{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SI7FP6PPBM24TXBJJDVLCOHKTT","short_pith_number":"pith:SI7FP6PP","canonical_record":{"source":{"id":"2406.01441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T15:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"04847e17a86d1330aeef0b38f0c65e006c3ac1503e6338ec04164ea7e80e8d7b","abstract_canon_sha256":"e7658881df7e247fd04681012e1eece04039f4cc5742f496ac6cf3ee3ab3701b"},"schema_version":"1.0"},"canonical_sha256":"923e57f9ef0b35c9dc2948eab138ea9ccd3a91ac4624d0af3f2cd51450acf55b","source":{"kind":"arxiv","id":"2406.01441","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01441","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01441v2","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01441","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"pith_short_12","alias_value":"SI7FP6PPBM24","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"pith_short_16","alias_value":"SI7FP6PPBM24TXBJ","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"pith_short_8","alias_value":"SI7FP6PP","created_at":"2026-07-05T09:25:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SI7FP6PPBM24TXBJJDVLCOHKTT","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T15:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"04847e17a86d1330aeef0b38f0c65e006c3ac1503e6338ec04164ea7e80e8d7b","abstract_canon_sha256":"e7658881df7e247fd04681012e1eece04039f4cc5742f496ac6cf3ee3ab3701b"},"schema_version":"1.0"},"canonical_sha256":"923e57f9ef0b35c9dc2948eab138ea9ccd3a91ac4624d0af3f2cd51450acf55b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:43.831191Z","signature_b64":"bD/x/aTrBjAjQPw/20fqOLQEncXCC1gpcfE8LySLzzJeO8tEJmmb6wiwQpC+zLer98bO4QqZL2ClCaPxwCeKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"923e57f9ef0b35c9dc2948eab138ea9ccd3a91ac4624d0af3f2cd51450acf55b","last_reissued_at":"2026-07-05T09:25:43.830707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:43.830707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01441","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:25:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmCd3rIu/OKCh091ajNjvlxA073DxArBS5kmylm96UHhz2t0YkKBV/py472v63avEBrWHgLHbq6DC6e+ee9+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:08:16.122442Z"},"content_sha256":"4f0e332b18e05925a304271546fa70688934e99518538b1b59c45be11558c561","schema_version":"1.0","event_id":"sha256:4f0e332b18e05925a304271546fa70688934e99518538b1b59c45be11558c561"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SI7FP6PPBM24TXBJJDVLCOHKTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jiali Zeng, Yafu Li, Yongjing Yin, Yue Zhang","submitted_at":"2024-06-03T15:30:36Z","abstract_excerpt":"The fine-tuning of open-source large language models (LLMs) for machine translation has recently received considerable attention, marking a shift towards data-centric research from traditional neural machine translation. However, the area of data collection for instruction fine-tuning in machine translation remains relatively underexplored. In this paper, we present LexMatcher, a simple yet effective method for data curation, the design of which is driven by the coverage of senses found in bilingual dictionaries. The construction process comprises data retrieval from an existing corpus and dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01441","kind":"arxiv","version":2},"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/2406.01441/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":"2026-07-05T09:25:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hl5Kc7W2paT4sP/DZNNvfE02uHJEJdr+wKs4x0WJFYgEGAsjKCDZzdCi/0vn3irSDoI9cWzV8+/VISVsTJMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:08:16.123023Z"},"content_sha256":"a06e39286f439f2131b5829e62bcddb3ebc152ae036553209c453c5bcca36842","schema_version":"1.0","event_id":"sha256:a06e39286f439f2131b5829e62bcddb3ebc152ae036553209c453c5bcca36842"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SI7FP6PPBM24TXBJJDVLCOHKTT/bundle.json","state_url":"https://pith.science/pith/SI7FP6PPBM24TXBJJDVLCOHKTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SI7FP6PPBM24TXBJJDVLCOHKTT/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":"2026-08-06T21:08:16Z","links":{"resolver":"https://pith.science/pith/SI7FP6PPBM24TXBJJDVLCOHKTT","bundle":"https://pith.science/pith/SI7FP6PPBM24TXBJJDVLCOHKTT/bundle.json","state":"https://pith.science/pith/SI7FP6PPBM24TXBJJDVLCOHKTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SI7FP6PPBM24TXBJJDVLCOHKTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SI7FP6PPBM24TXBJJDVLCOHKTT","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":"e7658881df7e247fd04681012e1eece04039f4cc5742f496ac6cf3ee3ab3701b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T15:30:36Z","title_canon_sha256":"04847e17a86d1330aeef0b38f0c65e006c3ac1503e6338ec04164ea7e80e8d7b"},"schema_version":"1.0","source":{"id":"2406.01441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01441","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01441v2","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01441","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"pith_short_12","alias_value":"SI7FP6PPBM24","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"pith_short_16","alias_value":"SI7FP6PPBM24TXBJ","created_at":"2026-07-05T09:25:43Z"},{"alias_kind":"pith_short_8","alias_value":"SI7FP6PP","created_at":"2026-07-05T09:25:43Z"}],"graph_snapshots":[{"event_id":"sha256:a06e39286f439f2131b5829e62bcddb3ebc152ae036553209c453c5bcca36842","target":"graph","created_at":"2026-07-05T09:25:43Z","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/2406.01441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The fine-tuning of open-source large language models (LLMs) for machine translation has recently received considerable attention, marking a shift towards data-centric research from traditional neural machine translation. However, the area of data collection for instruction fine-tuning in machine translation remains relatively underexplored. In this paper, we present LexMatcher, a simple yet effective method for data curation, the design of which is driven by the coverage of senses found in bilingual dictionaries. The construction process comprises data retrieval from an existing corpus and dat","authors_text":"Fandong Meng, Jiali Zeng, Yafu Li, Yongjing Yin, Yue Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T15:30:36Z","title":"LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01441","kind":"arxiv","version":2},"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":"sha256:4f0e332b18e05925a304271546fa70688934e99518538b1b59c45be11558c561","target":"record","created_at":"2026-07-05T09:25:43Z","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":"e7658881df7e247fd04681012e1eece04039f4cc5742f496ac6cf3ee3ab3701b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T15:30:36Z","title_canon_sha256":"04847e17a86d1330aeef0b38f0c65e006c3ac1503e6338ec04164ea7e80e8d7b"},"schema_version":"1.0","source":{"id":"2406.01441","kind":"arxiv","version":2}},"canonical_sha256":"923e57f9ef0b35c9dc2948eab138ea9ccd3a91ac4624d0af3f2cd51450acf55b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"923e57f9ef0b35c9dc2948eab138ea9ccd3a91ac4624d0af3f2cd51450acf55b","first_computed_at":"2026-07-05T09:25:43.830707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:43.830707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bD/x/aTrBjAjQPw/20fqOLQEncXCC1gpcfE8LySLzzJeO8tEJmmb6wiwQpC+zLer98bO4QqZL2ClCaPxwCeKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:43.831191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f0e332b18e05925a304271546fa70688934e99518538b1b59c45be11558c561","sha256:a06e39286f439f2131b5829e62bcddb3ebc152ae036553209c453c5bcca36842"],"state_sha256":"b2dd073a3ef21ab7627dff69a8dde71ff40d77d073c59c6a2b1e6ac7c758ac2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDj4bJH5tgbumEXFrD98hBHl3LVFSw0zAvNLYTgpsSaNmlCriLij1PFF81L6yry2uj/rvUJZLYjVoDo6pXSiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:08:16.128185Z","bundle_sha256":"274f2a19b2c8f234d745a055c9fcb1bf4b86dd5eb9244d93cb052ea14ac24e04"}}