{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QUHZ5UWFDDPQ4QKOCKVDJGVURR","short_pith_number":"pith:QUHZ5UWF","canonical_record":{"source":{"id":"2605.15085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T17:07:41Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ME"],"title_canon_sha256":"50c6fe4ecfc524301901fb2a8ce95613d4c82205e78ca65a54ea4187b6b7a0d3","abstract_canon_sha256":"1b30f3cda314cdbdaa29bc63ef231cd2bd5e44ba51f3939a6fee8b1a274758ae"},"schema_version":"1.0"},"canonical_sha256":"850f9ed2c518df0e414e12aa349ab48c4789af2509782ad75c75635d2182ee4a","source":{"kind":"arxiv","id":"2605.15085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15085","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15085v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"QUHZ5UWFDDPQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QUHZ5UWFDDPQ4QKO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QUHZ5UWF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QUHZ5UWFDDPQ4QKOCKVDJGVURR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T17:07:41Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ME"],"title_canon_sha256":"50c6fe4ecfc524301901fb2a8ce95613d4c82205e78ca65a54ea4187b6b7a0d3","abstract_canon_sha256":"1b30f3cda314cdbdaa29bc63ef231cd2bd5e44ba51f3939a6fee8b1a274758ae"},"schema_version":"1.0"},"canonical_sha256":"850f9ed2c518df0e414e12aa349ab48c4789af2509782ad75c75635d2182ee4a","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"850f9ed2c518df0e414e12aa349ab48c4789af2509782ad75c75635d2182ee4a","last_reissued_at":"2026-05-17T21:57:19.273748Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.963337Z"},"source_kind":"arxiv","source_id":"2605.15085","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":"2026-05-17T21:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfqIhoFEFy3MQsm/p+agUlvY5oHMYFliA1WvzXpOo1eoFpQeBG8+qJmxRD0lF6tfPxa/597s00B5SynTyCceDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:12:16.369285Z"},"content_sha256":"79fa4eca0047a12fdd6aecd3a12420f43a6d17eb701816af99477d0fa33dbfb1","schema_version":"1.0","event_id":"sha256:79fa4eca0047a12fdd6aecd3a12420f43a6d17eb701816af99477d0fa33dbfb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QUHZ5UWFDDPQ4QKOCKVDJGVURR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Data to Action: Accelerating Refinery Optimization with AI","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Transformed ECOD anomaly detection with pair selection reveals business opportunities and data errors in refinery LP plans.","cross_cats":["cs.LG","stat.AP","stat.ME"],"primary_cat":"stat.ML","authors_text":"\\'Abrah\\'am Papp, Botond Szil\\'agyi, D\\'aniel Pfeifer, Edith Alice Kov\\'acs, M\\'ark Czifra, Tam\\'as Zolt\\'an Varga, Tibor Bern\\'ath","submitted_at":"2026-05-14T17:07:41Z","abstract_excerpt":"Nowadays refinery optimization utilizes sheer amounts of data, which can be handled with modern Linear Programming (LP) software, but the interpreting and applying the results remains challenging. Large petrochemical companies use massive models, with hundreds of thousands of input matrix elements. The LP solution is mathematically correct, but simplifications are made in the model, and data supply errors may occur. Therefore, further insight is needed to trust the results. The LP solver does not have a memory, so additional understanding could be gained by analyzing historical data and compar"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A transformed version of the popular ECOD methodology is applied. New methods are proposed to handle high-dimensional data: choosing the most informative pairs. Then, this is used alongside two 2D Anomaly Detection algorithms, revealing several business opportunities and data supply errors in the MOL refinery scheduling and planning architecture.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That comparing current LP plans to historical data via the transformed ECOD and pair selection will reliably surface actionable anomalies without excessive false positives or loss of critical signals due to the high-dimensional reduction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A transformed ECOD anomaly detection approach with informative pair selection is applied to refinery LP data to reveal business opportunities and data supply errors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Transformed ECOD anomaly detection with pair selection reveals business opportunities and data errors in refinery LP plans.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8735d61b841053ec2aec86329cb482aefd50d580715091e2c02c10f16e8b9b31"},"source":{"id":"2605.15085","kind":"arxiv","version":1},"verdict":{"id":"ff2fa093-d7fd-47ba-8f0e-a0cccc5d7fa7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:15:26.311259Z","strongest_claim":"A transformed version of the popular ECOD methodology is applied. New methods are proposed to handle high-dimensional data: choosing the most informative pairs. Then, this is used alongside two 2D Anomaly Detection algorithms, revealing several business opportunities and data supply errors in the MOL refinery scheduling and planning architecture.","one_line_summary":"A transformed ECOD anomaly detection approach with informative pair selection is applied to refinery LP data to reveal business opportunities and data supply errors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That comparing current LP plans to historical data via the transformed ECOD and pair selection will reliably surface actionable anomalies without excessive false positives or loss of critical signals due to the high-dimensional reduction.","pith_extraction_headline":"Transformed ECOD anomaly detection with pair selection reveals business opportunities and data errors in refinery LP plans."