{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3JYWLKTWB7CY2KFS6JPZB53EIY","short_pith_number":"pith:3JYWLKTW","schema_version":"1.0","canonical_sha256":"da7165aa760fc58d28b2f25f90f76446048b19a7b6c001091674bde3f30e5d10","source":{"kind":"arxiv","id":"2606.02750","version":1},"attestation_state":"computed","paper":{"title":"On the Persistent Effects of Lexicality in Large Language Mod","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A.B. Siddique, Hammad Rizwan, Hassan Sajjad, Mona T. Diab, Muhammad Umair Haider, Nishant Subramani","submitted_at":"2026-06-01T18:15:45Z","abstract_excerpt":"Representations extracted from large language models (LLMs) play an important role in many downstream applications. However, the structure of these representations is often influenced by lexical overlap rather than semantic content. Our understanding of the relationship between this lexical influence and semantic content, and its implications for downstream tasks, remains limited. In this work, we investigate representations to quantify the effect of lexical overlap relative to semantic content. We consider several adversarial semantic stress tests and further connect our findings to the infor"},"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":"2606.02750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T18:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"ed52722832f38ab41b7bc42c41cc6ec83511aac3b4369cf04b9bffb56e9398e3","abstract_canon_sha256":"5fbd783bdef6b047edff5962deafcd92fbb425966bdac63b7a47140637204832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T00:05:08.906765Z","signature_b64":"IDwzucz3bFkdQ0SQW0/K+lyGnwK+4jhFTuIVeCYc6iibGjz5kKnJjBs2hEOzUMg3p6CjzyYQ6ehQ0CdOcLv8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da7165aa760fc58d28b2f25f90f76446048b19a7b6c001091674bde3f30e5d10","last_reissued_at":"2026-06-03T00:05:08.906333Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T00:05:08.906333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Persistent Effects of Lexicality in Large Language Mod","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A.B. Siddique, Hammad Rizwan, Hassan Sajjad, Mona T. Diab, Muhammad Umair Haider, Nishant Subramani","submitted_at":"2026-06-01T18:15:45Z","abstract_excerpt":"Representations extracted from large language models (LLMs) play an important role in many downstream applications. However, the structure of these representations is often influenced by lexical overlap rather than semantic content. Our understanding of the relationship between this lexical influence and semantic content, and its implications for downstream tasks, remains limited. In this work, we investigate representations to quantify the effect of lexical overlap relative to semantic content. We consider several adversarial semantic stress tests and further connect our findings to the infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02750","kind":"arxiv","version":1},"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/2606.02750/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":"2606.02750","created_at":"2026-06-03T00:05:08.906406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02750v1","created_at":"2026-06-03T00:05:08.906406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02750","created_at":"2026-06-03T00:05:08.906406+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JYWLKTWB7CY","created_at":"2026-06-03T00:05:08.906406+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JYWLKTWB7CY2KFS","created_at":"2026-06-03T00:05:08.906406+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JYWLKTW","created_at":"2026-06-03T00:05:08.906406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY","json":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY.json","graph_json":"https://pith.science/api/pith-number/3JYWLKTWB7CY2KFS6JPZB53EIY/graph.json","events_json":"https://pith.science/api/pith-number/3JYWLKTWB7CY2KFS6JPZB53EIY/events.json","paper":"https://pith.science/paper/3JYWLKTW"},"agent_actions":{"view_html":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY","download_json":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY.json","view_paper":"https://pith.science/paper/3JYWLKTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02750&json=true","fetch_graph":"https://pith.science/api/pith-number/3JYWLKTWB7CY2KFS6JPZB53EIY/graph.json","fetch_events":"https://pith.science/api/pith-number/3JYWLKTWB7CY2KFS6JPZB53EIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY/action/storage_attestation","attest_author":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY/action/author_attestation","sign_citation":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY/action/citation_signature","submit_replication":"https://pith.science/pith/3JYWLKTWB7CY2KFS6JPZB53EIY/action/replication_record"}},"created_at":"2026-06-03T00:05:08.906406+00:00","updated_at":"2026-06-03T00:05:08.906406+00:00"}