{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6KOUT3TSGJTJGG6YUYWH6HS6O7","short_pith_number":"pith:6KOUT3TS","schema_version":"1.0","canonical_sha256":"f29d49ee723266931bd8a62c7f1e5e77f8de4ef8f7628ad74a9ee8b59419bf84","source":{"kind":"arxiv","id":"1701.03077","version":10},"attestation_state":"computed","paper":{"title":"A General and Adaptive Robust Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jonathan T. Barron","submitted_at":"2017-01-11T17:39:14Z","abstract_excerpt":"We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which improves performance on basic vision tasks such as registration and clustering. Interpreting our loss as the negative log of a univariate density yields a general probability distribution that includes normal and Cauchy distributions as special cases. This probabilistic interpretati"},"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":"1701.03077","kind":"arxiv","version":10},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-11T17:39:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a74f566019746c240c29866c032def22367ade4374e46d47eb16d1bba824f8f0","abstract_canon_sha256":"2beff66df82a91633685a6e72975d22f708b801b801b6e2d93ef2267f85d57c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:22.814547Z","signature_b64":"JkfTY8l4nLSzTKPacs5MB6vTb/E9oncki47CKkLzqiq8CYcguuvM9sl062DmbLxeYfk4NMSr7tkYnCny28ItBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29d49ee723266931bd8a62c7f1e5e77f8de4ef8f7628ad74a9ee8b59419bf84","last_reissued_at":"2026-05-17T23:49:22.813773Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:22.813773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General and Adaptive Robust Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jonathan T. Barron","submitted_at":"2017-01-11T17:39:14Z","abstract_excerpt":"We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which improves performance on basic vision tasks such as registration and clustering. Interpreting our loss as the negative log of a univariate density yields a general probability distribution that includes normal and Cauchy distributions as special cases. This probabilistic interpretati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03077","kind":"arxiv","version":10},"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":"1701.03077","created_at":"2026-05-17T23:49:22.813875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.03077v10","created_at":"2026-05-17T23:49:22.813875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03077","created_at":"2026-05-17T23:49:22.813875+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KOUT3TSGJTJ","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KOUT3TSGJTJGG6Y","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KOUT3TS","created_at":"2026-05-18T12:31:03.183658+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/6KOUT3TSGJTJGG6YUYWH6HS6O7","json":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7.json","graph_json":"https://pith.science/api/pith-number/6KOUT3TSGJTJGG6YUYWH6HS6O7/graph.json","events_json":"https://pith.science/api/pith-number/6KOUT3TSGJTJGG6YUYWH6HS6O7/events.json","paper":"https://pith.science/paper/6KOUT3TS"},"agent_actions":{"view_html":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7","download_json":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7.json","view_paper":"https://pith.science/paper/6KOUT3TS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.03077&json=true","fetch_graph":"https://pith.science/api/pith-number/6KOUT3TSGJTJGG6YUYWH6HS6O7/graph.json","fetch_events":"https://pith.science/api/pith-number/6KOUT3TSGJTJGG6YUYWH6HS6O7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7/action/storage_attestation","attest_author":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7/action/author_attestation","sign_citation":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7/action/citation_signature","submit_replication":"https://pith.science/pith/6KOUT3TSGJTJGG6YUYWH6HS6O7/action/replication_record"}},"created_at":"2026-05-17T23:49:22.813875+00:00","updated_at":"2026-05-17T23:49:22.813875+00:00"}