{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RP7QJUSDSSVB6HYCACCQ2RBZX2","short_pith_number":"pith:RP7QJUSD","canonical_record":{"source":{"id":"2505.23146","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T06:37:02Z","cross_cats_sorted":[],"title_canon_sha256":"d32a1010f5306df5ecb8c449a4df176d0733502ad7d130037e859eb252e186c1","abstract_canon_sha256":"cd8e3579feab512312276a223377d1271d084120eacf8aa3830171847b383384"},"schema_version":"1.0"},"canonical_sha256":"8bff04d24394aa1f1f0200850d4439be961c3f14cf88b956de0675d0f55a80fa","source":{"kind":"arxiv","id":"2505.23146","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23146","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23146v1","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23146","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"RP7QJUSDSSVB","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"RP7QJUSDSSVB6HYC","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"RP7QJUSD","created_at":"2026-07-05T11:11:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RP7QJUSDSSVB6HYCACCQ2RBZX2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23146","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T06:37:02Z","cross_cats_sorted":[],"title_canon_sha256":"d32a1010f5306df5ecb8c449a4df176d0733502ad7d130037e859eb252e186c1","abstract_canon_sha256":"cd8e3579feab512312276a223377d1271d084120eacf8aa3830171847b383384"},"schema_version":"1.0"},"canonical_sha256":"8bff04d24394aa1f1f0200850d4439be961c3f14cf88b956de0675d0f55a80fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:56.267206Z","signature_b64":"uP4Qn05q60zrZxDi29FGfgrq3dfhbToCKtIBlOgD9nEly3rK5zskL/kajooL7lY59NCfV2QgUn4GgyMExu3nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bff04d24394aa1f1f0200850d4439be961c3f14cf88b956de0675d0f55a80fa","last_reissued_at":"2026-07-05T11:11:56.266507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:56.266507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23146","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":"2026-07-05T11:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvB2pf3yaAEJ6QBueFo8sZYotFdMSy3jyw6vEOtyGwfJuOKFavpg+VzxIvUaUHAxi9fEzXC/4M1OQH6yevGkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:06:13.043387Z"},"content_sha256":"9c8e0efbe6ccda7f23e955babe3d818aaa89d4c0ce311bd293ecf691c7a3ba2a","schema_version":"1.0","event_id":"sha256:9c8e0efbe6ccda7f23e955babe3d818aaa89d4c0ce311bd293ecf691c7a3ba2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RP7QJUSDSSVB6HYCACCQ2RBZX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Domain Bilingual Lexicon Induction via Pretrained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hailong Cao, Qiuyu Ding, Tiejun Zhao, Zhiqiang Cao","submitted_at":"2025-05-29T06:37:02Z","abstract_excerpt":"Bilingual Lexicon Induction (BLI) is generally based on common domain data to obtain monolingual word embedding, and by aligning the monolingual word embeddings to obtain the cross-lingual embeddings which are used to get the word translation pairs. In this paper, we propose a new task of BLI, which is to use the monolingual corpus of the general domain and target domain to extract domain-specific bilingual dictionaries. Motivated by the ability of Pre-trained models, we propose a method to get better word embeddings that build on the recent work on BLI. This way, we introduce the Code Switch("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23146","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/2505.23146/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":"2026-07-05T11:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RhohCY7xCTfksfxEY3VZneIROZKtxHw0FDFDFpBp2CpvQISDYp6TkZeU8OzD8JlaGlKeK4Iqi8dtx+IPzXeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:06:13.044214Z"},"content_sha256":"25cf6837228178a2c0ce65e77aa89069f0899dd9d85eb8d6755576c7a358dfd7","schema_version":"1.0","event_id":"sha256:25cf6837228178a2c0ce65e77aa89069f0899dd9d85eb8d6755576c7a358dfd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2/bundle.json","state_url":"https://pith.science/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2/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":"2026-08-08T03:06:13Z","links":{"resolver":"https://pith.science/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2","bundle":"https://pith.science/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2/bundle.json","state":"https://pith.science/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RP7QJUSDSSVB6HYCACCQ2RBZX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RP7QJUSDSSVB6HYCACCQ2RBZX2","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":"cd8e3579feab512312276a223377d1271d084120eacf8aa3830171847b383384","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T06:37:02Z","title_canon_sha256":"d32a1010f5306df5ecb8c449a4df176d0733502ad7d130037e859eb252e186c1"},"schema_version":"1.0","source":{"id":"2505.23146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23146","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23146v1","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23146","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"RP7QJUSDSSVB","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"RP7QJUSDSSVB6HYC","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"RP7QJUSD","created_at":"2026-07-05T11:11:56Z"}],"graph_snapshots":[{"event_id":"sha256:25cf6837228178a2c0ce65e77aa89069f0899dd9d85eb8d6755576c7a358dfd7","target":"graph","created_at":"2026-07-05T11:11:56Z","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/2505.23146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bilingual Lexicon Induction (BLI) is generally based on common domain data to obtain monolingual word embedding, and by aligning the monolingual word embeddings to obtain the cross-lingual embeddings which are used to get the word translation pairs. In this paper, we propose a new task of BLI, which is to use the monolingual corpus of the general domain and target domain to extract domain-specific bilingual dictionaries. Motivated by the ability of Pre-trained models, we propose a method to get better word embeddings that build on the recent work on BLI. This way, we introduce the Code Switch(","authors_text":"Hailong Cao, Qiuyu Ding, Tiejun Zhao, Zhiqiang Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T06:37:02Z","title":"Cross-Domain Bilingual Lexicon Induction via Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23146","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":"sha256:9c8e0efbe6ccda7f23e955babe3d818aaa89d4c0ce311bd293ecf691c7a3ba2a","target":"record","created_at":"2026-07-05T11:11:56Z","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":"cd8e3579feab512312276a223377d1271d084120eacf8aa3830171847b383384","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T06:37:02Z","title_canon_sha256":"d32a1010f5306df5ecb8c449a4df176d0733502ad7d130037e859eb252e186c1"},"schema_version":"1.0","source":{"id":"2505.23146","kind":"arxiv","version":1}},"canonical_sha256":"8bff04d24394aa1f1f0200850d4439be961c3f14cf88b956de0675d0f55a80fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bff04d24394aa1f1f0200850d4439be961c3f14cf88b956de0675d0f55a80fa","first_computed_at":"2026-07-05T11:11:56.266507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:56.266507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uP4Qn05q60zrZxDi29FGfgrq3dfhbToCKtIBlOgD9nEly3rK5zskL/kajooL7lY59NCfV2QgUn4GgyMExu3nCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:56.267206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c8e0efbe6ccda7f23e955babe3d818aaa89d4c0ce311bd293ecf691c7a3ba2a","sha256:25cf6837228178a2c0ce65e77aa89069f0899dd9d85eb8d6755576c7a358dfd7"],"state_sha256":"ba75e5924005aa428c8686f2c282b1b23c837d0ec31e46c1f5ac826ee0bde171"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuhdW7E3JqicjScF+Y6No11W2w/CDcIkfj+CkILvZsQbyC0uY4PUitLZ9l/V3mtpyPDLIKeOr/ACpqNsFVLeCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:06:13.050052Z","bundle_sha256":"e69799db73fab359353a1b8c20bb9d831e49a52bfe00886e9f8d44862a98ebe6"}}