{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPS6CQUU7HUMIMKH7WUIXUIM3U","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":"383490907eedfcc7b35269f2d69d9ef00d02a89085c7aa3419f049a6124a85c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T14:03:22Z","title_canon_sha256":"63b9c143f0c827f4faad60df208187acac1c196a3b75027f7a78ff8edb382728"},"schema_version":"1.0","source":{"id":"2412.14867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14867","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14867v1","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14867","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"KPS6CQUU7HUM","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"KPS6CQUU7HUMIMKH","created_at":"2026-07-05T09:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"KPS6CQUU","created_at":"2026-07-05T09:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:e0019a1794202ae43521c67ee29bdce11a4a3ff1c24ac47b25130ec66cecbbdb","target":"graph","created_at":"2026-07-05T09:51:53Z","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/2412.14867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in machine learning, particularly Large Language Models (LLMs) such as BERT and GPT, provide rich contextual embeddings that improve text representation. However, current document clustering approaches often ignore the deeper relationships between named entities (NEs) and the potential of LLM embeddings. This paper proposes a novel approach that integrates Named Entity Recognition (NER) and LLM embeddings within a graph-based framework for document clustering. The method builds a graph with nodes representing documents and edges weighted by named entity similarity, optimized us","authors_text":"Imed Keraghel, Mohamed Nadif","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T14:03:22Z","title":"Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14867","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":"sha256:1f97b8e1a188d0d520e6ae27eaf5cd408e09158b8573e4d6eebc3722770cda48","target":"record","created_at":"2026-07-05T09:51:53Z","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":"383490907eedfcc7b35269f2d69d9ef00d02a89085c7aa3419f049a6124a85c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T14:03:22Z","title_canon_sha256":"63b9c143f0c827f4faad60df208187acac1c196a3b75027f7a78ff8edb382728"},"schema_version":"1.0","source":{"id":"2412.14867","kind":"arxiv","version":1}},"canonical_sha256":"53e5e14294f9e8c43147fda88bd10cdd2ee57474721fdf53a8018c520934caea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e5e14294f9e8c43147fda88bd10cdd2ee57474721fdf53a8018c520934caea","first_computed_at":"2026-07-05T09:51:53.787393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:53.787393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uuv7Kg6w4rywYtYvx1BIuOjjbp2tMn0L7W5W8RJgLeGUglMdziAOaPHfj6GNxsb9y2oNfbh+8QOlLSV+G+OwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:53.787790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f97b8e1a188d0d520e6ae27eaf5cd408e09158b8573e4d6eebc3722770cda48","sha256:e0019a1794202ae43521c67ee29bdce11a4a3ff1c24ac47b25130ec66cecbbdb"],"state_sha256":"69e583aaf28a873c4fc55dcede90ed10c562a83911493c465957d430d928cc96"}