{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AEPM27M5UR2IJDIQPXGYJABE54","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":"9d0d4860ffd341e3def6d3ef3ad9038d3a6401135549e1755525f207932c3fe1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T08:36:48Z","title_canon_sha256":"fe84007a28c8f91d2e0c4706fccf2210b786a36a12221e2193a8ac333abff7b4"},"schema_version":"1.0","source":{"id":"2101.00403","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00403","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00403v3","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00403","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_12","alias_value":"AEPM27M5UR2I","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_16","alias_value":"AEPM27M5UR2IJDIQ","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_8","alias_value":"AEPM27M5","created_at":"2026-07-05T02:45:35Z"}],"graph_snapshots":[{"event_id":"sha256:b2a9fd95bceded5bd9566a18ddb282a625071ca825f326eb438646f1766ffe00","target":"graph","created_at":"2026-07-05T02:45:35Z","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/2101.00403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How does the input segmentation of pretrained language models (PLMs) affect their interpretations of complex words? We present the first study investigating this question, taking BERT as the example PLM and focusing on its semantic representations of English derivatives. We show that PLMs can be interpreted as serial dual-route models, i.e., the meanings of complex words are either stored or else need to be computed from the subwords, which implies that maximally meaningful input tokens should allow for the best generalization on new words. This hypothesis is confirmed by a series of semantic ","authors_text":"Hinrich Sch\\\"utze, Janet B. Pierrehumbert, Valentin Hofmann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T08:36:48Z","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00403","kind":"arxiv","version":3},"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:b4540de8d3d130b1563c7ed53339b990cd483bf6abf024385b4dbc3626851434","target":"record","created_at":"2026-07-05T02:45:35Z","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":"9d0d4860ffd341e3def6d3ef3ad9038d3a6401135549e1755525f207932c3fe1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T08:36:48Z","title_canon_sha256":"fe84007a28c8f91d2e0c4706fccf2210b786a36a12221e2193a8ac333abff7b4"},"schema_version":"1.0","source":{"id":"2101.00403","kind":"arxiv","version":3}},"canonical_sha256":"011ecd7d9da474848d107dcd848024ef0687f9454c427e6f1212c1604d53f1d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"011ecd7d9da474848d107dcd848024ef0687f9454c427e6f1212c1604d53f1d1","first_computed_at":"2026-07-05T02:45:35.649513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:35.649513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3od+MTC41Hjau0Tnk+Nq5hsKzOFpMfauS0ibY7sN5LRmMd9urxcCx6WHqc4ngWPTM6KvgsluFYSkfC6W1HXUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:35.650001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00403","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4540de8d3d130b1563c7ed53339b990cd483bf6abf024385b4dbc3626851434","sha256:b2a9fd95bceded5bd9566a18ddb282a625071ca825f326eb438646f1766ffe00"],"state_sha256":"bc7dbaa50384d0d8fad006e68f4737a430f1ec3790ca32f9020f719d5d0c63e9"}