{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EGDMNPDCQO4Z3PRHYL4OA7FEPM","short_pith_number":"pith:EGDMNPDC","schema_version":"1.0","canonical_sha256":"2186c6bc6283b99dbe27c2f8e07ca47b2a88a3a6166315644889287e1f6bc9d7","source":{"kind":"arxiv","id":"2309.10539","version":1},"attestation_state":"computed","paper":{"title":"OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dana Alon, Don Metzler, Ivan Korotkov, Ji Ma, Keith Hall, Yang Gao","submitted_at":"2023-09-19T11:38:39Z","abstract_excerpt":"We develop and evaluate multilingual scientific documents similarity measurement models in this work. Such models can be used to find related works in different languages, which can help multilingual researchers find and explore papers more efficiently. We propose the first multilingual scientific documents dataset, Open-access Multilingual Scientific Documents (OpenMSD), which has 74M papers in 103 languages and 778M citation pairs. With OpenMSD, we pretrain science-specialized language models, and explore different strategies to derive \"related\" paper pairs to fine-tune the models, including"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.10539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T11:38:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84f7fde76ed424173f941f4fffbb88b395f57ef618067f4e49e95dae82fc7a13","abstract_canon_sha256":"bcfdc7a8ab48da57c0eb2f4bd447437d8396069dae8bc01aaf2dfca62da7533d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:13.533164Z","signature_b64":"dtw2JLrphC85h9dbNirfB3G/STBrfQ5w4tKQ4bRwYtV40MbqxOur2sOACXcZlBZX5QDLTmYKIqymY8dgnN7WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2186c6bc6283b99dbe27c2f8e07ca47b2a88a3a6166315644889287e1f6bc9d7","last_reissued_at":"2026-07-05T06:52:13.532744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:13.532744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dana Alon, Don Metzler, Ivan Korotkov, Ji Ma, Keith Hall, Yang Gao","submitted_at":"2023-09-19T11:38:39Z","abstract_excerpt":"We develop and evaluate multilingual scientific documents similarity measurement models in this work. Such models can be used to find related works in different languages, which can help multilingual researchers find and explore papers more efficiently. We propose the first multilingual scientific documents dataset, Open-access Multilingual Scientific Documents (OpenMSD), which has 74M papers in 103 languages and 778M citation pairs. With OpenMSD, we pretrain science-specialized language models, and explore different strategies to derive \"related\" paper pairs to fine-tune the models, including"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10539","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/2309.10539/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.10539","created_at":"2026-07-05T06:52:13.532802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10539v1","created_at":"2026-07-05T06:52:13.532802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10539","created_at":"2026-07-05T06:52:13.532802+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGDMNPDCQO4Z","created_at":"2026-07-05T06:52:13.532802+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGDMNPDCQO4Z3PRH","created_at":"2026-07-05T06:52:13.532802+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGDMNPDC","created_at":"2026-07-05T06:52:13.532802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM","json":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM.json","graph_json":"https://pith.science/api/pith-number/EGDMNPDCQO4Z3PRHYL4OA7FEPM/graph.json","events_json":"https://pith.science/api/pith-number/EGDMNPDCQO4Z3PRHYL4OA7FEPM/events.json","paper":"https://pith.science/paper/EGDMNPDC"},"agent_actions":{"view_html":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM","download_json":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM.json","view_paper":"https://pith.science/paper/EGDMNPDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10539&json=true","fetch_graph":"https://pith.science/api/pith-number/EGDMNPDCQO4Z3PRHYL4OA7FEPM/graph.json","fetch_events":"https://pith.science/api/pith-number/EGDMNPDCQO4Z3PRHYL4OA7FEPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM/action/storage_attestation","attest_author":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM/action/author_attestation","sign_citation":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM/action/citation_signature","submit_replication":"https://pith.science/pith/EGDMNPDCQO4Z3PRHYL4OA7FEPM/action/replication_record"}},"created_at":"2026-07-05T06:52:13.532802+00:00","updated_at":"2026-07-05T06:52:13.532802+00:00"}