{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W375HDFYHXEIMDOZAU6L73IJRF","short_pith_number":"pith:W375HDFY","schema_version":"1.0","canonical_sha256":"b6ffd38cb83dc8860dd9053cbfed09895cbc41aa3562ab7e886d58bbbb7b75c2","source":{"kind":"arxiv","id":"2209.02055","version":1},"attestation_state":"computed","paper":{"title":"Full Kullback-Leibler-Divergence Loss for Hyperparameter-free Label Distribution Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Bauckhage, Maurice G\\\"under, Nico Piatkowski","submitted_at":"2022-09-05T17:01:46Z","abstract_excerpt":"The concept of Label Distribution Learning (LDL) is a technique to stabilize classification and regression problems with ambiguous and/or imbalanced labels. A prototypical use-case of LDL is human age estimation based on profile images. Regarding this regression problem, a so called Deep Label Distribution Learning (DLDL) method has been developed. The main idea is the joint regression of the label distribution and its expectation value. However, the original DLDL method uses loss components with different mathematical motivation and, thus, different scales, which is why the use of a hyperpara"},"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":"2209.02055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T17:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"59ab68cfcb8e1480011ea3bd0107fbd7bc031adaa8692fb659d96847d49f3ae3","abstract_canon_sha256":"fb77cf531eceed573b0673a2330e61b0229838e5e6bcc2e2a3bab7acbc5f1400"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:37.481167Z","signature_b64":"04viBYo5HfmuCaZfIEeranq4rkSxGV3tkRp57uZ/CZ8WiP1Vy4oLEWlJnFlkJid4f7qEu6v0YZpgfF6R4+MODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6ffd38cb83dc8860dd9053cbfed09895cbc41aa3562ab7e886d58bbbb7b75c2","last_reissued_at":"2026-07-05T04:54:37.480809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:37.480809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Full Kullback-Leibler-Divergence Loss for Hyperparameter-free Label Distribution Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Bauckhage, Maurice G\\\"under, Nico Piatkowski","submitted_at":"2022-09-05T17:01:46Z","abstract_excerpt":"The concept of Label Distribution Learning (LDL) is a technique to stabilize classification and regression problems with ambiguous and/or imbalanced labels. A prototypical use-case of LDL is human age estimation based on profile images. Regarding this regression problem, a so called Deep Label Distribution Learning (DLDL) method has been developed. The main idea is the joint regression of the label distribution and its expectation value. However, the original DLDL method uses loss components with different mathematical motivation and, thus, different scales, which is why the use of a hyperpara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.02055","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.02055/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":"2209.02055","created_at":"2026-07-05T04:54:37.480866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.02055v1","created_at":"2026-07-05T04:54:37.480866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.02055","created_at":"2026-07-05T04:54:37.480866+00:00"},{"alias_kind":"pith_short_12","alias_value":"W375HDFYHXEI","created_at":"2026-07-05T04:54:37.480866+00:00"},{"alias_kind":"pith_short_16","alias_value":"W375HDFYHXEIMDOZ","created_at":"2026-07-05T04:54:37.480866+00:00"},{"alias_kind":"pith_short_8","alias_value":"W375HDFY","created_at":"2026-07-05T04:54:37.480866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01458","citing_title":"The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF","json":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF.json","graph_json":"https://pith.science/api/pith-number/W375HDFYHXEIMDOZAU6L73IJRF/graph.json","events_json":"https://pith.science/api/pith-number/W375HDFYHXEIMDOZAU6L73IJRF/events.json","paper":"https://pith.science/paper/W375HDFY"},"agent_actions":{"view_html":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF","download_json":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF.json","view_paper":"https://pith.science/paper/W375HDFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.02055&json=true","fetch_graph":"https://pith.science/api/pith-number/W375HDFYHXEIMDOZAU6L73IJRF/graph.json","fetch_events":"https://pith.science/api/pith-number/W375HDFYHXEIMDOZAU6L73IJRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF/action/storage_attestation","attest_author":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF/action/author_attestation","sign_citation":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF/action/citation_signature","submit_replication":"https://pith.science/pith/W375HDFYHXEIMDOZAU6L73IJRF/action/replication_record"}},"created_at":"2026-07-05T04:54:37.480866+00:00","updated_at":"2026-07-05T04:54:37.480866+00:00"}