{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H6ZWXPME4EXVFH4MHUXJLRWHQN","short_pith_number":"pith:H6ZWXPME","schema_version":"1.0","canonical_sha256":"3fb36bbd84e12f529f8c3d2e95c6c783405db780450f95c44d34d911aad7db4f","source":{"kind":"arxiv","id":"1807.10937","version":2},"attestation_state":"computed","paper":{"title":"PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Greg Slabaugh, Muhammad Asad, Rilwan Basaru, S M Masudur Rahman Al Arif","submitted_at":"2018-07-28T13:41:44Z","abstract_excerpt":"In recent years, Convolutional Neural Networks (CNNs) have enabled significant advancements to the state-of-the-art in computer vision. For classification tasks, CNNs have widely employed probabilistic output and have shown the significance of providing additional confidence for predictions. However, such probabilistic methodologies are not widely applicable for addressing regression problems using CNNs, as regression involves learning unconstrained continuous and, in many cases, multi-variate target variables. We propose a PRObabilistic Parametric rEgression Loss (PROPEL) that facilitates CNN"},"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":"1807.10937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-28T13:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"1f241d0c3e4425c904fe0cf6a028bdb8ab2dc83a0f5ea7fdb37b5a98937f756b","abstract_canon_sha256":"3719ca8d940d9a1c4e967ed0623a86f8faf6017cd44d608de5b06e79a871b5f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:33.524169Z","signature_b64":"5U/UZDEhnZ6xfEtZOlSbNh1AG4/AHQ1iujiSFAIUMyqGvu2cwwPSEHlz89BDxhglieTS2wSQFwNMY06RKQL5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fb36bbd84e12f529f8c3d2e95c6c783405db780450f95c44d34d911aad7db4f","last_reissued_at":"2026-07-05T01:25:33.523747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:33.523747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Greg Slabaugh, Muhammad Asad, Rilwan Basaru, S M Masudur Rahman Al Arif","submitted_at":"2018-07-28T13:41:44Z","abstract_excerpt":"In recent years, Convolutional Neural Networks (CNNs) have enabled significant advancements to the state-of-the-art in computer vision. For classification tasks, CNNs have widely employed probabilistic output and have shown the significance of providing additional confidence for predictions. However, such probabilistic methodologies are not widely applicable for addressing regression problems using CNNs, as regression involves learning unconstrained continuous and, in many cases, multi-variate target variables. We propose a PRObabilistic Parametric rEgression Loss (PROPEL) that facilitates CNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10937","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1807.10937/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":"1807.10937","created_at":"2026-07-05T01:25:33.523802+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10937v2","created_at":"2026-07-05T01:25:33.523802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10937","created_at":"2026-07-05T01:25:33.523802+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6ZWXPME4EXV","created_at":"2026-07-05T01:25:33.523802+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6ZWXPME4EXVFH4M","created_at":"2026-07-05T01:25:33.523802+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6ZWXPME","created_at":"2026-07-05T01:25:33.523802+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/H6ZWXPME4EXVFH4MHUXJLRWHQN","json":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN.json","graph_json":"https://pith.science/api/pith-number/H6ZWXPME4EXVFH4MHUXJLRWHQN/graph.json","events_json":"https://pith.science/api/pith-number/H6ZWXPME4EXVFH4MHUXJLRWHQN/events.json","paper":"https://pith.science/paper/H6ZWXPME"},"agent_actions":{"view_html":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN","download_json":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN.json","view_paper":"https://pith.science/paper/H6ZWXPME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10937&json=true","fetch_graph":"https://pith.science/api/pith-number/H6ZWXPME4EXVFH4MHUXJLRWHQN/graph.json","fetch_events":"https://pith.science/api/pith-number/H6ZWXPME4EXVFH4MHUXJLRWHQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN/action/storage_attestation","attest_author":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN/action/author_attestation","sign_citation":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN/action/citation_signature","submit_replication":"https://pith.science/pith/H6ZWXPME4EXVFH4MHUXJLRWHQN/action/replication_record"}},"created_at":"2026-07-05T01:25:33.523802+00:00","updated_at":"2026-07-05T01:25:33.523802+00:00"}