{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WBMYPLQIDA6ZKQE6EYKTZKLKTC","short_pith_number":"pith:WBMYPLQI","canonical_record":{"source":{"id":"1811.03039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-07T17:50:05Z","cross_cats_sorted":[],"title_canon_sha256":"c617572e5ef8333660fe9f6304ca59e3519c453f0605c920f6d588c461476c7e","abstract_canon_sha256":"83b07d498ce796edb91d5d89bb9379bf0bceaa861e1f355a3bbef5612d156eb0"},"schema_version":"1.0"},"canonical_sha256":"b05987ae08183d95409e26153ca96a98b739214031588756f00b52bf96a7e09d","source":{"kind":"arxiv","id":"1811.03039","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03039","created_at":"2026-05-18T00:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03039v1","created_at":"2026-05-18T00:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03039","created_at":"2026-05-18T00:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"WBMYPLQIDA6Z","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WBMYPLQIDA6ZKQE6","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WBMYPLQI","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WBMYPLQIDA6ZKQE6EYKTZKLKTC","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-07T17:50:05Z","cross_cats_sorted":[],"title_canon_sha256":"c617572e5ef8333660fe9f6304ca59e3519c453f0605c920f6d588c461476c7e","abstract_canon_sha256":"83b07d498ce796edb91d5d89bb9379bf0bceaa861e1f355a3bbef5612d156eb0"},"schema_version":"1.0"},"canonical_sha256":"b05987ae08183d95409e26153ca96a98b739214031588756f00b52bf96a7e09d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:20.060041Z","signature_b64":"We/Ix32Z1xTHVMSzBZKx9t4jUZcAbboKg+ZkJ9pmkZOUrjDlks1ya+lQiGRxx/nn+MNZlSCbQGfz9X9O3OVhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05987ae08183d95409e26153ca96a98b739214031588756f00b52bf96a7e09d","last_reissued_at":"2026-05-18T00:01:20.059518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:20.059518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03039","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":"2026-05-18T00:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50H1O71v0RlT1ohhv6m3iONPo3z0M0tAUNe7uLnVvSVaEpdBz7WF1ZEOAoVWxSeUXS5rq1qgL8EgM2S8lk58Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:27:06.418643Z"},"content_sha256":"1d7a0e33a68f3f7a3aa7b351680fc14e2d134d244e65385df281d423d6db388a","schema_version":"1.0","event_id":"sha256:1d7a0e33a68f3f7a3aa7b351680fc14e2d134d244e65385df281d423d6db388a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WBMYPLQIDA6ZKQE6EYKTZKLKTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Selection with Feature Decay Algorithms Using an Approximated Target Side","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Andy Way, Gideon Maillette de Buy Wenniger","submitted_at":"2018-11-07T17:50:05Z","abstract_excerpt":"Data selection techniques applied to neural machine translation (NMT) aim to increase the performance of a model by retrieving a subset of sentences for use as training data.\n  One of the possible data selection techniques are transductive learning methods, which select the data based on the test set, i.e. the document to be translated. A limitation of these methods to date is that using the source-side test set does not by itself guarantee that sentences are selected with correct translations, or translations that are suitable given the test-set domain. Some corpora, such as subtitle corpora,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03039","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":"2026-05-18T00:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9UwKewh1Gd9okrJU/Y46YOnWNjEmqoES+N8G9oRTdNICWOFuqrJwW15DXqklXqcG4Cqj79FXHCRDB10H1NBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:27:06.418989Z"},"content_sha256":"27087653140696a6f467cce628d695d6ea20064fa5bcc9d1ffa73ea5ce229ad5","schema_version":"1.0","event_id":"sha256:27087653140696a6f467cce628d695d6ea20064fa5bcc9d1ffa73ea5ce229ad5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC/bundle.json","state_url":"https://pith.science/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC/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":"2026-06-30T07:27:06Z","links":{"resolver":"https://pith.science/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC","bundle":"https://pith.science/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC/bundle.json","state":"https://pith.science/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBMYPLQIDA6ZKQE6EYKTZKLKTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WBMYPLQIDA6ZKQE6EYKTZKLKTC","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":"83b07d498ce796edb91d5d89bb9379bf0bceaa861e1f355a3bbef5612d156eb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-07T17:50:05Z","title_canon_sha256":"c617572e5ef8333660fe9f6304ca59e3519c453f0605c920f6d588c461476c7e"},"schema_version":"1.0","source":{"id":"1811.03039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03039","created_at":"2026-05-18T00:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03039v1","created_at":"2026-05-18T00:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03039","created_at":"2026-05-18T00:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"WBMYPLQIDA6Z","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WBMYPLQIDA6ZKQE6","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WBMYPLQI","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:27087653140696a6f467cce628d695d6ea20064fa5bcc9d1ffa73ea5ce229ad5","target":"graph","created_at":"2026-05-18T00:01:20Z","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":"Data selection techniques applied to neural machine translation (NMT) aim to increase the performance of a model by retrieving a subset of sentences for use as training data.\n  One of the possible data selection techniques are transductive learning methods, which select the data based on the test set, i.e. the document to be translated. A limitation of these methods to date is that using the source-side test set does not by itself guarantee that sentences are selected with correct translations, or translations that are suitable given the test-set domain. Some corpora, such as subtitle corpora,","authors_text":"Alberto Poncelas, Andy Way, Gideon Maillette de Buy Wenniger","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-07T17:50:05Z","title":"Data Selection with Feature Decay Algorithms Using an Approximated Target Side"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03039","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":"sha256:1d7a0e33a68f3f7a3aa7b351680fc14e2d134d244e65385df281d423d6db388a","target":"record","created_at":"2026-05-18T00:01:20Z","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":"83b07d498ce796edb91d5d89bb9379bf0bceaa861e1f355a3bbef5612d156eb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-07T17:50:05Z","title_canon_sha256":"c617572e5ef8333660fe9f6304ca59e3519c453f0605c920f6d588c461476c7e"},"schema_version":"1.0","source":{"id":"1811.03039","kind":"arxiv","version":1}},"canonical_sha256":"b05987ae08183d95409e26153ca96a98b739214031588756f00b52bf96a7e09d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b05987ae08183d95409e26153ca96a98b739214031588756f00b52bf96a7e09d","first_computed_at":"2026-05-18T00:01:20.059518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:20.059518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"We/Ix32Z1xTHVMSzBZKx9t4jUZcAbboKg+ZkJ9pmkZOUrjDlks1ya+lQiGRxx/nn+MNZlSCbQGfz9X9O3OVhDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:20.060041Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d7a0e33a68f3f7a3aa7b351680fc14e2d134d244e65385df281d423d6db388a","sha256:27087653140696a6f467cce628d695d6ea20064fa5bcc9d1ffa73ea5ce229ad5"],"state_sha256":"5d2fc3ce0e698d31bf8a16b446caaab280e977daa16873549e31f473c61935f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEOQH3cOlvlHceXddj//2pscd8EVJ+gCDgP1mKI1We7QSBmab02fda4YSe8bKaYPLw3bRBtyJ91lIZh96ssHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T07:27:06.421094Z","bundle_sha256":"3f487aee877c4823e4522639f66c0a0737b6e7b0b0131c585a384cf1336d54ed"}}