{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D3PFMI63QW7LYDSFENT2OKXKFN","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":"8e42c6f556c0712d1368535dacfa13f1cd79ce72a431748d749c7f2a03d5514c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T05:46:50Z","title_canon_sha256":"38cf3faa035ce5f22f271ce90206ad42793b3d57a73e108db8c5a7bdb4cf4f9c"},"schema_version":"1.0","source":{"id":"2501.13397","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13397","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13397v5","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13397","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"D3PFMI63QW7L","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"D3PFMI63QW7LYDSF","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"D3PFMI63","created_at":"2026-07-05T11:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:b4dc2b0b7a355bc3cdf390c5fd509845e6443d5cac63ff7688f390b5876f307a","target":"graph","created_at":"2026-07-05T11:17:39Z","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/2501.13397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked Language Models (MLMs) have achieved remarkable success in many self-supervised representation learning tasks. MLMs are trained by randomly masking portions of the input sequences with [MASK] tokens and learning to reconstruct the original content based on the remaining context. This paper explores the impact of [MASK] tokens on MLMs. Analytical studies show that masking tokens can introduce the corrupted semantics problem, wherein the corrupted context may convey multiple, ambiguous meanings. This problem is also a key factor affecting the performance of MLMs on downstream tasks. Based","authors_text":"Bin Feng, Junwei Yang, Kangjie Zheng, Ming Zhang, Siyue Liang, Wei Ju, Zequn Liu, Zhiping Xiao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T05:46:50Z","title":"ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13397","kind":"arxiv","version":5},"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":"sha256:3502c86e629203ce12dd60fa01d7efbfb21c82f02d845f31333a1c45ddd24181","target":"record","created_at":"2026-07-05T11:17:39Z","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":"8e42c6f556c0712d1368535dacfa13f1cd79ce72a431748d749c7f2a03d5514c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T05:46:50Z","title_canon_sha256":"38cf3faa035ce5f22f271ce90206ad42793b3d57a73e108db8c5a7bdb4cf4f9c"},"schema_version":"1.0","source":{"id":"2501.13397","kind":"arxiv","version":5}},"canonical_sha256":"1ede5623db85bebc0e452367a72aea2b43c8e842bcbc727d0cc12f4b5861c867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ede5623db85bebc0e452367a72aea2b43c8e842bcbc727d0cc12f4b5861c867","first_computed_at":"2026-07-05T11:17:39.968648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:39.968648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xEGaMxitaqpJ7BgfNXDGXNouw1BJAue9iOjazsaIWjrzzAP04ehWg4/Yw1ByVlhoylC8svU55u5qgLuqNf5pCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:39.969130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13397","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3502c86e629203ce12dd60fa01d7efbfb21c82f02d845f31333a1c45ddd24181","sha256:b4dc2b0b7a355bc3cdf390c5fd509845e6443d5cac63ff7688f390b5876f307a"],"state_sha256":"1067fd0b07963fd89d8b2ef3a6e8142208ad5a90c21494b6249560cb53096b4d"}