{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DRHHEUUFCOBZGHEYE5YAQOFJLT","short_pith_number":"pith:DRHHEUUF","canonical_record":{"source":{"id":"2502.12001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T16:39:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fd56b6aadc420bbcd48018f70ed32deabaea947b99cd562f85a895952d77f3d","abstract_canon_sha256":"0780410da4edc8d6b9247861d657fe7ee20400ac70d9740eddf1a00dbe0ed51e"},"schema_version":"1.0"},"canonical_sha256":"1c4e7252851383931c9827700838a95cd3b86a32c1a4779144561872c869fdfa","source":{"kind":"arxiv","id":"2502.12001","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12001","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12001v2","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12001","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_12","alias_value":"DRHHEUUFCOBZ","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"DRHHEUUFCOBZGHEY","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"DRHHEUUF","created_at":"2026-07-05T10:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DRHHEUUFCOBZGHEYE5YAQOFJLT","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T16:39:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fd56b6aadc420bbcd48018f70ed32deabaea947b99cd562f85a895952d77f3d","abstract_canon_sha256":"0780410da4edc8d6b9247861d657fe7ee20400ac70d9740eddf1a00dbe0ed51e"},"schema_version":"1.0"},"canonical_sha256":"1c4e7252851383931c9827700838a95cd3b86a32c1a4779144561872c869fdfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:34.346975Z","signature_b64":"ruTFqmQg5OZ+VVItntbw6vaKobQuOPXwwwa3tHngKPdki/xaBtEZyLJrdAS+Q3RnpOyiESMePI+Di7vigLCjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c4e7252851383931c9827700838a95cd3b86a32c1a4779144561872c869fdfa","last_reissued_at":"2026-07-05T10:29:34.346459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:34.346459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12001","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":"2026-07-05T10:29:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/KDaLGhXElGPK2DqgK3H25+IVTHjsIayZVEFfoI+tuyX/dmcFm13w22zRLSDtIzoHHaguYjOpY++YgrO/SQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:57:44.188399Z"},"content_sha256":"56c8c429a9bf763c1cbfae4c2410ff7423f0d3fbfcaff3894a1ec17d58894283","schema_version":"1.0","event_id":"sha256:56c8c429a9bf763c1cbfae4c2410ff7423f0d3fbfcaff3894a1ec17d58894283"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DRHHEUUFCOBZGHEYE5YAQOFJLT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Merging Language and Domain Specific Models: The Impact on Technical Vocabulary Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Taisei Kakibuchi, Thibault Rousset, Yoshihide Nomura, Yusuke Sasaki","submitted_at":"2025-02-17T16:39:28Z","abstract_excerpt":"Advancements in Natural Language Processing have enabled specialized language models, but integrating domain-specific knowledge into general-purpose models in multilingual settings remains challenging, particularly for technical vocabulary. This paper investigates the integration of technical vocabulary in merged language models and explores the knowledge transfer mechanisms involved when combining a general-purpose language-specific model with a domain-specific model, focusing on the resulting model's comprehension of technical jargon. Our experiments analyze the impact of this merging proces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12001","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/2502.12001/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":"2026-07-05T10:29:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nyPgq729RLJ4b4zEJFUHvhODUhkCMRzfdK8Cd+xzjcwQts/MmqGd9osZzGpy7zE/6JkvJ58f/r7JaVWJEYGADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:57:44.188922Z"},"content_sha256":"d1fedd8db1bbaf2fd5a15ae647da0d5187a16e3804b5fa4da2f393167b27df7b","schema_version":"1.0","event_id":"sha256:d1fedd8db1bbaf2fd5a15ae647da0d5187a16e3804b5fa4da2f393167b27df7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT/bundle.json","state_url":"https://pith.science/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT/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":"2026-08-08T14:57:44Z","links":{"resolver":"https://pith.science/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT","bundle":"https://pith.science/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT/bundle.json","state":"https://pith.science/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DRHHEUUFCOBZGHEYE5YAQOFJLT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DRHHEUUFCOBZGHEYE5YAQOFJLT","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":"0780410da4edc8d6b9247861d657fe7ee20400ac70d9740eddf1a00dbe0ed51e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T16:39:28Z","title_canon_sha256":"6fd56b6aadc420bbcd48018f70ed32deabaea947b99cd562f85a895952d77f3d"},"schema_version":"1.0","source":{"id":"2502.12001","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12001","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12001v2","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12001","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_12","alias_value":"DRHHEUUFCOBZ","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"DRHHEUUFCOBZGHEY","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"DRHHEUUF","created_at":"2026-07-05T10:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:d1fedd8db1bbaf2fd5a15ae647da0d5187a16e3804b5fa4da2f393167b27df7b","target":"graph","created_at":"2026-07-05T10:29:34Z","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/2502.12001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advancements in Natural Language Processing have enabled specialized language models, but integrating domain-specific knowledge into general-purpose models in multilingual settings remains challenging, particularly for technical vocabulary. This paper investigates the integration of technical vocabulary in merged language models and explores the knowledge transfer mechanisms involved when combining a general-purpose language-specific model with a domain-specific model, focusing on the resulting model's comprehension of technical jargon. Our experiments analyze the impact of this merging proces","authors_text":"Taisei Kakibuchi, Thibault Rousset, Yoshihide Nomura, Yusuke Sasaki","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T16:39:28Z","title":"Merging Language and Domain Specific Models: The Impact on Technical Vocabulary Acquisition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12001","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":"sha256:56c8c429a9bf763c1cbfae4c2410ff7423f0d3fbfcaff3894a1ec17d58894283","target":"record","created_at":"2026-07-05T10:29:34Z","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":"0780410da4edc8d6b9247861d657fe7ee20400ac70d9740eddf1a00dbe0ed51e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T16:39:28Z","title_canon_sha256":"6fd56b6aadc420bbcd48018f70ed32deabaea947b99cd562f85a895952d77f3d"},"schema_version":"1.0","source":{"id":"2502.12001","kind":"arxiv","version":2}},"canonical_sha256":"1c4e7252851383931c9827700838a95cd3b86a32c1a4779144561872c869fdfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c4e7252851383931c9827700838a95cd3b86a32c1a4779144561872c869fdfa","first_computed_at":"2026-07-05T10:29:34.346459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:34.346459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ruTFqmQg5OZ+VVItntbw6vaKobQuOPXwwwa3tHngKPdki/xaBtEZyLJrdAS+Q3RnpOyiESMePI+Di7vigLCjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:34.346975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12001","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56c8c429a9bf763c1cbfae4c2410ff7423f0d3fbfcaff3894a1ec17d58894283","sha256:d1fedd8db1bbaf2fd5a15ae647da0d5187a16e3804b5fa4da2f393167b27df7b"],"state_sha256":"848ea76c591c97b5f2733359a74f64f1e617e97868e83c388bc5fdf852a3ba5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RDD/wqtF5vdM2GKnNJwOv0tIVVH6291kcih3it36mFAAgldq/vgXwUgY/ekMUeJuHyS6xhDAb2+Av1G6RvdcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:57:44.193709Z","bundle_sha256":"8efcc067924bb4ca2c7773d5a098235db8a74d0be318585fbafd22418bab1db8"}}