{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J4UBB3UIKDWTXFV4LOJ76JWYUT","short_pith_number":"pith:J4UBB3UI","schema_version":"1.0","canonical_sha256":"4f2810ee8850ed3b96bc5b93ff26d8a4f4522b55dfc413d2d592c6cb560c44d0","source":{"kind":"arxiv","id":"1804.06504","version":2},"attestation_state":"computed","paper":{"title":"Learning how to be robust: Deep polynomial regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juan-Manuel Perez-Rua, Patrick Bouthemy, Patrick Perez, Tomas Crivelli","submitted_at":"2018-04-17T23:36:12Z","abstract_excerpt":"Polynomial regression is a recurrent problem with a large number of applications. In computer vision it often appears in motion analysis. Whatever the application, standard methods for regression of polynomial models tend to deliver biased results when the input data is heavily contaminated by outliers. Moreover, the problem is even harder when outliers have strong structure. Departing from problem-tailored heuristics for robust estimation of parametric models, we explore deep convolutional neural networks. Our work aims to find a generic approach for training deep regression models without th"},"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":"1804.06504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-17T23:36:12Z","cross_cats_sorted":[],"title_canon_sha256":"221f80744e7cb8ccdbaeac28cba151f8b80f9224a09c05f80c3e883f1c09a901","abstract_canon_sha256":"1b6c7c74b96c8bde719ac6ca852665b7fc6809d5abe92933265c529ef807bb96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.552085Z","signature_b64":"Vf5yEQbpdOk7n0S+eZMTRQ+i4PpKjCUlBMHwWWKyNyeizcnn5Zs3bgnpg2jzHFQGr84cVf+PU0z+SHXh4MgtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f2810ee8850ed3b96bc5b93ff26d8a4f4522b55dfc413d2d592c6cb560c44d0","last_reissued_at":"2026-05-18T00:15:09.551483Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.551483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning how to be robust: Deep polynomial regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juan-Manuel Perez-Rua, Patrick Bouthemy, Patrick Perez, Tomas Crivelli","submitted_at":"2018-04-17T23:36:12Z","abstract_excerpt":"Polynomial regression is a recurrent problem with a large number of applications. In computer vision it often appears in motion analysis. Whatever the application, standard methods for regression of polynomial models tend to deliver biased results when the input data is heavily contaminated by outliers. Moreover, the problem is even harder when outliers have strong structure. Departing from problem-tailored heuristics for robust estimation of parametric models, we explore deep convolutional neural networks. Our work aims to find a generic approach for training deep regression models without th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06504","kind":"arxiv","version":2},"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":"1804.06504","created_at":"2026-05-18T00:15:09.551576+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06504v2","created_at":"2026-05-18T00:15:09.551576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06504","created_at":"2026-05-18T00:15:09.551576+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4UBB3UIKDWT","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4UBB3UIKDWTXFV4","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4UBB3UI","created_at":"2026-05-18T12:32:31.084164+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/J4UBB3UIKDWTXFV4LOJ76JWYUT","json":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT.json","graph_json":"https://pith.science/api/pith-number/J4UBB3UIKDWTXFV4LOJ76JWYUT/graph.json","events_json":"https://pith.science/api/pith-number/J4UBB3UIKDWTXFV4LOJ76JWYUT/events.json","paper":"https://pith.science/paper/J4UBB3UI"},"agent_actions":{"view_html":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT","download_json":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT.json","view_paper":"https://pith.science/paper/J4UBB3UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06504&json=true","fetch_graph":"https://pith.science/api/pith-number/J4UBB3UIKDWTXFV4LOJ76JWYUT/graph.json","fetch_events":"https://pith.science/api/pith-number/J4UBB3UIKDWTXFV4LOJ76JWYUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT/action/storage_attestation","attest_author":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT/action/author_attestation","sign_citation":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT/action/citation_signature","submit_replication":"https://pith.science/pith/J4UBB3UIKDWTXFV4LOJ76JWYUT/action/replication_record"}},"created_at":"2026-05-18T00:15:09.551576+00:00","updated_at":"2026-05-18T00:15:09.551576+00:00"}