{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6AWQWGKGF4XR7MLTHDLXFGVCXA","short_pith_number":"pith:6AWQWGKG","schema_version":"1.0","canonical_sha256":"f02d0b19462f2f1fb17338d7729aa2b81c500a93a4824d3ef402b61c6655b874","source":{"kind":"arxiv","id":"1806.04613","version":1},"attestation_state":"computed","paper":{"title":"Improving Regression Performance with Distributional Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ehsan Imani, Martha White","submitted_at":"2018-06-12T15:42:25Z","abstract_excerpt":"There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such as by adding label noise, incorporating label ambiguity or using distillation. In parallel, there is some evidence from a regression setting in reinforcement learning that learning distributions can improve performance. In this work, we investigate the reasons for this improvement, in a regression setting. We introduce a novel distributional regression loss, "},"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":"1806.04613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T15:42:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9ccb212012e2c9d39781e70801f23927794990ab4ed0400d54ba491929f2de5","abstract_canon_sha256":"db28c01a54553923406994b57829d7374d398e73796b800a333fd71a31964dda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:33.205816Z","signature_b64":"CoAKVsGjg573//uypB07KMFB3+J7+sqxf6b9qf4HWOyvnsSu4ujc1lKJ6V2SaMj40zdhXvPMGEMhjVMOIN+qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f02d0b19462f2f1fb17338d7729aa2b81c500a93a4824d3ef402b61c6655b874","last_reissued_at":"2026-05-18T00:13:33.205306Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:33.205306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Regression Performance with Distributional Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ehsan Imani, Martha White","submitted_at":"2018-06-12T15:42:25Z","abstract_excerpt":"There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such as by adding label noise, incorporating label ambiguity or using distillation. In parallel, there is some evidence from a regression setting in reinforcement learning that learning distributions can improve performance. In this work, we investigate the reasons for this improvement, in a regression setting. We introduce a novel distributional regression loss, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04613","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1806.04613","created_at":"2026-05-18T00:13:33.205399+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04613v1","created_at":"2026-05-18T00:13:33.205399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04613","created_at":"2026-05-18T00:13:33.205399+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AWQWGKGF4XR","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AWQWGKGF4XR7MLT","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AWQWGKG","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA","json":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA.json","graph_json":"https://pith.science/api/pith-number/6AWQWGKGF4XR7MLTHDLXFGVCXA/graph.json","events_json":"https://pith.science/api/pith-number/6AWQWGKGF4XR7MLTHDLXFGVCXA/events.json","paper":"https://pith.science/paper/6AWQWGKG"},"agent_actions":{"view_html":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA","download_json":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA.json","view_paper":"https://pith.science/paper/6AWQWGKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04613&json=true","fetch_graph":"https://pith.science/api/pith-number/6AWQWGKGF4XR7MLTHDLXFGVCXA/graph.json","fetch_events":"https://pith.science/api/pith-number/6AWQWGKGF4XR7MLTHDLXFGVCXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/action/storage_attestation","attest_author":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/action/author_attestation","sign_citation":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/action/citation_signature","submit_replication":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/action/replication_record"}},"created_at":"2026-05-18T00:13:33.205399+00:00","updated_at":"2026-05-18T00:13:33.205399+00:00"}