{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:66GCTIJ3DYSCTTN4IQDH2HWFSD","short_pith_number":"pith:66GCTIJ3","schema_version":"1.0","canonical_sha256":"f78c29a13b1e2429cdbc44067d1ec590d4a5064dc216deef4dfded0faebb9d44","source":{"kind":"arxiv","id":"2605.17245","version":1},"attestation_state":"computed","paper":{"title":"An Efficient Machine Learning-based Framework for Detection and Prevention of Frauds in Telecom Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Random Forest detects telecom fraud at 99.9% accuracy after data balancing.","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Mishal Shah, Praveen Hegde","submitted_at":"2026-05-17T04:03:36Z","abstract_excerpt":"Telecommunication fraud is an acute problem that leads to substantial material losses and compromises the reliability of telecom systems worldwide. Only effective and efficient detection mechanisms can help to deal with these threats, though there are certain shifts in the approaches to fraud detection. This paper evaluates the performance of AI-driven models for fraud detection in telecommunication networks using Call Detail Record (CDR) datasets. This study focuses on fraud detection in telecom networks using the Telecom CDR dataset, which contains 101,174 customer records with 17 attributes"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.17245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2026-05-17T04:03:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f7e89a285814f86063cbd20320484c44161bbc22772f15abf2d565e7af32a90","abstract_canon_sha256":"b680743cda4f7255efc6052b29734ee4981188aa53e47ecb82682fcc949e1aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:47.309425Z","signature_b64":"MY3RVqxnw1jQq0DznjpI2oG6R2F5bcUXD86UxLFaOOb4PnHAkbkdIDaWJSXqhmSR1cFF6bSl2DEmUieR8QQ8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78c29a13b1e2429cdbc44067d1ec590d4a5064dc216deef4dfded0faebb9d44","last_reissued_at":"2026-05-20T00:03:47.308548Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:47.308548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Machine Learning-based Framework for Detection and Prevention of Frauds in Telecom Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Random Forest detects telecom fraud at 99.9% accuracy after data balancing.","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Mishal Shah, Praveen Hegde","submitted_at":"2026-05-17T04:03:36Z","abstract_excerpt":"Telecommunication fraud is an acute problem that leads to substantial material losses and compromises the reliability of telecom systems worldwide. Only effective and efficient detection mechanisms can help to deal with these threats, though there are certain shifts in the approaches to fraud detection. This paper evaluates the performance of AI-driven models for fraud detection in telecommunication networks using Call Detail Record (CDR) datasets. This study focuses on fraud detection in telecom networks using the Telecom CDR dataset, which contains 101,174 customer records with 17 attributes"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RF recorded a high level of accuracy at 99.9% while XGBoost at 99.7%. RF was seen to give the highest performance with an accuracy of 99.9% and precision of 99.9%, recall of 99.9% and F1-score of 99.9%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that performance metrics measured after SMOTE balancing and on the same dataset used for training reflect genuine generalization to unseen fraud patterns in live telecom networks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Random Forest achieves 99.9% accuracy, precision, recall and F1-score for fraud detection on a 101k-record telecom CDR dataset after Min-Max scaling and SMOTE.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Random Forest detects telecom fraud at 99.9% accuracy after data balancing.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"59765c23d85f671d2c125502aa9a0968eabae1b3ac32c9d49d60682e67529bfc"},"source":{"id":"2605.17245","kind":"arxiv","version":1},"verdict":{"id":"4792ee24-b9ce-4427-90e9-9081084634a5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T23:22:07.742799Z","strongest_claim":"RF recorded a high level of accuracy at 99.9% while XGBoost at 99.7%. RF was seen to give the highest performance with an accuracy of 99.9% and precision of 99.9%, recall of 99.9% and F1-score of 99.9%.","one_line_summary":"Random Forest achieves 99.9% accuracy, precision, recall and F1-score for fraud detection on a 101k-record telecom CDR dataset after Min-Max scaling and SMOTE.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that performance metrics measured after SMOTE balancing and on the same dataset used for training reflect genuine generalization to unseen fraud patterns in live telecom networks.","pith_extraction_headline":"Random Forest detects telecom fraud at 99.9% accuracy after data balancing."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17245/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:20.315838Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:31:11.941855Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.877124Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.793640Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4c75d9d5035122560a98ff3767d681a26cd0ed690778a859cad140b45f78f072"},"references":{"count":36,"sample":[{"doi":"10.30574/ijsra.2024.12.2.1456","year":2024,"title":"An examination of machine learning -based credit card fraud detection systems,","work_id":"17f51eed-32b1-469b-9950-828d949d7f88","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48175/ijarsct-14000u","year":2023,"title":"A Machine and Deep Learning Framework for Robust Health Insurance Fraud Detection and Prevention,","work_id":"dbadf4c1-4e58-4987-88b3-72fe105f4605","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.procs.2018.01.107","year":2018,"title":"ConvNets for fraud detection analysis,","work_id":"c3a1a58a-b744-4fc7-820e-42339faba8f1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"The Assessments Of Financial Risk Based On Renewable Energy Industry,","work_id":"b8ec7130-5103-479b-b30e-2dc28ae9d3af","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"The Machine Learning Based Regression Models Analysis For House Price Prediction,","work_id":"6f25dc2f-50fd-42b7-ab35-58b41fa37e99","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":36,"snapshot_sha256":"4f21554e834cb54e0f6d913f6044062879a0c138c221845ae15201039b318697","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"f2349010fa9af30c4d8c3b72f7fb4663cbc524097a2576db096d55a47f6d95d5"},"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":"2605.17245","created_at":"2026-05-20T00:03:47.308680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17245v1","created_at":"2026-05-20T00:03:47.308680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17245","created_at":"2026-05-20T00:03:47.308680+00:00"},{"alias_kind":"pith_short_12","alias_value":"66GCTIJ3DYSC","created_at":"2026-05-20T00:03:47.308680+00:00"},{"alias_kind":"pith_short_16","alias_value":"66GCTIJ3DYSCTTN4","created_at":"2026-05-20T00:03:47.308680+00:00"},{"alias_kind":"pith_short_8","alias_value":"66GCTIJ3","created_at":"2026-05-20T00:03:47.308680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD","json":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD.json","graph_json":"https://pith.science/api/pith-number/66GCTIJ3DYSCTTN4IQDH2HWFSD/graph.json","events_json":"https://pith.science/api/pith-number/66GCTIJ3DYSCTTN4IQDH2HWFSD/events.json","paper":"https://pith.science/paper/66GCTIJ3"},"agent_actions":{"view_html":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD","download_json":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD.json","view_paper":"https://pith.science/paper/66GCTIJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17245&json=true","fetch_graph":"https://pith.science/api/pith-number/66GCTIJ3DYSCTTN4IQDH2HWFSD/graph.json","fetch_events":"https://pith.science/api/pith-number/66GCTIJ3DYSCTTN4IQDH2HWFSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD/action/storage_attestation","attest_author":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD/action/author_attestation","sign_citation":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD/action/citation_signature","submit_replication":"https://pith.science/pith/66GCTIJ3DYSCTTN4IQDH2HWFSD/action/replication_record"}},"created_at":"2026-05-20T00:03:47.308680+00:00","updated_at":"2026-05-20T00:03:47.308680+00:00"}