{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6AWQWGKGF4XR7MLTHDLXFGVCXA","short_pith_number":"pith:6AWQWGKG","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"},"canonical_sha256":"f02d0b19462f2f1fb17338d7729aa2b81c500a93a4824d3ef402b61c6655b874","source":{"kind":"arxiv","id":"1806.04613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04613","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04613v1","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04613","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"6AWQWGKGF4XR","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6AWQWGKGF4XR7MLT","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6AWQWGKG","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6AWQWGKGF4XR7MLTHDLXFGVCXA","target":"record","payload":{"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"},"canonical_sha256":"f02d0b19462f2f1fb17338d7729aa2b81c500a93a4824d3ef402b61c6655b874","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"},"source_kind":"arxiv","source_id":"1806.04613","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":"2026-05-18T00:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zeHPo8fQlORZxxNbsoEvPWcxU0ZD1pxJUdtDSnkGl8uNYVvIe+8yQhmKPZV56tjFYHfewfyUxprv8aZKqxDQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:35:04.899795Z"},"content_sha256":"1a57aad26668b34b2bc52f17d7e2cebc06577d97b1b291cce24317f65bd208af","schema_version":"1.0","event_id":"sha256:1a57aad26668b34b2bc52f17d7e2cebc06577d97b1b291cce24317f65bd208af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6AWQWGKGF4XR7MLTHDLXFGVCXA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wz9pLoMNjkCSovavWs+k8MgcIL+fJwXK3Sa7eRS+gWYNFmlviY2pChT20MGHL84FJxhjZRF1WDlrqGCI+yIoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:35:04.900168Z"},"content_sha256":"9e5542de058a3e26709bad91638a6a5a35ec4f4916d9b28a31fc614862e77d5f","schema_version":"1.0","event_id":"sha256:9e5542de058a3e26709bad91638a6a5a35ec4f4916d9b28a31fc614862e77d5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/bundle.json","state_url":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/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":"2026-05-26T01:35:04Z","links":{"resolver":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA","bundle":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/bundle.json","state":"https://pith.science/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6AWQWGKGF4XR7MLTHDLXFGVCXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6AWQWGKGF4XR7MLTHDLXFGVCXA","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":"db28c01a54553923406994b57829d7374d398e73796b800a333fd71a31964dda","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T15:42:25Z","title_canon_sha256":"a9ccb212012e2c9d39781e70801f23927794990ab4ed0400d54ba491929f2de5"},"schema_version":"1.0","source":{"id":"1806.04613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04613","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04613v1","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04613","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"6AWQWGKGF4XR","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6AWQWGKGF4XR7MLT","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6AWQWGKG","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:9e5542de058a3e26709bad91638a6a5a35ec4f4916d9b28a31fc614862e77d5f","target":"graph","created_at":"2026-05-18T00:13:33Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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, ","authors_text":"Ehsan Imani, Martha White","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T15:42:25Z","title":"Improving Regression Performance with Distributional Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04613","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1a57aad26668b34b2bc52f17d7e2cebc06577d97b1b291cce24317f65bd208af","target":"record","created_at":"2026-05-18T00:13:33Z","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":"db28c01a54553923406994b57829d7374d398e73796b800a333fd71a31964dda","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T15:42:25Z","title_canon_sha256":"a9ccb212012e2c9d39781e70801f23927794990ab4ed0400d54ba491929f2de5"},"schema_version":"1.0","source":{"id":"1806.04613","kind":"arxiv","version":1}},"canonical_sha256":"f02d0b19462f2f1fb17338d7729aa2b81c500a93a4824d3ef402b61c6655b874","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f02d0b19462f2f1fb17338d7729aa2b81c500a93a4824d3ef402b61c6655b874","first_computed_at":"2026-05-18T00:13:33.205306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:33.205306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CoAKVsGjg573//uypB07KMFB3+J7+sqxf6b9qf4HWOyvnsSu4ujc1lKJ6V2SaMj40zdhXvPMGEMhjVMOIN+qCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:33.205816Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a57aad26668b34b2bc52f17d7e2cebc06577d97b1b291cce24317f65bd208af","sha256:9e5542de058a3e26709bad91638a6a5a35ec4f4916d9b28a31fc614862e77d5f"],"state_sha256":"677752c787f0768f654ad7f802985166773a8dc0757899922ebe60c2ad7c369d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zcRrheNyynkVwzhZvZb2G2STV/ZMiVfQRi5CsiuMnEc0hEIjVDLksB3FWRhjpZZ6e0/QciAYXIFQXqnMgVm5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:35:04.903502Z","bundle_sha256":"8b319c8817a93daf753385bf1125af9e2e9a191d56cfb549d604988d86ce5e13"}}