{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MZ4KFFVCCFF2AKZV47J5WXPY4Z","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":"696f12f70de7586ee2702793833475a4f03cad07deaf2b1b8d9d0fa18036d7e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T06:30:36Z","title_canon_sha256":"3854563f4497442422596ae69e563d275f245bce6878acab7299be89eb0836ab"},"schema_version":"1.0","source":{"id":"2104.06644","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06644","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06644v2","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06644","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"MZ4KFFVCCFF2","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"MZ4KFFVCCFF2AKZV","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"MZ4KFFVC","created_at":"2026-07-05T03:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:b0b43b7033f08339d11d97b2bff40fda9e59affd685544946696993e3bfc4dbc","target":"graph","created_at":"2026-07-05T03:13:02Z","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/2104.06644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a different explanation: MLMs succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. To demonstrate this, we pre-train MLMs on sentences with randomly shuffled word order, and show that these models still achieve high accuracy after fine-tuning on many downstream tasks -- including on tasks specifically","authors_text":"Adina Williams, Dieuwke Hupkes, Douwe Kiela, Joelle Pineau, Koustuv Sinha, Robin Jia","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T06:30:36Z","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06644","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:ef2f3411ec2ed747432f8273a727ffc93fee8c2b9134405d6ce85f3396f4e2e0","target":"record","created_at":"2026-07-05T03:13:02Z","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":"696f12f70de7586ee2702793833475a4f03cad07deaf2b1b8d9d0fa18036d7e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T06:30:36Z","title_canon_sha256":"3854563f4497442422596ae69e563d275f245bce6878acab7299be89eb0836ab"},"schema_version":"1.0","source":{"id":"2104.06644","kind":"arxiv","version":2}},"canonical_sha256":"6678a296a2114ba02b35e7d3db5df8e64b273ba754c7c3485f6220b1bf597f17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6678a296a2114ba02b35e7d3db5df8e64b273ba754c7c3485f6220b1bf597f17","first_computed_at":"2026-07-05T03:13:02.878798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:02.878798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrnUn9Ib+oJRNf/EeeGn1uNG62S0tzrYVXAz7zRu8XUvhHv3ipbPRD/2TyszFBAfPGggvlc5rtsuXxq7z0XuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:02.879268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06644","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef2f3411ec2ed747432f8273a727ffc93fee8c2b9134405d6ce85f3396f4e2e0","sha256:b0b43b7033f08339d11d97b2bff40fda9e59affd685544946696993e3bfc4dbc"],"state_sha256":"6663552395cf44ade9fab6f2520caa01871891e0d427ade3b0a0a96133625145"}