{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3MFVWKPDJHIGXMMNCTNYBWF7YP","short_pith_number":"pith:3MFVWKPD","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"},"canonical_sha256":"db0b5b29e349d06bb18d14db80d8bfc3e1e76f3239dc9b75b47b5163bda5c418","source":{"kind":"arxiv","id":"2508.15823","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15823","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15823v1","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15823","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"3MFVWKPDJHIG","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"3MFVWKPDJHIGXMMN","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"3MFVWKPD","created_at":"2026-07-05T11:57:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3MFVWKPDJHIGXMMNCTNYBWF7YP","target":"record","payload":{"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"},"canonical_sha256":"db0b5b29e349d06bb18d14db80d8bfc3e1e76f3239dc9b75b47b5163bda5c418","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"},"source_kind":"arxiv","source_id":"2508.15823","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:57:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wXcwyIUur1mYmmm80FRLWAz2P2keMJlE5lCk7LQdsyQ+3q7hfIVubx/iBtiZZ4oATV05ce/D5f+E6MxxMAfEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:00:37.403251Z"},"content_sha256":"f6df125d68f22a89d8b50371867bdf33156781c030b8144a27cb6c59cc5d31e2","schema_version":"1.0","event_id":"sha256:f6df125d68f22a89d8b50371867bdf33156781c030b8144a27cb6c59cc5d31e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3MFVWKPDJHIGXMMNCTNYBWF7YP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:57:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vzebEaMsMStQjnHrIeJreqRuOtBg0/sWPjHOUc5tr7kiQbZ8PXtb42SrX7ha4hT4xMU2uVfxj8DaYtdlJB4tAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:00:37.403887Z"},"content_sha256":"87aa359cc8be68deed490707868fee1cb742ea5aba49cb5c16b3ac9846209cee","schema_version":"1.0","event_id":"sha256:87aa359cc8be68deed490707868fee1cb742ea5aba49cb5c16b3ac9846209cee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/bundle.json","state_url":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T07:00:37Z","links":{"resolver":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP","bundle":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/bundle.json","state":"https://pith.science/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MFVWKPDJHIGXMMNCTNYBWF7YP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3MFVWKPDJHIGXMMNCTNYBWF7YP","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":"8d812aee0c3f79104642ce4e6b5a2af0cb44cba44910dd4f3cc5e7a01abd849d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T02:08:35Z","title_canon_sha256":"0fb4a5b0fd0c8cadd785e09cd3ce7ced9fbd4b4307840314d0f0a51576975a9d"},"schema_version":"1.0","source":{"id":"2508.15823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15823","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15823v1","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15823","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"3MFVWKPDJHIG","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"3MFVWKPDJHIGXMMN","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"3MFVWKPD","created_at":"2026-07-05T11:57:21Z"}],"graph_snapshots":[{"event_id":"sha256:87aa359cc8be68deed490707868fee1cb742ea5aba49cb5c16b3ac9846209cee","target":"graph","created_at":"2026-07-05T11:57:21Z","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/2508.15823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lamia Tasnim Mim, Mohammad Wali Ur Rahman, Ric Nevarez, Salim Hariri","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T02:08:35Z","title":"SDEC: Semantic Deep Embedded Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15823","kind":"arxiv","version":1},"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:f6df125d68f22a89d8b50371867bdf33156781c030b8144a27cb6c59cc5d31e2","target":"record","created_at":"2026-07-05T11:57:21Z","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":"8d812aee0c3f79104642ce4e6b5a2af0cb44cba44910dd4f3cc5e7a01abd849d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T02:08:35Z","title_canon_sha256":"0fb4a5b0fd0c8cadd785e09cd3ce7ced9fbd4b4307840314d0f0a51576975a9d"},"schema_version":"1.0","source":{"id":"2508.15823","kind":"arxiv","version":1}},"canonical_sha256":"db0b5b29e349d06bb18d14db80d8bfc3e1e76f3239dc9b75b47b5163bda5c418","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db0b5b29e349d06bb18d14db80d8bfc3e1e76f3239dc9b75b47b5163bda5c418","first_computed_at":"2026-07-05T11:57:21.624672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:21.624672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GbxTDTM5mo6/QyHDQMxprB/CPqm1KEIGMi8bRmM2ELaCOvkB8hIYqi/CqxU7+bSQvTM/1+9aSOeSNGYjHQF5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:21.625250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6df125d68f22a89d8b50371867bdf33156781c030b8144a27cb6c59cc5d31e2","sha256:87aa359cc8be68deed490707868fee1cb742ea5aba49cb5c16b3ac9846209cee"],"state_sha256":"f9f7005508eb83a0c697757638079b6555afe9650bab0d88ce9f00da11b3afea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FdvpQs76Fct1A+6YHG64ohg7ac1rxTP5O44nYGTKVhLQzh7C6L5ghSBKE29tX3+3sB/w9BcssK4zCmU65gI7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:00:37.410111Z","bundle_sha256":"8713fa5c56bfac4d7ac2362754a4ec62b60140187e4de0081df6c3608dfda9be"}}