{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WY6BBASFJLOKSMDE2WBTRH7Y3S","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":"efd8b93df8290e8cc472bf1c7d611a7e63cc26f5069154c74bd6e8fba3a797d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-05T08:22:05Z","title_canon_sha256":"a36fcc0e37edacd15b869ecac84527b9b4210406f946083a4ec47cf61141028b"},"schema_version":"1.0","source":{"id":"2106.02834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02834","created_at":"2026-07-05T02:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02834v1","created_at":"2026-07-05T02:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02834","created_at":"2026-07-05T02:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"WY6BBASFJLOK","created_at":"2026-07-05T02:46:30Z"},{"alias_kind":"pith_short_16","alias_value":"WY6BBASFJLOKSMDE","created_at":"2026-07-05T02:46:30Z"},{"alias_kind":"pith_short_8","alias_value":"WY6BBASF","created_at":"2026-07-05T02:46:30Z"}],"graph_snapshots":[{"event_id":"sha256:983e8abf1e5f85f83881c1863b235e237c5c47f8e21973828c2e5ee3a64267bb","target":"graph","created_at":"2026-07-05T02:46:30Z","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/2106.02834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained multilingual language models (LMs) have achieved state-of-the-art results in cross-lingual transfer, but they often lead to an inequitable representation of languages due to limited capacity, skewed pre-training data, and sub-optimal vocabularies. This has prompted the creation of an ever-growing pre-trained model universe, where each model is trained on large amounts of language or domain specific data with a carefully curated, linguistically informed vocabulary. However, doing so brings us back full circle and prevents one from leveraging the benefits of multilinguality. To addre","authors_text":"Melvin Johnson, Partha Talukdar, Simran Khanuja","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-05T08:22:05Z","title":"MergeDistill: Merging Pre-trained Language Models using Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02834","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":"sha256:0eda281ba9d74fb1e087267bebd06e09bd053632027dca0fc8b32f61f4565d1e","target":"record","created_at":"2026-07-05T02:46:30Z","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":"efd8b93df8290e8cc472bf1c7d611a7e63cc26f5069154c74bd6e8fba3a797d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-05T08:22:05Z","title_canon_sha256":"a36fcc0e37edacd15b869ecac84527b9b4210406f946083a4ec47cf61141028b"},"schema_version":"1.0","source":{"id":"2106.02834","kind":"arxiv","version":1}},"canonical_sha256":"b63c1082454adca93064d583389ff8dcb9d67ff571eb95246d223153e1329ba7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b63c1082454adca93064d583389ff8dcb9d67ff571eb95246d223153e1329ba7","first_computed_at":"2026-07-05T02:46:30.703539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:30.703539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZD7krrLW6ZBYPad+Vb1HXx9/oEfBGmGklOJkV+PJLDNGVPV0+Y0uRlPgWfr3xr8prACapmaYycRoYwfXttrBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:30.703939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eda281ba9d74fb1e087267bebd06e09bd053632027dca0fc8b32f61f4565d1e","sha256:983e8abf1e5f85f83881c1863b235e237c5c47f8e21973828c2e5ee3a64267bb"],"state_sha256":"0fe23844d2e9744532060bb0a13feb41c45b6fe849c3f2ff2ea8449233030ee1"}