{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MMMN62J6GXRARUV6N53JR5YIVV","short_pith_number":"pith:MMMN62J6","canonical_record":{"source":{"id":"2512.11388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-12T08:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"6c606425dd6c7c9a91ec506fb8d5196ba05591c9fb9ea0f30f75c0e1c0439da3","abstract_canon_sha256":"6bcaaf7ba0f5c7661cb87928e1d305033cda6acc8c4a1c80c527a6ed1536780b"},"schema_version":"1.0"},"canonical_sha256":"6318df693e35e208d2be6f7698f708ad7bebdcae1944f389ad2a7e2d8eff69ba","source":{"kind":"arxiv","id":"2512.11388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.11388","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"arxiv_version","alias_value":"2512.11388v1","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11388","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"pith_short_12","alias_value":"MMMN62J6GXRA","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"pith_short_16","alias_value":"MMMN62J6GXRARUV6","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"pith_short_8","alias_value":"MMMN62J6","created_at":"2026-07-07T02:19:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MMMN62J6GXRARUV6N53JR5YIVV","target":"record","payload":{"canonical_record":{"source":{"id":"2512.11388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-12T08:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"6c606425dd6c7c9a91ec506fb8d5196ba05591c9fb9ea0f30f75c0e1c0439da3","abstract_canon_sha256":"6bcaaf7ba0f5c7661cb87928e1d305033cda6acc8c4a1c80c527a6ed1536780b"},"schema_version":"1.0"},"canonical_sha256":"6318df693e35e208d2be6f7698f708ad7bebdcae1944f389ad2a7e2d8eff69ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:43.620247Z","signature_b64":"/GsC2exDJuRmoQqPsCgV0ch3hDA524g8N8LOdmG2HqgF5KN+4lJOqiNJiYdClblF7IAzNOURa+IoELxEUJDsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6318df693e35e208d2be6f7698f708ad7bebdcae1944f389ad2a7e2d8eff69ba","last_reissued_at":"2026-07-07T02:19:43.619362Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:43.619362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.11388","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":"2026-07-07T02:19:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaPa4ZmTHg4bDgeGets+8G0bRzgGqxwJny9n2KjtmPE6F3niQ69V8+8WF9qzeo0el2du9lzXhAeZT4xWbLFDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:05:16.820935Z"},"content_sha256":"ffa4e4a8b9d893e39ab35bfe593ca30d9468956b7d075ef0426b7df18e3638f4","schema_version":"1.0","event_id":"sha256:ffa4e4a8b9d893e39ab35bfe593ca30d9468956b7d075ef0426b7df18e3638f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MMMN62J6GXRARUV6N53JR5YIVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felipe Ribeiro Fujita de Mello, Hideyuki Takada","submitted_at":"2025-12-12T08:59:27Z","abstract_excerpt":"We investigated the impact of data selection on machine translation fine-tuning for open LLMs. Using Japanese-English corpora, we compare five selectors: TF-IDF, COMET Kiwi, QuRate, FD-Score, and random selection, under controlled training conditions. We observed that semantic selectors consistently outperform lexical and geometry-based heuristics, and that even when the selected data differ by less than 3%, the impact on model performance is substantial, underscoring the sensitivity of fine-tuning to data quality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11388","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/2512.11388/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":"2026-07-07T02:19:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQQMsPmdY8agMWK7cBSE7w45aN0HbdGzB3dUCnvublDpsy+Rjtbb46Lie8WOXMhAIADBoUYMSalu5c/Ns2n9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:05:16.821729Z"},"content_sha256":"9ec145961f1abaecd2b3755d1fdcc6e8ff8c326046fee0913173e27dbf3743a4","schema_version":"1.0","event_id":"sha256:9ec145961f1abaecd2b3755d1fdcc6e8ff8c326046fee0913173e27dbf3743a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMMN62J6GXRARUV6N53JR5YIVV/bundle.json","state_url":"https://pith.science/pith/MMMN62J6