{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PPMABXXDFIR4WQGIBQKWSR5KVD","short_pith_number":"pith:PPMABXXD","schema_version":"1.0","canonical_sha256":"7bd800dee32a23cb40c80c156947aaa8da4144244d487f56705b1056f666a4bc","source":{"kind":"arxiv","id":"2402.05132","version":2},"attestation_state":"computed","paper":{"title":"TexShape: Information Theoretic Sentence Embedding for Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Homa Esfahanizadeh, Kaan Kale, Muriel Medard, Noel Elias, Oguzhan Baser, Sriram Vishwanath","submitted_at":"2024-02-05T22:48:28Z","abstract_excerpt":"With the exponential growth in data volume and the emergence of data-intensive applications, particularly in the field of machine learning, concerns related to resource utilization, privacy, and fairness have become paramount. This paper focuses on the textual domain of data and addresses challenges regarding encoding sentences to their optimized representations through the lens of information-theory. In particular, we use empirical estimates of mutual information, using the Donsker-Varadhan definition of Kullback-Leibler divergence. Our approach leverages this estimation to train an informati"},"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":"2402.05132","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T22:48:28Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"a710534578005ce644f79f3bb8dfcc55abffe23406052e0fd9456d624a9c9427","abstract_canon_sha256":"5947ece30d0bbb19a3d661bda33ad36bd26be292b693b21d58032b756fd292e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:05.088846Z","signature_b64":"xoOUv4sQclWbCfB6hUi6a/xbvJe6JefAxKO1/vj+kjhmzPqvS8oidxb1tyIJSEuUZ2f9FXkrguybqMxyy8cNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd800dee32a23cb40c80c156947aaa8da4144244d487f56705b1056f666a4bc","last_reissued_at":"2026-07-05T08:18:05.088356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:05.088356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TexShape: Information Theoretic Sentence Embedding for Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Homa Esfahanizadeh, Kaan Kale, Muriel Medard, Noel Elias, Oguzhan Baser, Sriram Vishwanath","submitted_at":"2024-02-05T22:48:28Z","abstract_excerpt":"With the exponential growth in data volume and the emergence of data-intensive applications, particularly in the field of machine learning, concerns related to resource utilization, privacy, and fairness have become paramount. This paper focuses on the textual domain of data and addresses challenges regarding encoding sentences to their optimized representations through the lens of information-theory. In particular, we use empirical estimates of mutual information, using the Donsker-Varadhan definition of Kullback-Leibler divergence. Our approach leverages this estimation to train an informati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05132","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/2402.05132/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":"2402.05132","created_at":"2026-07-05T08:18:05.088416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05132v2","created_at":"2026-07-05T08:18:05.088416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05132","created_at":"2026-07-05T08:18:05.088416+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPMABXXDFIR4","created_at":"2026-07-05T08:18:05.088416+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPMABXXDFIR4WQGI","created_at":"2026-07-05T08:18:05.088416+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPMABXXD","created_at":"2026-07-05T08:18:05.088416+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/PPMABXXDFIR4WQGIBQKWSR5KVD","json":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD.json","graph_json":"https://pith.science/api/pith-number/PPMABXXDFIR4WQGIBQKWSR5KVD/graph.json","events_json":"https://pith.science/api/pith-number/PPMABXXDFIR4WQGIBQKWSR5KVD/events.json","paper":"https://pith.science/paper/PPMABXXD"},"agent_actions":{"view_html":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD","download_json":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD.json","view_paper":"https://pith.science/paper/PPMABXXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05132&json=true","fetch_graph":"https://pith.science/api/pith-number/PPMABXXDFIR4WQGIBQKWSR5KVD/graph.json","fetch_events":"https://pith.science/api/pith-number/PPMABXXDFIR4WQGIBQKWSR5KVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD/action/storage_attestation","attest_author":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD/action/author_attestation","sign_citation":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD/action/citation_signature","submit_replication":"https://pith.science/pith/PPMABXXDFIR4WQGIBQKWSR5KVD/action/replication_record"}},"created_at":"2026-07-05T08:18:05.088416+00:00","updated_at":"2026-07-05T08:18:05.088416+00:00"}