{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UQ7BBRVO6GUKMTLA7ABC6FNHIK","short_pith_number":"pith:UQ7BBRVO","schema_version":"1.0","canonical_sha256":"a43e10c6aef1a8a64d60f8022f15a742887a68f2260af96dfd7b1843f5d3af4d","source":{"kind":"arxiv","id":"2305.18657","version":2},"attestation_state":"computed","paper":{"title":"Representation Of Lexical Stylistic Features In Language Models' Embedding Space","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Callison-Burch, Marianna Apidianaki, Qing Lyu","submitted_at":"2023-05-29T23:44:26Z","abstract_excerpt":"The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstract semantic notions (e.g., intensity). In this paper, we demonstrate that lexical stylistic notions such as complexity, formality, and figurativeness, can also be identified in this space. We show that it is possible to derive a vector representation for each of these stylistic notions from only a small number of seed pairs. Using these vectors, we can characterize new texts in terms of these dimensions by performing "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.18657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T23:44:26Z","cross_cats_sorted":[],"title_canon_sha256":"715ac2483b5d956e0def7f434d76b59270a93812cfcc1a8e5da829ad20ed5fcf","abstract_canon_sha256":"3628860b84c59db6e739a7120bd6d6567441be072f9a892466abb134fcd8c07e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:19.277495Z","signature_b64":"7w2SPMS+tYzVTqCgAkUoFPFVNv7RzIk4z1awa3XP7KFsYuJ0c3z+naHrVxVDhG7rWuPuzxsrlJ2lf9WlaX40DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a43e10c6aef1a8a64d60f8022f15a742887a68f2260af96dfd7b1843f5d3af4d","last_reissued_at":"2026-07-05T06:16:19.277066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:19.277066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Of Lexical Stylistic Features In Language Models' Embedding Space","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Callison-Burch, Marianna Apidianaki, Qing Lyu","submitted_at":"2023-05-29T23:44:26Z","abstract_excerpt":"The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstract semantic notions (e.g., intensity). In this paper, we demonstrate that lexical stylistic notions such as complexity, formality, and figurativeness, can also be identified in this space. We show that it is possible to derive a vector representation for each of these stylistic notions from only a small number of seed pairs. Using these vectors, we can characterize new texts in terms of these dimensions by performing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18657","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.18657/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.18657","created_at":"2026-07-05T06:16:19.277127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18657v2","created_at":"2026-07-05T06:16:19.277127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18657","created_at":"2026-07-05T06:16:19.277127+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQ7BBRVO6GUK","created_at":"2026-07-05T06:16:19.277127+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQ7BBRVO6GUKMTLA","created_at":"2026-07-05T06:16:19.277127+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQ7BBRVO","created_at":"2026-07-05T06:16:19.277127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17621","citing_title":"A Combined Feature Embedding Tools for Multi-Class Software Defect and Identification","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK","json":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK.json","graph_json":"https://pith.science/api/pith-number/UQ7BBRVO6GUKMTLA7ABC6FNHIK/graph.json","events_json":"https://pith.science/api/pith-number/UQ7BBRVO6GUKMTLA7ABC6FNHIK/events.json","paper":"https://pith.science/paper/UQ7BBRVO"},"agent_actions":{"view_html":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK","download_json":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK.json","view_paper":"https://pith.science/paper/UQ7BBRVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18657&json=true","fetch_graph":"https://pith.science/api/pith-number/UQ7BBRVO6GUKMTLA7ABC6FNHIK/graph.json","fetch_events":"https://pith.science/api/pith-number/UQ7BBRVO6GUKMTLA7ABC6FNHIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK/action/storage_attestation","attest_author":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK/action/author_attestation","sign_citation":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK/action/citation_signature","submit_replication":"https://pith.science/pith/UQ7BBRVO6GUKMTLA7ABC6FNHIK/action/replication_record"}},"created_at":"2026-07-05T06:16:19.277127+00:00","updated_at":"2026-07-05T06:16:19.277127+00:00"}