{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WY6BBASFJLOKSMDE2WBTRH7Y3S","short_pith_number":"pith:WY6BBASF","canonical_record":{"source":{"id":"2106.02834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-05T08:22:05Z","cross_cats_sorted":[],"title_canon_sha256":"a36fcc0e37edacd15b869ecac84527b9b4210406f946083a4ec47cf61141028b","abstract_canon_sha256":"efd8b93df8290e8cc472bf1c7d611a7e63cc26f5069154c74bd6e8fba3a797d9"},"schema_version":"1.0"},"canonical_sha256":"b63c1082454adca93064d583389ff8dcb9d67ff571eb95246d223153e1329ba7","source":{"kind":"arxiv","id":"2106.02834","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WY6BBASFJLOKSMDE2WBTRH7Y3S","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-05T08:22:05Z","cross_cats_sorted":[],"title_canon_sha256":"a36fcc0e37edacd15b869ecac84527b9b4210406f946083a4ec47cf61141028b","abstract_canon_sha256":"efd8b93df8290e8cc472bf1c7d611a7e63cc26f5069154c74bd6e8fba3a797d9"},"schema_version":"1.0"},"canonical_sha256":"b63c1082454adca93064d583389ff8dcb9d67ff571eb95246d223153e1329ba7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:30.703939Z","signature_b64":"ZD7krrLW6ZBYPad+Vb1HXx9/oEfBGmGklOJkV+PJLDNGVPV0+Y0uRlPgWfr3xr8prACapmaYycRoYwfXttrBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63c1082454adca93064d583389ff8dcb9d67ff571eb95246d223153e1329ba7","last_reissued_at":"2026-07-05T02:46:30.703539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:30.703539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02834","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":"2026-07-05T02:46:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K71Ow4peb7+VN+uEj/mUt9lHguB8tTA8ueQR/kMCtLyQUvIs3nfCoSvtuNMyyncY0GcHPa/s/1+t5J7NnXEEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:29:08.173756Z"},"content_sha256":"0eda281ba9d74fb1e087267bebd06e09bd053632027dca0fc8b32f61f4565d1e","schema_version":"1.0","event_id":"sha256:0eda281ba9d74fb1e087267bebd06e09bd053632027dca0fc8b32f61f4565d1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WY6BBASFJLOKSMDE2WBTRH7Y3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MergeDistill: Merging Pre-trained Language Models using Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Melvin Johnson, Partha Talukdar, Simran Khanuja","submitted_at":"2021-06-05T08:22:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02834","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/2106.02834/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":"2026-07-05T02:46:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a8vfpqZheNSa76WE8HVboVdMvvEbjD/qnzurTYVIlKvX+rsyiagy0StVuyo7d3z9cZfzgPmxBt6o3IlWPMyJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:29:08.174268Z"},"content_sha256":"983e8abf1e5f85f83881c1863b235e237c5c47f8e21973828c2e5ee3a64267bb","schema_version":"1.0","event_id":"sha256:983e8abf1e5f85f83881c1863b235e237c5c47f8e21973828c2e5ee3a64267bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S/bundle.json","state_url":"https://pith.science/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S/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":"2026-08-04T00:29:08Z","links":{"resolver":"https://pith.science/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S","bundle":"https://pith.science/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S/bundle.json","state":"https://pith.science/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WY6BBASFJLOKSMDE2WBTRH7Y3S/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrDgs4oWFGmUylzRtXTEHtfRITgvfQ/OVXd79lA5QS5hU/QBrgSLEe13IcMKURv4A4GG8UVSAHEYr8jyN2dgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:29:08.179780Z","bundle_sha256":"20668dfce50b1612c956e640afd2cb6e546924f7c10c7a8f9b15c58a48f8afee"}}