{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UHFUBLEU5GUIXVDNV3JDJINZ22","short_pith_number":"pith:UHFUBLEU","schema_version":"1.0","canonical_sha256":"a1cb40ac94e9a88bd46daed234a1b9d680482a72b31c167bc49adae5484f4fc5","source":{"kind":"arxiv","id":"2605.15363","version":1},"attestation_state":"computed","paper":{"title":"PRB-RUPFormer: A Recursive Unified Probabilistic Transformer for Residual PRB Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single shared probabilistic Transformer trained across carriers forecasts residual PRBs with median error below 0.05 for one- and seven-day horizons.","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Ajay Rajkumar, Ismail Guvenc, Matti Hiltunen, Saad Masrur, Yuxuan Jiang","submitted_at":"2026-05-14T19:42:32Z","abstract_excerpt":"Accurate forecasting of residual Physical Resource Blocks (PRBs) is critical for proactive network slice provisioning, energy-efficient operation, and spectrum-aware decision making in cellular systems, where residual PRBs serve as a practical proxy for short- and medium-term spectrum availability. Existing PRB prediction methods typically rely only on historical PRB values and are trained independently per carrier or sector, limiting their ability to capture cross-carrier dependencies and providing no measure of forecast uncertainty. Moreover, point forecasts alone are insufficient for robust"},"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":"2605.15363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T19:42:32Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"eaf5ae96ac9bb3bd05dafdb49e953ab121afba93aabc104fb12c3e2f231dbb32","abstract_canon_sha256":"472e9d1108cf064b696ef3358cb447308d655cb1826b5ea689bb042137c9bd78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:54.522808Z","signature_b64":"dxBm4K3zWmZCaXtOrNhM4sj7ppaeANuzFzG3B7iUawrAdYyX9mJG1nbf1APQtqfSMy5sePXJlvSkf0rZILz8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1cb40ac94e9a88bd46daed234a1b9d680482a72b31c167bc49adae5484f4fc5","last_reissued_at":"2026-05-20T00:00:54.521846Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:54.521846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRB-RUPFormer: A Recursive Unified Probabilistic Transformer for Residual PRB Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single shared probabilistic Transformer trained across carriers forecasts residual PRBs with median error below 0.05 for one- and seven-day horizons.","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Ajay Rajkumar, Ismail Guvenc, Matti Hiltunen, Saad Masrur, Yuxuan Jiang","submitted_at":"2026-05-14T19:42:32Z","abstract_excerpt":"Accurate forecasting of residual Physical Resource Blocks (PRBs) is critical for proactive network slice provisioning, energy-efficient operation, and spectrum-aware decision making in cellular systems, where residual PRBs serve as a practical proxy for short- and medium-term spectrum availability. Existing PRB prediction methods typically rely only on historical PRB values and are trained independently per carrier or sector, limiting their ability to capture cross-carrier dependencies and providing no measure of forecast uncertainty. Moreover, point forecasts alone are insufficient for robust"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluations on six months of commercial LTE network data from multiple U.S. locations demonstrate median MAE below 0.05 and hit probabilities above 0.80 for both one-day and seven-day recursive forecasts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that a single shared model trained across all carriers and sectors can capture cross-carrier dependencies without site-specific overfitting or loss of local accuracy, as stated in the description of the unified training approach.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PRB-RUPFormer delivers recursive probabilistic forecasts of residual PRBs with median MAE below 0.05 and hit rates above 0.80 using a single shared model across carriers on real LTE data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single shared probabilistic Transformer trained across carriers forecasts residual PRBs with median error below 0.05 for one- and seven-day horizons.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1f0cfa87ff5613f29bf22b877cb2d8e56b86f46ea0424608ee9fc39be3d66fbe"},"source":{"id":"2605.15363","kind":"arxiv","version":1},"verdict":{"id":"2f9b00e6-2411-4d8f-ac36-8857c60f4565","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:44:51.451616Z","strongest_claim":"Evaluations on six months of commercial LTE network data from multiple U.S. locations demonstrate median MAE below 0.05 and hit probabilities above 0.80 for both one-day and seven-day recursive forecasts.","one_line_summary":"PRB-RUPFormer delivers recursive probabilistic forecasts of residual PRBs with median MAE below 0.05 and hit rates above 0.80 using a single shared model across carriers on real LTE data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that a single shared model trained across all carriers and sectors can capture cross-carrier dependencies without site-specific overfitting or loss of local accuracy, as stated in the description of the unified training approach.","pith_extraction_headline":"A single shared probabilistic Transformer trained across carriers forecasts residual PRBs with median error below 0.05 for one- and seven-day horizons."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15363/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:18.292937Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:56:30.139868Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.192837Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.741321Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ab4137e15fbe8eeb906e583a54fed7f25fc03e713d82b04c95e36b604ba367fe"},"references":{"count":13,"sample":[{"doi":"","year":2016,"title":"An overview of dynamic spectrum sharing: Ongoing initiatives, challenges, and a roadmap for future research,","work_id":"ab20dddd-8a5d-4099-b8be-6018bb02f1f4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Understand- ing O-RAN: Architecture, interfaces, algorithms, security, and research challenges,","work_id":"fb336400-e76c-4b02-837e-e9cdf011131a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Data-driven energy conservation in cellular networks: A systems approach,","work_id":"361ec533-e6c5-410e-b4a3-c796b7c24db2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Network downlink PRB utilization rate forecasting and evaluation method based on multi-feature construction,","work_id":"2bc4ed4f-c2ba-439c-a11c-cbd4576b4774","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Downlink throughput pre- diction in LTE cellular networks using time series forecasting,","work_id":"f9eada35-c895-4562-9dfa-468552e2c3fa","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"b27e064079970263b4800b21b9077ed0de42e1c4786339d48fb290a8c90c5036","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"541bd8bc7e21b312f61e29c1eea4599163b1af368eee7ca71b554c8ec87397c8"},"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":"2605.15363","created_at":"2026-05-20T00:00:54.521993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15363v1","created_at":"2026-05-20T00:00:54.521993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15363","created_at":"2026-05-20T00:00:54.521993+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHFUBLEU5GUI","created_at":"2026-05-20T00:00:54.521993+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHFUBLEU5GUIXVDN","created_at":"2026-05-20T00:00:54.521993+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHFUBLEU","created_at":"2026-05-20T00:00:54.521993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22","json":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22.json","graph_json":"https://pith.science/api/pith-number/UHFUBLEU5GUIXVDNV3JDJINZ22/graph.json","events_json":"https://pith.science/api/pith-number/UHFUBLEU5GUIXVDNV3JDJINZ22/events.json","paper":"https://pith.science/paper/UHFUBLEU"},"agent_actions":{"view_html":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22","download_json":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22.json","view_paper":"https://pith.science/paper/UHFUBLEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15363&json=true","fetch_graph":"https://pith.science/api/pith-number/UHFUBLEU5GUIXVDNV3JDJINZ22/graph.json","fetch_events":"https://pith.science/api/pith-number/UHFUBLEU5GUIXVDNV3JDJINZ22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22/action/storage_attestation","attest_author":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22/action/author_attestation","sign_citation":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22/action/citation_signature","submit_replication":"https://pith.science/pith/UHFUBLEU5GUIXVDNV3JDJINZ22/action/replication_record"}},"created_at":"2026-05-20T00:00:54.521993+00:00","updated_at":"2026-05-20T00:00:54.521993+00:00"}