},"references":{"count":23,"sample":[{"doi":"","year":2016,"title":"L. Rodríguez-Mazahua, C.-A. Rodríguez-Enríquez, J. L. Sánchez- Cervantes, J. Cervantes, J. L. García-Alcaraz, G. Alor-Hernández, A general perspective of big data: applications, tools, challenges and ","work_id":"4cf696a3-d3ac-4537-a3d9-833b7d004d98","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"M. Hamzehi, S. Hosseini, Business intelligence using machine learning algorithms, Multimedia tools and applications 81 (23) (2022) 33233– 33251","work_id":"0ba158c5-bec3-4d16-9915-f7cd389becea","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"M. Rath, Realization of business intelligence using machine learning, In- ternet of Things in Business Transformation: Developing an Engineering and Business Strategy for Industry 5.0 (2021) 169–184","work_id":"7955f6ac-1d76-4679-82e9-94898ac5c93e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"F. Ridzuan, W. M. N. W. Zainon, Diagnostic analysis for outlier de- tection in big data analytics, Procedia Computer Science 197 (2022) 685–692","work_id":"ba8f657d-9f5e-4729-8b3c-f71b43751c7c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"P. Larrañaga, D. Atienza, J. Diaz-Rozo, A. Ogbechie, C. E. Puerto- Santana, C. Bielza, Industrial applications of machine learning, CRC press, 2018","work_id":"2b838aa4-3b19-46e7-bdf0-265f39b6df9f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"df336bc0e0481efef791c8c20644783f0ee57c9f3765727a23c81d330acb4405","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":"ff2fa093-d7fd-47ba-8f0e-a0cccc5d7fa7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQvqwVVa7733/qRY2tGQueJRftzMYPaoSOZNsH4BZPPLxPNhDF270iI2t8JsdI7IYEiG0szFtLtavrnhWcB2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:12:16.369941Z"},"content_sha256":"ed7355b2852e2163888bc08968983eddff379869386a1336ab4657bb5daf6d67","schema_version":"1.0","event_id":"sha256:ed7355b2852e2163888bc08968983eddff379869386a1336ab4657bb5daf6d67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR/bundle.json","state_url":"https://pith.science/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR/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":"2026-06-10T18:12:16Z","links":{"resolver":"https://pith.science/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR","bundle":"https://pith.science/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR/bundle.json","state":"https://pith.science/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUHZ5UWFDDPQ4QKOCKVDJGVURR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QUHZ5UWFDDPQ4QKOCKVDJGVURR","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":"1b30f3cda314cdbdaa29bc63ef231cd2bd5e44ba51f3939a6fee8b1a274758ae","cross_cats_sorted":["cs.LG","stat.AP","stat.ME"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T17:07:41Z","title_canon_sha256":"50c6fe4ecfc524301901fb2a8ce95613d4c82205e78ca65a54ea4187b6b7a0d3"},"schema_version":"1.0","source":{"id":"2605.15085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15085","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15085v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"QUHZ5UWFDDPQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QUHZ5UWFDDPQ4QKO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QUHZ5UWF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ed7355b2852e2163888bc08968983eddff379869386a1336ab4657bb5daf6d67","target":"graph","created_at":"2026-05-17T21:57:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"A transformed version of the popular ECOD methodology is applied. New methods are proposed to handle high-dimensional data: choosing the most informative pairs. Then, this is used alongside two 2D Anomaly Detection algorithms, revealing several business opportunities and data supply errors in the MOL refinery scheduling and planning architecture."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That comparing current LP plans to historical data via the transformed ECOD and pair selection will reliably surface actionable anomalies without excessive false positives or loss of critical signals due to the high-dimensional reduction."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A transformed ECOD anomaly detection approach with informative pair selection is applied to refinery LP data to reveal business opportunities and data supply errors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Transformed ECOD anomaly detection with pair selection reveals business opportunities and data errors in refinery LP plans."