{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UVVD2JRF7J4LQRKLINQAWZOPTQ","short_pith_number":"pith:UVVD2JRF","canonical_record":{"source":{"id":"2301.12140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-28T09:28:55Z","cross_cats_sorted":[],"title_canon_sha256":"ed513f6e21688bf9b99a1ee1b2161bbca7768627ba7e26199a6766b2fecda111","abstract_canon_sha256":"f4f62233ee5166f1b41facf6b5ed99714774a75c503e0686f0aab7f66b3c237a"},"schema_version":"1.0"},"canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","source":{"kind":"arxiv","id":"2301.12140","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12140","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12140v1","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12140","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"pith_short_12","alias_value":"UVVD2JRF7J4L","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"pith_short_16","alias_value":"UVVD2JRF7J4LQRKL","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"pith_short_8","alias_value":"UVVD2JRF","created_at":"2026-07-05T05:36:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UVVD2JRF7J4LQRKLINQAWZOPTQ","target":"record","payload":{"canonical_record":{"source":{"id":"2301.12140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-28T09:28:55Z","cross_cats_sorted":[],"title_canon_sha256":"ed513f6e21688bf9b99a1ee1b2161bbca7768627ba7e26199a6766b2fecda111","abstract_canon_sha256":"f4f62233ee5166f1b41facf6b5ed99714774a75c503e0686f0aab7f66b3c237a"},"schema_version":"1.0"},"canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:35.728066Z","signature_b64":"CXxiMYt2xo6K0lnfNLD7TboJOkXVNg0CIkmbHGbLkj4AFm4hhI2JRJYRNwZmbqqwcOZpfEWJ9E5Vt8tVIp7tCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","last_reissued_at":"2026-07-05T05:36:35.727595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:35.727595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.12140","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":"2026-07-05T05:36:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JFaZuj3sesOQdVnYmoHI8Ndoum8yAlhTqcycgD7AEPLuY8i/6KjEo1QB4NenXAkJ8efFTE9o++sMJMqDzptUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:50:53.761362Z"},"content_sha256":"623deeaa41f1d22f761138edeb1203d79ffbfd8f4016d5bbbefaf12edff5633d","schema_version":"1.0","event_id":"sha256:623deeaa41f1d22f761138edeb1203d79ffbfd8f4016d5bbbefaf12edff5633d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UVVD2JRF7J4LQRKLINQAWZOPTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Sentence Transformer as A Multilingual Word Aligner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanhua Chen, Hanqing Wang, Weikang Wang, Yue Han, Yun Chen","submitted_at":"2023-01-28T09:28:55Z","abstract_excerpt":"Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner. This idea is non-trivial as LaBSE is trained to learn language-agnostic sentence-level embeddings, while the alignment extraction task requires the more fine-grained word-level embeddings to be language-agnostic. We demonstrate that the vanilla LaBSE outperforms other mPLMs currently used in the alignme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12140","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/2301.12140/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":"2026-07-05T05:36:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MTmGaYis+XYQUSODAU31JohC8eef6xRDqIy75WsmLMMx4+n6QRN4QaIqyiNU8IXXjsbNLE9FKLT4vxKtUWkCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:50:53.761873Z"},"content_sha256":"78ee6bf7fa166bd4a4551330b639a9aa876700bcf5193fd5e2a66c5915078a6c","schema_version":"1.0","event_id":"sha256:78ee6bf7fa166bd4a4551330b639a9aa876700bcf5193fd5e2a66c5915078a6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/bundle.json","state_url":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/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":"2026-08-07T21:50:53Z","links":{"resolver":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ","bundle":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/bundle.json","state":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UVVD2JRF7J4LQRKLINQAWZOPTQ","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":"f4f62233ee5166f1b41facf6b5ed99714774a75c503e0686f0aab7f66b3c237a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-28T09:28:55Z","title_canon_sha256":"ed513f6e21688bf9b99a1ee1b2161bbca7768627ba7e26199a6766b2fecda111"},"schema_version":"1.0","source":{"id":"2301.12140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12140","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12140v1","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12140","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"pith_short_12","alias_value":"UVVD2JRF7J4L","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"pith_short_16","alias_value":"UVVD2JRF7J4LQRKL","created_at":"2026-07-05T05:36:35Z"},{"alias_kind":"pith_short_8","alias_value":"UVVD2JRF","created_at":"2026-07-05T05:36:35Z"}],"graph_snapshots":[{"event_id":"sha256:78ee6bf7fa166bd4a4551330b639a9aa876700bcf5193fd5e2a66c5915078a6c","target":"graph","created_at":"2026-07-05T05:36:35Z","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/2301.12140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner. This idea is non-trivial as LaBSE is trained to learn language-agnostic sentence-level embeddings, while the alignment extraction task requires the more fine-grained word-level embeddings to be language-agnostic. We demonstrate that the vanilla LaBSE outperforms other mPLMs currently used in the alignme","authors_text":"Guanhua Chen, Hanqing Wang, Weikang Wang, Yue Han, Yun Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-28T09:28:55Z","title":"Multilingual Sentence Transformer as A Multilingual Word Aligner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12140","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":"sha256:623deeaa41f1d22f761138edeb1203d79ffbfd8f4016d5bbbefaf12edff5633d","target":"record","created_at":"2026-07-05T05:36:35Z","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":"f4f62233ee5166f1b41facf6b5ed99714774a75c503e0686f0aab7f66b3c237a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-28T09:28:55Z","title_canon_sha256":"ed513f6e21688bf9b99a1ee1b2161bbca7768627ba7e26199a6766b2fecda111"},"schema_version":"1.0","source":{"id":"2301.12140","kind":"arxiv","version":1}},"canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","first_computed_at":"2026-07-05T05:36:35.727595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:35.727595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CXxiMYt2xo6K0lnfNLD7TboJOkXVNg0CIkmbHGbLkj4AFm4hhI2JRJYRNwZmbqqwcOZpfEWJ9E5Vt8tVIp7tCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:35.728066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:623deeaa41f1d22f761138edeb1203d79ffbfd8f4016d5bbbefaf12edff5633d","sha256:78ee6bf7fa166bd4a4551330b639a9aa876700bcf5193fd5e2a66c5915078a6c"],"state_sha256":"16aaafc226c5628774b0265f6e79cb85c077d9b98073577d5697e7cda591ef73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M1FjOPMBKHVy1+Zj2vom5/c/D+Tk5TlkfW3+U66hjuPbXnuljVQnyiCJNyVza8wpxWMlh5rXa3JZeOYq8ERVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:50:53.766307Z","bundle_sha256":"f8dafdc2811c5d7acabb28bb0d8742b668366f64a3ddd5789f0f0e622bb3f4c0"}}