{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LJSMJK2NKPP5LGLR2AEMCOZ6PT","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":"96f53579918cdcf762e8d3d6b74dba49288c9f9e5e5a3e5f69385d71f7b779b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-08T07:40:21Z","title_canon_sha256":"ae68b01def93249a5f5e37ec63b1a7a56fd43bffd978784fb129ff077a5fa85f"},"schema_version":"1.0","source":{"id":"2010.03813","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03813","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03813v2","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03813","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"pith_short_12","alias_value":"LJSMJK2NKPP5","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"pith_short_16","alias_value":"LJSMJK2NKPP5LGLR","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"pith_short_8","alias_value":"LJSMJK2N","created_at":"2026-07-05T01:41:34Z"}],"graph_snapshots":[{"event_id":"sha256:d9329afea7ac58a6f1b04b656c57699979abd3c9e0be1897c18b62ca41a2d341","target":"graph","created_at":"2026-07-05T01:41:34Z","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/2010.03813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language modeling have led to computationally intensive and resource-demanding state-of-the-art models. In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language models. Multiple BERT-based models are trained on gradually increasing amounts of French text. Through fine-tuning on the French Question Answering Dataset (FQuAD), we observe that well-performing models are obtained with as little as 100 MB of text. In addition, we show that past critically low amounts of pre-training data, an intermediate pre-training step on t","authors_text":"Fran\\c{c}ois Fleuret, Martin d'Hoffschmidt, Vincent Micheli","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-08T07:40:21Z","title":"On the importance of pre-training data volume for compact language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03813","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:dcbfecd18e4eeafb9661e1e1a2616dd2e91d6206813ad1b21788e218a908573c","target":"record","created_at":"2026-07-05T01:41:34Z","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":"96f53579918cdcf762e8d3d6b74dba49288c9f9e5e5a3e5f69385d71f7b779b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-08T07:40:21Z","title_canon_sha256":"ae68b01def93249a5f5e37ec63b1a7a56fd43bffd978784fb129ff077a5fa85f"},"schema_version":"1.0","source":{"id":"2010.03813","kind":"arxiv","version":2}},"canonical_sha256":"5a64c4ab4d53dfd59971d008c13b3e7cec121d68ce8c4dc9dc9727fc858de705","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a64c4ab4d53dfd59971d008c13b3e7cec121d68ce8c4dc9dc9727fc858de705","first_computed_at":"2026-07-05T01:41:34.298791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:34.298791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/R1LxIKuDIFnj+vIPtuhIDJVz286hZZ3RR2v7wF/vKdtNt7bHx/RZLoHrJRCNFo3yJuBwnX8TzAhN7aAN+jIDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:34.299173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03813","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcbfecd18e4eeafb9661e1e1a2616dd2e91d6206813ad1b21788e218a908573c","sha256:d9329afea7ac58a6f1b04b656c57699979abd3c9e0be1897c18b62ca41a2d341"],"state_sha256":"b915911bc8423341f0d57b22d75b5fc311ddc2a59b82d249a56a1111a2241337"}