{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MWBASENHYJET6BYV4VJVHXWVQT","short_pith_number":"pith:MWBASENH","canonical_record":{"source":{"id":"1811.00066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-31T18:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"768151412cbe52ed0b145b0901658a3d4f5853415f79c155bf1891179e13d0a5","abstract_canon_sha256":"4071068bda04582fb2057f78f4f34fa244206f385d7bfdcbffd60e74b283839f"},"schema_version":"1.0"},"canonical_sha256":"65820911a7c2493f0715e55353ded584f007d41ba36cd48e2cc46e584e2bb0a8","source":{"kind":"arxiv","id":"1811.00066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00066","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00066v1","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00066","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"MWBASENHYJET","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MWBASENHYJET6BYV","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MWBASENH","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MWBASENHYJET6BYV4VJVHXWVQT","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-31T18:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"768151412cbe52ed0b145b0901658a3d4f5853415f79c155bf1891179e13d0a5","abstract_canon_sha256":"4071068bda04582fb2057f78f4f34fa244206f385d7bfdcbffd60e74b283839f"},"schema_version":"1.0"},"canonical_sha256":"65820911a7c2493f0715e55353ded584f007d41ba36cd48e2cc46e584e2bb0a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.350274Z","signature_b64":"C6SdUulFDjQ8W6sifJbF78Q15lmLtRyfpiv9idksYnb4/wiPAAI0dF0bFaAaxcH9fl9C5P87fBG/FjpZuB05DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65820911a7c2493f0715e55353ded584f007d41ba36cd48e2cc46e584e2bb0a8","last_reissued_at":"2026-05-18T00:01:48.349771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.349771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00066","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":"2026-05-18T00:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JX1dA1sG77Opyz1P4QAvNMNRlDXJ/ArH+qlcyoMRArs5AQQmoLwEHtqNBEG6MjAVwVHcTgjb0nHRzlGgkelhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:23:22.240091Z"},"content_sha256":"c928224ff8713203c58017445f159158ce0ac9896a7bf83cc64a2d8bf17f7afb","schema_version":"1.0","event_id":"sha256:c928224ff8713203c58017445f159158ce0ac9896a7bf83cc64a2d8bf17f7afb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MWBASENHYJET6BYV4VJVHXWVQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Very Small Parallel Corpora Using Cross-Lingual Word Embeddings and a Monogamy Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Roth, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Nina Poerner","submitted_at":"2018-10-31T18:58:22Z","abstract_excerpt":"Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora. We therefore present an alternative approach based on cross-lingual word embeddings (CLWEs), which are trained on purely monolingual data. Our main contribution is an unsupervised objective to adapt CLWEs to parallel corpora. In experiments on between 25 and 500 sentences, our method outperforms fast-align. We also show that our fine-tuning objective consistently improves a CLWE-only baseline."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00066","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":"2026-05-18T00:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOhI6egg9/h3A0pElhMGhu4eZmEO6zL7sSq2Ymiind18hQn5900lbqgZT6ng1+uh8EKWF/PYcsksNQyBRsYrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:23:22.240742Z"},"content_sha256":"792be76bc2e21a6c27bc5aa44692c7bd6699420a80775e24dcaab0c6a2fb6b36","schema_version":"1.0","event_id":"sha256:792be76bc2e21a6c27bc5aa44692c7bd6699420a80775e24dcaab0c6a2fb6b36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWBASENHYJET6BYV4VJVHXWVQT/bundle.json","state_url":"https://pith.science/pith/MWBASENHYJET6BYV4VJVHXWVQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWBASENHYJET6BYV4VJVHXWVQT/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":"2026-06-06T19:23:22Z","links":{"resolver":"https://pith.science/pith/MWBASENHYJET6BYV4VJVHXWVQT","bundle":"https://pith.science/pith/MWBASENHYJET6BYV4VJVHXWVQT/bundle.json","state":"https://pith.science/pith/MWBASENHYJET6BYV4VJVHXWVQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWBASENHYJET6BYV4VJVHXWVQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MWBASENHYJET6BYV4VJVHXWVQT","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":"4071068bda04582fb2057f78f4f34fa244206f385d7bfdcbffd60e74b283839f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-31T18:58:22Z","title_canon_sha256":"768151412cbe52ed0b145b0901658a3d4f5853415f79c155bf1891179e13d0a5"},"schema_version":"1.0","source":{"id":"1811.00066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00066","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00066v1","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00066","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"MWBASENHYJET","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MWBASENHYJET6BYV","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MWBASENH","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:792be76bc2e21a6c27bc5aa44692c7bd6699420a80775e24dcaab0c6a2fb6b36","target":"graph","created_at":"2026-05-18T00:01:48Z","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":"Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora. We therefore present an alternative approach based on cross-lingual word embeddings (CLWEs), which are trained on purely monolingual data. Our main contribution is an unsupervised objective to adapt CLWEs to parallel corpora. In experiments on between 25 and 500 sentences, our method outperforms fast-align. We also show that our fine-tuning objective consistently improves a CLWE-only baseline.","authors_text":"Benjamin Roth, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Nina Poerner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-31T18:58:22Z","title":"Aligning Very Small Parallel Corpora Using Cross-Lingual Word Embeddings and a Monogamy Objective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00066","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:c928224ff8713203c58017445f159158ce0ac9896a7bf83cc64a2d8bf17f7afb","target":"record","created_at":"2026-05-18T00:01:48Z","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":"4071068bda04582fb2057f78f4f34fa244206f385d7bfdcbffd60e74b283839f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-31T18:58:22Z","title_canon_sha256":"768151412cbe52ed0b145b0901658a3d4f5853415f79c155bf1891179e13d0a5"},"schema_version":"1.0","source":{"id":"1811.00066","kind":"arxiv","version":1}},"canonical_sha256":"65820911a7c2493f0715e55353ded584f007d41ba36cd48e2cc46e584e2bb0a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65820911a7c2493f0715e55353ded584f007d41ba36cd48e2cc46e584e2bb0a8","first_computed_at":"2026-05-18T00:01:48.349771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:48.349771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6SdUulFDjQ8W6sifJbF78Q15lmLtRyfpiv9idksYnb4/wiPAAI0dF0bFaAaxcH9fl9C5P87fBG/FjpZuB05DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:48.350274Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c928224ff8713203c58017445f159158ce0ac9896a7bf83cc64a2d8bf17f7afb","sha256:792be76bc2e21a6c27bc5aa44692c7bd6699420a80775e24dcaab0c6a2fb6b36"],"state_sha256":"77c76016d40d89c261497f075ccd671c16de372904e93c6630e25420a7adfe0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dT+Foec/lx+H4P8t1xwBAjEa0cFQP+2FSH32QnhE0uG4iWWe+G3uU3u7XeH0/Gm1DXpXzyGXyKI6QeIXUjx6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:23:22.244088Z","bundle_sha256":"4031353a7d4fc0e8b86cbd0510a4e5cb62d69fd9361c135eb1985f2fdad69d38"}}