state_url":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/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":"2026-08-09T06:21:32Z","links":{"resolver":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ","bundle":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/bundle.json","state":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GZCWEVMY4JASX4JLD55FF3SPFJ","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":"bfef49cf9a96a225abfd3c3e47601021fcf15831518d186d3ff8daff46e29d95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T02:14:14Z","title_canon_sha256":"65850ca2105227f4245337b6fb0902d9229065f52e5a164584d12f542cd13c88"},"schema_version":"1.0","source":{"id":"2004.02071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02071","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02071v1","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02071","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"GZCWEVMY4JAS","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"GZCWEVMY4JASX4JL","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"GZCWEVMY","created_at":"2026-07-05T00:52:55Z"}],"graph_snapshots":[{"event_id":"sha256:f7b2122fbc73eefd88fd2a709a4fd0e90f8a54df586cadb2b1439c178afa60e9","target":"graph","created_at":"2026-07-05T00:52:55Z","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/2004.02071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of back-translation models is tied to the size of the available parallel corpora, this could adversely impact the synthetically generated sentences in a low resource setting. We propose a simple data augmentation technique to address both this shortcoming. We incorporate widely available bilingual dictionaries that yield word-by-word translations to generate s","authors_text":"Mihir Kale, Sreyashi Nag, Swapnil Singhavi, Varun Lakshminarasimhan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T02:14:14Z","title":"Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02071","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:d9b048fe90eb9bf3e10024be884a45f07620bb026c6f351a6115475a10667629","target":"record","created_at":"2026-07-05T00:52:55Z","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":"bfef49cf9a96a225abfd3c3e47601021fcf15831518d186d3ff8daff46e29d95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T02:14:14Z","title_canon_sha256":"65850ca2105227f4245337b6fb0902d9229065f52e5a164584d12f542cd13c88"},"schema_version":"1.0","source":{"id":"2004.02071","kind":"arxiv","version":1}},"canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","first_computed_at":"2026-07-05T00:52:55.678970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:55.678970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ApPcoh1QyZhmtWWKW+YYTkqUO/XhJfty2uYB5Iyp0lLW9yDSnEfAqETbtCZKdcjx+C6YX/CulgIM/KLsdQiUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:55.679403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9b048fe90eb9bf3e10024be884a45f07620bb026c6f351a6115475a10667629","sha256:f7b2122fbc73eefd88fd2a709a4fd0e90f8a54df586cadb2b1439c178afa60e9"],"state_sha256":"cfaab561a6d8282df4996ddd3fb7150af898b55df357a1d25e93cbd81736052a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AuGifjIAiWpNZIW1MMPxfZadMxr9W7/j8i9IW0VWzaA5u6ulT5wmB9MXNWk1sLbhNjM6QDsxXecqyrGkX39BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:21:32.645417Z","bundle_sha256":"46028d785ee4ae206e8ce03b23f63cb2bd61611bc47538da9422576345186507"}}