{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3MFVWKPDJHIGXMMNCTNYBWF7YP","short_pith_number":"pith:3MFVWKPD","schema_version":"1.0","canonical_sha256":"db0b5b29e349d06bb18d14db80d8bfc3e1e76f3239dc9b75b47b5163bda5c418","source":{"kind":"arxiv","id":"2508.15823","version":1},"attestation_state":"computed","paper":{"title":"SDEC: Semantic Deep Embedded Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Lamia Tasnim Mim, Mohammad Wali Ur Rahman, Ric Nevarez, Salim Hariri","submitted_at":"2025-08-18T02:08:35Z","abstract_excerpt":"The high dimensional and semantically complex nature of textual Big data presents significant challenges for text clustering, which frequently lead to suboptimal groupings when using conventional techniques like k-means or hierarchical clustering. This work presents Semantic Deep Embedded Clustering (SDEC), an unsupervised text clustering framework that combines an improved autoencoder with transformer-based embeddings to overcome these challenges. This novel method preserves semantic relationships during data reconstruction by combining Mean Squared Error (MSE) and Cosine Similarity Loss (CSL"},"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":"2508.15823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T02:08:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0fb4a5b0fd0c8cadd785e09cd3ce7ced9fbd4b4307840314d0f0a51576975a9d","abstract_canon_sha256":"8d812aee0c3f79104642ce4e6b5a2af0cb44cba44910dd4f3cc5e7a01abd849d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:21.625250Z","signature_b64":"GbxTDTM5mo6/QyHDQMxprB/CPqm1KEIGMi8bRmM2ELaCOvkB8hIYqi/CqxU7+bSQvTM/1+9aSOeSNGYjHQF5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db0b5b29e349d06bb18d14db80d8bfc3e1e76f3239dc9b75b47b5163bda5c418","last_reissued_at":"2026-07-05T11:57:21.624672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:21.624672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDEC: Semantic Deep Embedded Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Lamia Tasnim Mim, Mohammad Wali Ur Rahman, Ric Nevarez, Salim Hariri","submitted_at":"2025-08-18T02:08:35Z","abstract_excerpt":"The high dimensional and semantically complex nature of textual Big data presents significant challenges for text clustering, which frequently lead to suboptimal groupings when using conventional techniques like k-means or hierarchical clustering. This work presents Semantic Deep Embedded Clustering (SDEC), an unsupervised text clustering framework that combines an improved autoencoder with transformer-based embeddings to overcome these challenges. This novel method preserves semantic relationships during data reconstruction by combining Mean Squared Error (MSE) and Cosine Similarity Loss (CSL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15823","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/2508.15823/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":"2508.15823","created_at":"2026-07-05T11:57:21.624733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15823v1","created_at":"2026-07-05T11:57:21.624733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15823","created_at":"2026-07-05T11:57:21.624733+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MFVWKPDJHIG","created_at":"2026-07-05T11:57:21.624733+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MFVWKPDJHIGXMMN","created_at":"2026-07-05T11:57:21.624733+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MFVWKPD","created_at":"2026-07-05T11:57:21.624733+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/3MFVWKPDJHIGXMMNCTNYBWF7YP","json":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP.json","graph_json":"https://pith.science/api/pith-number/3MFVWKPDJHIGXMMNCTNYBWF7YP/graph.json","events_json":"https://pith.science/api/pith-number/3MFVWKPDJHIGXMMNCTNYBWF7YP/events.json","paper":"https://pith.science/paper/3MFVWKPD"},"agent_actions":{"view_html":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP","download_json":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP.json","view_paper":"https://pith.science/paper/3MFVWKPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15823&json=true","fetch_graph":"https://pith.science/api/pith-number/3MFVWKPDJHIGXMMNCTNYBWF7YP/graph.json","fetch_events":"https://pith.science/api/pith-number/3MFVWKPDJHIGXMMNCTNYBWF7YP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/action/storage_attestation","attest_author":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/action/author_attestation","sign_citation":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/action/citation_signature","submit_replication":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/action/replication_record"}},"created_at":"2026-07-05T11:57:21.624733+00:00","updated_at":"2026-07-05T11:57:21.624733+00:00"}