{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LUWA4SBFCB4KBDG5OQT7NIN6SB","short_pith_number":"pith:LUWA4SBF","schema_version":"1.0","canonical_sha256":"5d2c0e48251078a08cdd7427f6a1be907668e70a055dfde514ba779605d5598b","source":{"kind":"arxiv","id":"2006.05139","version":3},"attestation_state":"computed","paper":{"title":"PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eli Simhayev, Gilad Katz, Lior Rokach","submitted_at":"2020-06-09T09:29:58Z","abstract_excerpt":"Improving the robustness of neural nets in regression tasks is key to their application in multiple domains. Deep learning-based approaches aim to achieve this goal either by improving their prediction of specific values (i.e., point prediction), or by producing prediction intervals (PIs) that quantify uncertainty. We present PIVEN, a deep neural network for producing both a PI and a value prediction. Our loss function expresses the value prediction as a function of the upper and lower bounds, thus ensuring that it falls within the interval without increasing model complexity. Moreover, our ap"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.05139","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T09:29:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5c0cea6e779ebac03ba6e5691e4931b70f158553478df1905b4f85be71cbf13f","abstract_canon_sha256":"63c19355d598ddeb48009d40ed26190f7fa6704a7abce58b190279459cf1f0b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:39.465675Z","signature_b64":"gahdy4KZpW7QnbNpb4AoaJ8CkRDyKT7f9ISur1wY1xGctoYJAuOI43e4dtKCN1uzpct416VeDQLwYc+jiCplBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d2c0e48251078a08cdd7427f6a1be907668e70a055dfde514ba779605d5598b","last_reissued_at":"2026-07-05T02:50:39.465240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:39.465240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eli Simhayev, Gilad Katz, Lior Rokach","submitted_at":"2020-06-09T09:29:58Z","abstract_excerpt":"Improving the robustness of neural nets in regression tasks is key to their application in multiple domains. Deep learning-based approaches aim to achieve this goal either by improving their prediction of specific values (i.e., point prediction), or by producing prediction intervals (PIs) that quantify uncertainty. We present PIVEN, a deep neural network for producing both a PI and a value prediction. Our loss function expresses the value prediction as a function of the upper and lower bounds, thus ensuring that it falls within the interval without increasing model complexity. Moreover, our ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05139","kind":"arxiv","version":3},"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/2006.05139/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.05139","created_at":"2026-07-05T02:50:39.465300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05139v3","created_at":"2026-07-05T02:50:39.465300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05139","created_at":"2026-07-05T02:50:39.465300+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUWA4SBFCB4K","created_at":"2026-07-05T02:50:39.465300+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUWA4SBFCB4KBDG5","created_at":"2026-07-05T02:50:39.465300+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUWA4SBF","created_at":"2026-07-05T02:50:39.465300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16324","citing_title":"Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB","json":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB.json","graph_json":"https://pith.science/api/pith-number/LUWA4SBFCB4KBDG5OQT7NIN6SB/graph.json","events_json":"https://pith.science/api/pith-number/LUWA4SBFCB4KBDG5OQT7NIN6SB/events.json","paper":"https://pith.science/paper/LUWA4SBF"},"agent_actions":{"view_html":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB","download_json":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB.json","view_paper":"https://pith.science/paper/LUWA4SBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05139&json=true","fetch_graph":"https://pith.science/api/pith-number/LUWA4SBFCB4KBDG5OQT7NIN6SB/graph.json","fetch_events":"https://pith.science/api/pith-number/LUWA4SBFCB4KBDG5OQT7NIN6SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB/action/storage_attestation","attest_author":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB/action/author_attestation","sign_citation":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB/action/citation_signature","submit_replication":"https://pith.science/pith/LUWA4SBFCB4KBDG5OQT7NIN6SB/action/replication_record"}},"created_at":"2026-07-05T02:50:39.465300+00:00","updated_at":"2026-07-05T02:50:39.465300+00:00"}