GXRARUV6N53JR5YIVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMMN62J6GXRARUV6N53JR5YIVV/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":"2026-08-04T15:05:16Z","links":{"resolver":"https://pith.science/pith/MMMN62J6GXRARUV6N53JR5YIVV","bundle":"https://pith.science/pith/MMMN62J6GXRARUV6N53JR5YIVV/bundle.json","state":"https://pith.science/pith/MMMN62J6GXRARUV6N53JR5YIVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMMN62J6GXRARUV6N53JR5YIVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MMMN62J6GXRARUV6N53JR5YIVV","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":"6bcaaf7ba0f5c7661cb87928e1d305033cda6acc8c4a1c80c527a6ed1536780b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-12T08:59:27Z","title_canon_sha256":"6c606425dd6c7c9a91ec506fb8d5196ba05591c9fb9ea0f30f75c0e1c0439da3"},"schema_version":"1.0","source":{"id":"2512.11388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.11388","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"arxiv_version","alias_value":"2512.11388v1","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11388","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"pith_short_12","alias_value":"MMMN62J6GXRA","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"pith_short_16","alias_value":"MMMN62J6GXRARUV6","created_at":"2026-07-07T02:19:43Z"},{"alias_kind":"pith_short_8","alias_value":"MMMN62J6","created_at":"2026-07-07T02:19:43Z"}],"graph_snapshots":[{"event_id":"sha256:9ec145961f1abaecd2b3755d1fdcc6e8ff8c326046fee0913173e27dbf3743a4","target":"graph","created_at":"2026-07-07T02:19:43Z","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/2512.11388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigated the impact of data selection on machine translation fine-tuning for open LLMs. Using Japanese-English corpora, we compare five selectors: TF-IDF, COMET Kiwi, QuRate, FD-Score, and random selection, under controlled training conditions. We observed that semantic selectors consistently outperform lexical and geometry-based heuristics, and that even when the selected data differ by less than 3%, the impact on model performance is substantial, underscoring the sensitivity of fine-tuning to data quality.","authors_text":"Felipe Ribeiro Fujita de Mello, Hideyuki Takada","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-12T08:59:27Z","title":"Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11388","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:ffa4e4a8b9d893e39ab35bfe593ca30d9468956b7d075ef0426b7df18e3638f4","target":"record","created_at":"2026-07-07T02:19:43Z","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":"6bcaaf7ba0f5c7661cb87928e1d305033cda6acc8c4a1c80c527a6ed1536780b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-12T08:59:27Z","title_canon_sha256":"6c606425dd6c7c9a91ec506fb8d5196ba05591c9fb9ea0f30f75c0e1c0439da3"},"schema_version":"1.0","source":{"id":"2512.11388","kind":"arxiv","version":1}},"canonical_sha256":"6318df693e35e208d2be6f7698f708ad7bebdcae1944f389ad2a7e2d8eff69ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6318df693e35e208d2be6f7698f708ad7bebdcae1944f389ad2a7e2d8eff69ba","first_computed_at":"2026-07-07T02:19:43.619362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:43.619362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/GsC2exDJuRmoQqPsCgV0ch3hDA524g8N8LOdmG2HqgF5KN+4lJOqiNJiYdClblF7IAzNOURa+IoELxEUJDsBQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:43.620247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.11388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffa4e4a8b9d893e39ab35bfe593ca30d9468956b7d075ef0426b7df18e3638f4","sha256:9ec145961f1abaecd2b3755d1fdcc6e8ff8c326046fee0913173e27dbf3743a4"],"state_sha256":"9f867be29bbc312cd944d0ac929037795bbec2dc52bfb41e2e1c5077a935feae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F4y9VXE7+WDaydo2OJ8qfcU56tkpmblSr6TfRPKG/K4/2hboZPL0nwKad/g0E3OK47wBG2lTocH29F1kaxhAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:05:16.827970Z","bundle_sha256":"4fd7965fd219ef527ecb033a49e5a19da31dea36b4478e01ba3270632639d376"}}