{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PL4XEJ3NZQXSG5KFES6NZEXFIQ","short_pith_number":"pith:PL4XEJ3N","canonical_record":{"source":{"id":"2010.05609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T11:29:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf3785651df4430d5f9d2c3d0f499d0ce03421133c0e9b47cc0b9f7849b0f431","abstract_canon_sha256":"3bedaad7b7e8fb9a3587c8d6eb3c368e4d18118bbea37f1ca3d01c18a0f323b8"},"schema_version":"1.0"},"canonical_sha256":"7af972276dcc2f23754524bcdc92e5442921ce2e3c1931eb533f59059c06f3b4","source":{"kind":"arxiv","id":"2010.05609","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05609","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05609v1","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05609","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"PL4XEJ3NZQXS","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"pith_short_16","alias_value":"PL4XEJ3NZQXSG5KF","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"pith_short_8","alias_value":"PL4XEJ3N","created_at":"2026-07-05T01:42:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PL4XEJ3NZQXSG5KFES6NZEXFIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.05609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T11:29:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf3785651df4430d5f9d2c3d0f499d0ce03421133c0e9b47cc0b9f7849b0f431","abstract_canon_sha256":"3bedaad7b7e8fb9a3587c8d6eb3c368e4d18118bbea37f1ca3d01c18a0f323b8"},"schema_version":"1.0"},"canonical_sha256":"7af972276dcc2f23754524bcdc92e5442921ce2e3c1931eb533f59059c06f3b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:08.561437Z","signature_b64":"BVjrTUitUir7cIYHOWlvZokW1X95OzTPVHqr+yPOsTYl3ENBWr6Uf7bXflsT6ix+1oJNv/BPQm4Jm0xI3BUoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7af972276dcc2f23754524bcdc92e5442921ce2e3c1931eb533f59059c06f3b4","last_reissued_at":"2026-07-05T01:42:08.561078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:08.561078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.05609","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":"2026-07-05T01:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hue64g9nNtzqtCNfiT25SMlcUKQ0IMmINB1nqGEzH30ZIqfheq0yp95wNSWHdLHRjZ+Ms2cIupjaYvJ/Qg/IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:33:01.946438Z"},"content_sha256":"4ea9d08d6e681435171672e1ff60b50d508ad751442a49f54146705524913025","schema_version":"1.0","event_id":"sha256:4ea9d08d6e681435171672e1ff60b50d508ad751442a49f54146705524913025"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PL4XEJ3NZQXSG5KFES6NZEXFIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Load What You Need: Smaller Versions of Multilingual BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amine Abdaoui, Camille Pradel, Gr\\'egoire Sigel","submitted_at":"2020-10-12T11:29:06Z","abstract_excerpt":"Pre-trained Transformer-based models are achieving state-of-the-art results on a variety of Natural Language Processing data sets. However, the size of these models is often a drawback for their deployment in real production applications. In the case of multilingual models, most of the parameters are located in the embeddings layer. Therefore, reducing the vocabulary size should have an important impact on the total number of parameters. In this paper, we propose to generate smaller models that handle fewer number of languages according to the targeted corpora. We present an evaluation of smal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05609","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/2010.05609/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":"2026-07-05T01:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XluMyIqXl0tBJU1uMEXvQCGO1/zUSJlVVlwnWrAIe4uayW3GDAX2m37t23Ic+yxdi2allONOeeBGtiFOPXBFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:33:01.946975Z"},"content_sha256":"06ba1b99c681dc210a4140ba6a06f0d695e7dd2eebb9472a416cfa181fc914d1","schema_version":"1.0","event_id":"sha256:06ba1b99c681dc210a4140ba6a06f0d695e7dd2eebb9472a416cfa181fc914d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ/bundle.json","state_url":"https://pith.science/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ/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":"2026-08-18T23:33:01Z","links":{"resolver":"https://pith.science/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ","bundle":"https://pith.science/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ/bundle.json","state":"https://pith.science/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PL4XEJ3NZQXSG5KFES6NZEXFIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PL4XEJ3NZQXSG5KFES6NZEXFIQ","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":"3bedaad7b7e8fb9a3587c8d6eb3c368e4d18118bbea37f1ca3d01c18a0f323b8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T11:29:06Z","title_canon_sha256":"cf3785651df4430d5f9d2c3d0f499d0ce03421133c0e9b47cc0b9f7849b0f431"},"schema_version":"1.0","source":{"id":"2010.05609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05609","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05609v1","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05609","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"PL4XEJ3NZQXS","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"pith_short_16","alias_value":"PL4XEJ3NZQXSG5KF","created_at":"2026-07-05T01:42:08Z"},{"alias_kind":"pith_short_8","alias_value":"PL4XEJ3N","created_at":"2026-07-05T01:42:08Z"}],"graph_snapshots":[{"event_id":"sha256:06ba1b99c681dc210a4140ba6a06f0d695e7dd2eebb9472a416cfa181fc914d1","target":"graph","created_at":"2026-07-05T01:42:08Z","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/2010.05609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Transformer-based models are achieving state-of-the-art results on a variety of Natural Language Processing data sets. However, the size of these models is often a drawback for their deployment in real production applications. In the case of multilingual models, most of the parameters are located in the embeddings layer. Therefore, reducing the vocabulary size should have an important impact on the total number of parameters. In this paper, we propose to generate smaller models that handle fewer number of languages according to the targeted corpora. We present an evaluation of smal","authors_text":"Amine Abdaoui, Camille Pradel, Gr\\'egoire Sigel","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T11:29:06Z","title":"Load What You Need: Smaller Versions of Multilingual BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05609","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":"sha256:4ea9d08d6e681435171672e1ff60b50d508ad751442a49f54146705524913025","target":"record","created_at":"2026-07-05T01:42:08Z","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":"3bedaad7b7e8fb9a3587c8d6eb3c368e4d18118bbea37f1ca3d01c18a0f323b8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-12T11:29:06Z","title_canon_sha256":"cf3785651df4430d5f9d2c3d0f499d0ce03421133c0e9b47cc0b9f7849b0f431"},"schema_version":"1.0","source":{"id":"2010.05609","kind":"arxiv","version":1}},"canonical_sha256":"7af972276dcc2f23754524bcdc92e5442921ce2e3c1931eb533f59059c06f3b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7af972276dcc2f23754524bcdc92e5442921ce2e3c1931eb533f59059c06f3b4","first_computed_at":"2026-07-05T01:42:08.561078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:08.561078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BVjrTUitUir7cIYHOWlvZokW1X95OzTPVHqr+yPOsTYl3ENBWr6Uf7bXflsT6ix+1oJNv/BPQm4Jm0xI3BUoAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:08.561437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.05609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ea9d08d6e681435171672e1ff60b50d508ad751442a49f54146705524913025","sha256:06ba1b99c681dc210a4140ba6a06f0d695e7dd2eebb9472a416cfa181fc914d1"],"state_sha256":"f9a0149a75b06f19448d73c9e67d6bf7a88db1d193b84d2739d8c1aabae725c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRLAMdNjEgPD2C8jmau4xKq9U5m8XUTnu0EECKOaiR2hOBURwIPhz2qh4cIGAkYLttYk2oKeZz5xquGxe8yuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:33:01.951899Z","bundle_sha256":"c3bcf98b53661f7a6e27718ee05b17d14e622fc93eae42bc3278680d8cf38fa5"}}