{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SOKECH66RMDOF4TJUOEZFTW4ZK","short_pith_number":"pith:SOKECH66","canonical_record":{"source":{"id":"2607.28635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T08:33:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94ef8f072f90c14ac5c4f29d150e551d5db20969b58f1909401d6586af2e4789","abstract_canon_sha256":"d5f6f8a546130417c21f2ca668227b92d2a1f5e55ca19babdb971513f597132a"},"schema_version":"1.0"},"canonical_sha256":"9394411fde8b06e2f269a38992cedccaae90b65496ecd5d1b4f946231634b8d4","source":{"kind":"arxiv","id":"2607.28635","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28635","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28635v1","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28635","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"SOKECH66RMDO","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"SOKECH66RMDOF4TJ","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"SOKECH66","created_at":"2026-08-03T00:11:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SOKECH66RMDOF4TJUOEZFTW4ZK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T08:33:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94ef8f072f90c14ac5c4f29d150e551d5db20969b58f1909401d6586af2e4789","abstract_canon_sha256":"d5f6f8a546130417c21f2ca668227b92d2a1f5e55ca19babdb971513f597132a"},"schema_version":"1.0"},"canonical_sha256":"9394411fde8b06e2f269a38992cedccaae90b65496ecd5d1b4f946231634b8d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:11:51.990657Z","signature_b64":"gGuJTOQuurWf5Grpii8rvh63LX9y1jjapxm7qdyuFjNab6D8Tdt95pCSazQKQHRIafm/wzfC4nYrMRLryqCpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9394411fde8b06e2f269a38992cedccaae90b65496ecd5d1b4f946231634b8d4","last_reissued_at":"2026-08-03T00:11:51.988502Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:11:51.988502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.28635","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":"2026-08-03T00:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CqAy4rp9mVERkGJkiCfu01rtB7wMvEbQHM/WSItss1IcYUl53rWP35+1yYxn1QkWryylT4N6g4YCcLsU0pOzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:42.389344Z"},"content_sha256":"be4a55868687368b214b5ba734d45189819fd1b169ee0484de9b1b53f9e6eceb","schema_version":"1.0","event_id":"sha256:be4a55868687368b214b5ba734d45189819fd1b169ee0484de9b1b53f9e6eceb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SOKECH66RMDOF4TJUOEZFTW4ZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imbalanced Data Clustering via Targeted Data Augmentation Using GMM and LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdallah Alaa-Eddine Djamai, Imed Keraghel, Mohamed Nadif, Noor Khalal","submitted_at":"2026-05-19T08:33:01Z","abstract_excerpt":"In Natural Language Processing (NLP), dealing with underrepresented topics is challenging, especially in unsupervised tasks where clustering might not adequately capture minority topics. To tackle this challenge, our paper presents a novel unsupervised data augmentation method that integrates Gaussian Mixture Models (GMMs) and Large Language Models (LLMs). Due to their flexibility and robustness, GMMs can detect clusters corresponding to underrepresented areas in the data, while LLMs create synthetic documents to enrich these clusters and improve their representation. Experiments on various im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28635","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/2607.28635/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":"2026-08-03T00:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/NYB4XSd9xRUtuexs8X2M7R9Twzv1mgdstDd5pWrxRtVr4MSTwXaXOy8wO16f2Rz8gFS3S3YmKJy6leW/fPSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:42.389846Z"},"content_sha256":"d97b7e3a441751295559e9589e0abbb8e5de0461a490910a0b3a537d0eac6d59","schema_version":"1.0","event_id":"sha256:d97b7e3a441751295559e9589e0abbb8e5de0461a490910a0b3a537d0eac6d59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOKECH66RMDOF4TJUOEZFTW4ZK/bundle.json","state_url":"https://pith.science/pith/SOKECH66RMDOF4TJUOEZFTW4ZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOKECH66RMDOF4TJUOEZFTW4ZK/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":"2026-08-08T18:23:42Z","links":{"resolver":"https://pith.science/pith/SOKECH66RMDOF4TJUOEZFTW4ZK","bundle":"https://pith.science/pith/SOKECH66RMDOF4TJUOEZFTW4ZK/bundle.json","state":"https://pith.science/pith/SOKECH66RMDOF4TJUOEZFTW4ZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOKECH66RMDOF4TJUOEZFTW4ZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SOKECH66RMDOF4TJUOEZFTW4ZK","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":"d5f6f8a546130417c21f2ca668227b92d2a1f5e55ca19babdb971513f597132a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T08:33:01Z","title_canon_sha256":"94ef8f072f90c14ac5c4f29d150e551d5db20969b58f1909401d6586af2e4789"},"schema_version":"1.0","source":{"id":"2607.28635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28635","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28635v1","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28635","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"SOKECH66RMDO","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"SOKECH66RMDOF4TJ","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"SOKECH66","created_at":"2026-08-03T00:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:d97b7e3a441751295559e9589e0abbb8e5de0461a490910a0b3a537d0eac6d59","target":"graph","created_at":"2026-08-03T00:11:51Z","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/2607.28635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Natural Language Processing (NLP), dealing with underrepresented topics is challenging, especially in unsupervised tasks where clustering might not adequately capture minority topics. To tackle this challenge, our paper presents a novel unsupervised data augmentation method that integrates Gaussian Mixture Models (GMMs) and Large Language Models (LLMs). Due to their flexibility and robustness, GMMs can detect clusters corresponding to underrepresented areas in the data, while LLMs create synthetic documents to enrich these clusters and improve their representation. Experiments on various im","authors_text":"Abdallah Alaa-Eddine Djamai, Imed Keraghel, Mohamed Nadif, Noor Khalal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T08:33:01Z","title":"Imbalanced Data Clustering via Targeted Data Augmentation Using GMM and LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28635","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:be4a55868687368b214b5ba734d45189819fd1b169ee0484de9b1b53f9e6eceb","target":"record","created_at":"2026-08-03T00:11:51Z","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":"d5f6f8a546130417c21f2ca668227b92d2a1f5e55ca19babdb971513f597132a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T08:33:01Z","title_canon_sha256":"94ef8f072f90c14ac5c4f29d150e551d5db20969b58f1909401d6586af2e4789"},"schema_version":"1.0","source":{"id":"2607.28635","kind":"arxiv","version":1}},"canonical_sha256":"9394411fde8b06e2f269a38992cedccaae90b65496ecd5d1b4f946231634b8d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9394411fde8b06e2f269a38992cedccaae90b65496ecd5d1b4f946231634b8d4","first_computed_at":"2026-08-03T00:11:51.988502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T00:11:51.988502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gGuJTOQuurWf5Grpii8rvh63LX9y1jjapxm7qdyuFjNab6D8Tdt95pCSazQKQHRIafm/wzfC4nYrMRLryqCpCA==","signature_status":"signed_v1","signed_at":"2026-08-03T00:11:51.990657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be4a55868687368b214b5ba734d45189819fd1b169ee0484de9b1b53f9e6eceb","sha256:d97b7e3a441751295559e9589e0abbb8e5de0461a490910a0b3a537d0eac6d59"],"state_sha256":"07f3adab8a7cf0ca1f36680faf61be0aeaae0d8fb4129252c2076eb611de2acd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+sI5+Tk61i1f9dOI1XUZ4CIAcQdVLpfPOcmFVGsQmYFp9gzl/d96tw6wHFjd4iqBaEp9nj6XKDs0BrDQsXyXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:23:42.393916Z","bundle_sha256":"2ff7f14c0676f93c95838549427f00e1ed06062c3b8b425d7ec8d3eb046ebeec"}}