{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:G75I6UX5TVFCQFRTNYL2MPUPBE","short_pith_number":"pith:G75I6UX5","canonical_record":{"source":{"id":"1805.09119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T13:20:16Z","cross_cats_sorted":[],"title_canon_sha256":"e7a44f38ff575138f16ada1431717d49fdb8b895eed8bbf9319c8102dde470e1","abstract_canon_sha256":"2cbdbfd61e41ddc69c232ca3be1d72320e39f9dfa5de525c4915d37cf9aadeb7"},"schema_version":"1.0"},"canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","source":{"kind":"arxiv","id":"1805.09119","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09119","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09119v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09119","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"G75I6UX5TVFC","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G75I6UX5TVFCQFRT","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G75I6UX5","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:G75I6UX5TVFCQFRTNYL2MPUPBE","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T13:20:16Z","cross_cats_sorted":[],"title_canon_sha256":"e7a44f38ff575138f16ada1431717d49fdb8b895eed8bbf9319c8102dde470e1","abstract_canon_sha256":"2cbdbfd61e41ddc69c232ca3be1d72320e39f9dfa5de525c4915d37cf9aadeb7"},"schema_version":"1.0"},"canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:08.526743Z","signature_b64":"XADWjFgGQiX+6qCavDtYObt1qy71nKylCexQ23+fVi1ZgrXc2JQi9ywgtOcLyg9Ts2BjuX1WCNOyOhrebrU2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","last_reissued_at":"2026-05-18T00:15:08.526338Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:08.526338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09119","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":"2026-05-18T00:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOsxfqg1y3vaZu2THJfyWJJRo1J2I7BVLMJ+608KdcwWMmYC5dIl5CgmCSMnzLrTguaB0T4x2IgDtqUfoV/mDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T08:18:20.609964Z"},"content_sha256":"397117f1ec70f74f581c4a9b50bc515c2b32a520f9a078120013ed77f872984b","schema_version":"1.0","event_id":"sha256:397117f1ec70f74f581c4a9b50bc515c2b32a520f9a078120013ed77f872984b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:G75I6UX5TVFCQFRTNYL2MPUPBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Judith Gaspers, Penny Karanasou, Rajen Chatterjee","submitted_at":"2018-05-23T13:20:16Z","abstract_excerpt":"This paper investigates the use of Machine Translation (MT) to bootstrap a Natural Language Understanding (NLU) system for a new language for the use case of a large-scale voice-controlled device. The goal is to decrease the cost and time needed to get an annotated corpus for the new language, while still having a large enough coverage of user requests. Different methods of filtering MT data in order to keep utterances that improve NLU performance and language-specific post-processing methods are investigated. These methods are tested in a large-scale NLU task with translating around 10 millio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09119","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":""},"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":"2026-05-18T00:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdB7Fb8cF6j37Wy7dziCVo1w9aZU2iil4AnaQcgjIH+eHWjIEaYrPWt48LYauNOXvTCu3qMeJC4d6TaKqUmKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T08:18:20.610714Z"},"content_sha256":"01ed1548fb32f63552458dfec5a6381f6a1c5f128d4733d0528c3748d88c5063","schema_version":"1.0","event_id":"sha256:01ed1548fb32f63552458dfec5a6381f6a1c5f128d4733d0528c3748d88c5063"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/bundle.json","state_url":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/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":"2026-06-08T08:18:20Z","links":{"resolver":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE","bundle":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/bundle.json","state":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G75I6UX5TVFCQFRTNYL2MPUPBE","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":"2cbdbfd61e41ddc69c232ca3be1d72320e39f9dfa5de525c4915d37cf9aadeb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T13:20:16Z","title_canon_sha256":"e7a44f38ff575138f16ada1431717d49fdb8b895eed8bbf9319c8102dde470e1"},"schema_version":"1.0","source":{"id":"1805.09119","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09119","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09119v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09119","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"G75I6UX5TVFC","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G75I6UX5TVFCQFRT","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G75I6UX5","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:01ed1548fb32f63552458dfec5a6381f6a1c5f128d4733d0528c3748d88c5063","target":"graph","created_at":"2026-05-18T00:15:08Z","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"},"paper":{"abstract_excerpt":"This paper investigates the use of Machine Translation (MT) to bootstrap a Natural Language Understanding (NLU) system for a new language for the use case of a large-scale voice-controlled device. The goal is to decrease the cost and time needed to get an annotated corpus for the new language, while still having a large enough coverage of user requests. Different methods of filtering MT data in order to keep utterances that improve NLU performance and language-specific post-processing methods are investigated. These methods are tested in a large-scale NLU task with translating around 10 millio","authors_text":"Judith Gaspers, Penny Karanasou, Rajen Chatterjee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T13:20:16Z","title":"Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09119","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":"sha256:397117f1ec70f74f581c4a9b50bc515c2b32a520f9a078120013ed77f872984b","target":"record","created_at":"2026-05-18T00:15:08Z","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":"2cbdbfd61e41ddc69c232ca3be1d72320e39f9dfa5de525c4915d37cf9aadeb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T13:20:16Z","title_canon_sha256":"e7a44f38ff575138f16ada1431717d49fdb8b895eed8bbf9319c8102dde470e1"},"schema_version":"1.0","source":{"id":"1805.09119","kind":"arxiv","version":1}},"canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","first_computed_at":"2026-05-18T00:15:08.526338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:08.526338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XADWjFgGQiX+6qCavDtYObt1qy71nKylCexQ23+fVi1ZgrXc2JQi9ywgtOcLyg9Ts2BjuX1WCNOyOhrebrU2Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:08.526743Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09119","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:397117f1ec70f74f581c4a9b50bc515c2b32a520f9a078120013ed77f872984b","sha256:01ed1548fb32f63552458dfec5a6381f6a1c5f128d4733d0528c3748d88c5063"],"state_sha256":"e4c2b1f7bd15189a2311bc8a7300115fa8fc0163dd6b06f652f0599266eb1198"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QXc70XmuPYVIbeIAd1BqU66LO2IqkvPjMzUtKYzyfKC9WojCsLHiMoj5oiIlYnx2laoamjIltkQ+igh4e4BjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T08:18:20.614981Z","bundle_sha256":"2e967407e07ccc21ca557530226452dddb0fa8874632e510fdb42148d616061e"}}