{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V7IJ2BNYAW5YIOAVBVTIR2CP2Z","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":"7154f9ff5077e50b09ae22de844a6d85fef6980437f00a75ea127aea22df6b0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T00:02:10Z","title_canon_sha256":"c00ccb3469078e532622eed6cc4ce607fe74f4e8268304b79df11be2a9bf294f"},"schema_version":"1.0","source":{"id":"2203.10415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10415","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10415v1","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10415","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"V7IJ2BNYAW5Y","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"V7IJ2BNYAW5YIOAV","created_at":"2026-07-05T04:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"V7IJ2BNY","created_at":"2026-07-05T04:06:52Z"}],"graph_snapshots":[{"event_id":"sha256:4172ab2a9abfc856f2729a5d1add71e0297ee6a691f08ec906f38069948cf218","target":"graph","created_at":"2026-07-05T04:06:52Z","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/2203.10415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e.g. BERT) with the aim of learning better language representations. However, to the best of our knowledge, no previous work so far has investigated how different pre-training objectives affect what BERT learns about linguistics properties. We hypothesize that linguistically motivated objectives such as MLM should help BERT to acquire better linguistic knowledge compared to other non-linguistically motivated objectives that are not intuitive or hard for humans to guess the ","authors_text":"Ahmed Alajrami, Nikolaos Aletras","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T00:02:10Z","title":"How does the pre-training objective affect what large language models learn about linguistic properties?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10415","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":"sha256:812f4a72b6a5c3f4d4e0777deb7b96f1acb549bbc3fcfa8bdf9949a8e39aece3","target":"record","created_at":"2026-07-05T04:06:52Z","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":"7154f9ff5077e50b09ae22de844a6d85fef6980437f00a75ea127aea22df6b0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T00:02:10Z","title_canon_sha256":"c00ccb3469078e532622eed6cc4ce607fe74f4e8268304b79df11be2a9bf294f"},"schema_version":"1.0","source":{"id":"2203.10415","kind":"arxiv","version":1}},"canonical_sha256":"afd09d05b805bb8438150d6688e84fd6751fb9b841d3f25305adff9b1a8f979e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afd09d05b805bb8438150d6688e84fd6751fb9b841d3f25305adff9b1a8f979e","first_computed_at":"2026-07-05T04:06:52.699489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:52.699489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WXBjKUzJtFBqYtIMaAjE8PAjnJvCq9UXv/IsHLVcZF85a4QI9ebVyi9VZaL6pZE9OqvTB+7Tchc7oIdkM5XKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:52.699826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:812f4a72b6a5c3f4d4e0777deb7b96f1acb549bbc3fcfa8bdf9949a8e39aece3","sha256:4172ab2a9abfc856f2729a5d1add71e0297ee6a691f08ec906f38069948cf218"],"state_sha256":"2e369a36e01759e03d6f75d1a437833fab88da3df753d0a6e6e7ec020e82b1a5"}