}],"snapshot_sha256":"8735d61b841053ec2aec86329cb482aefd50d580715091e2c02c10f16e8b9b31"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Nowadays refinery optimization utilizes sheer amounts of data, which can be handled with modern Linear Programming (LP) software, but the interpreting and applying the results remains challenging. Large petrochemical companies use massive models, with hundreds of thousands of input matrix elements. The LP solution is mathematically correct, but simplifications are made in the model, and data supply errors may occur. Therefore, further insight is needed to trust the results. The LP solver does not have a memory, so additional understanding could be gained by analyzing historical data and compar","authors_text":"\\'Abrah\\'am Papp, Botond Szil\\'agyi, D\\'aniel Pfeifer, Edith Alice Kov\\'acs, M\\'ark Czifra, Tam\\'as Zolt\\'an Varga, Tibor Bern\\'ath","cross_cats":["cs.LG","stat.AP","stat.ME"],"headline":"Transformed ECOD anomaly detection with pair selection reveals business opportunities and data errors in refinery LP plans.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T17:07:41Z","title":"From Data to Action: Accelerating Refinery Optimization with AI"},"references":{"count":23,"internal_anchors":0,"resolved_work":23,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"L. Rodríguez-Mazahua, C.-A. Rodríguez-Enríquez, J. L. Sánchez- Cervantes, J. Cervantes, J. L. García-Alcaraz, G. Alor-Hernández, A general perspective of big data: applications, tools, challenges and ","work_id":"4cf696a3-d3ac-4537-a3d9-833b7d004d98","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"M. Hamzehi, S. Hosseini, Business intelligence using machine learning algorithms, Multimedia tools and applications 81 (23) (2022) 33233– 33251","work_id":"0ba158c5-bec3-4d16-9915-f7cd389becea","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"M. Rath, Realization of business intelligence using machine learning, In- ternet of Things in Business Transformation: Developing an Engineering and Business Strategy for Industry 5.0 (2021) 169–184","work_id":"7955f6ac-1d76-4679-82e9-94898ac5c93e","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"F. Ridzuan, W. M. N. W. Zainon, Diagnostic analysis for outlier de- tection in big data analytics, Procedia Computer Science 197 (2022) 685–692","work_id":"ba8f657d-9f5e-4729-8b3c-f71b43751c7c","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"P. Larrañaga, D. Atienza, J. Diaz-Rozo, A. Ogbechie, C. E. Puerto- Santana, C. Bielza, Industrial applications of machine learning, CRC press, 2018","work_id":"2b838aa4-3b19-46e7-bdf0-265f39b6df9f","year":2018}],"snapshot_sha256":"df336bc0e0481efef791c8c20644783f0ee57c9f3765727a23c81d330acb4405"},"source":{"id":"2605.15085","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:15:26.311259Z","id":"ff2fa093-d7fd-47ba-8f0e-a0cccc5d7fa7","model_set":{"reader":"grok-4.3"},"one_line_summary":"A transformed ECOD anomaly detection approach with informative pair selection is applied to refinery LP data to reveal business opportunities and data supply errors.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Transformed ECOD anomaly detection with pair selection reveals business opportunities and data errors in refinery LP plans.","strongest_claim":"A transformed version of the popular ECOD methodology is applied. New methods are proposed to handle high-dimensional data: choosing the most informative pairs. Then, this is used alongside two 2D Anomaly Detection algorithms, revealing several business opportunities and data supply errors in the MOL refinery scheduling and planning architecture.","weakest_assumption":"That comparing current LP plans to historical data via the transformed ECOD and pair selection will reliably surface actionable anomalies without excessive false positives or loss of critical signals due to the high-dimensional reduction."}},"verdict_id":"ff2fa093-d7fd-47ba-8f0e-a0cccc5d7fa7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79fa4eca0047a12fdd6aecd3a12420f43a6d17eb701816af99477d0fa33dbfb1","target":"record","created_at":"2026-05-17T21:18:33Z","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":"1b30f3cda314cdbdaa29bc63ef231cd2bd5e44ba51f3939a6fee8b1a274758ae","cross_cats_sorted":["cs.LG","stat.AP","stat.ME"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T17:07:41Z","title_canon_sha256":"50c6fe4ecfc524301901fb2a8ce95613d4c82205e78ca65a54ea4187b6b7a0d3"},"schema_version":"1.0","source":{"id":"2605.15085","kind":"arxiv","version":1}},"canonical_sha256":"850f9ed2c518df0e414e12aa349ab48c4789af2509782ad75c75635d2182ee4a","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"850f9ed2c518df0e414e12aa349ab48c4789af2509782ad75c75635d2182ee4a","first_computed_at":"2026-05-17T21:40:25.963337Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:19.273748Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79fa4eca0047a12fdd6aecd3a12420f43a6d17eb701816af99477d0fa33dbfb1","sha256:ed7355b2852e2163888bc08968983eddff379869386a1336ab4657bb5daf6d67"],"state_sha256":"9898f69db0f32f9b2be20cba5a1ed4e9ca45c86263081768ddefd5a93c3171bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8DdKUUG42TZxoT6rS179nRd5pWzHApaxArF5OPEbExFw2ZJJIgqiU6+MWiDy3GotSOnvm2f/kUU5HZd1ZHcmCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T18:12:16.372630Z","bundle_sha256":"41a4ef407d0571192b297996bcc74a0a320f714e946611df33c6d8359378b555"}}