{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QDIWXCPM2BGXXNP554FJZEFEG5","short_pith_number":"pith:QDIWXCPM","schema_version":"1.0","canonical_sha256":"80d16b89ecd04d7bb5fdef0a9c90a4375389be4758b23339d62d089945976069","source":{"kind":"arxiv","id":"2411.12032","version":2},"attestation_state":"computed","paper":{"title":"Machine Learning Evaluation Metric Discrepancies across Programming Languages and Their Components: Need for Standardization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SE","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Arman Rahmim, Ghazal Mousavi, Ilker Hacihaliloglu, Mehrdad Oveisi, Mohammad R. Salmanpour, Morteza Alizadeh, Saba Sadeghi, Sajad Amiri","submitted_at":"2024-11-18T20:07:31Z","abstract_excerpt":"This study evaluates metrics for tasks such as classification, regression, clustering, correlation analysis, statistical tests, segmentation, and image-to-image (I2I) translation. Metrics were compared across Python libraries, R packages, and Matlab functions to assess their consistency and highlight discrepancies. The findings underscore the need for a unified roadmap to standardize metrics, ensuring reliable and reproducible ML evaluations across platforms. This study examined a wide range of evaluation metrics across various tasks and found only some to be consistent across platforms, such "},"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":"2411.12032","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T20:07:31Z","cross_cats_sorted":["cs.SE","physics.comp-ph"],"title_canon_sha256":"6edfc689985b041c869313477e3342c414f3232529add03e3d268f8f2865cc8c","abstract_canon_sha256":"e922f6b627228134a56b8dc732b0a1836b213b3d44481753782ef955b48e01c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:19.764018Z","signature_b64":"i1q2JtDr3Qh8Wg5Dq+dzRy9ISu4m6lB/Wb3bqlNrz3cSgRqWwKpGGIBVqJn5Dn6MJYUMRDPy9M3JPulIpneDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80d16b89ecd04d7bb5fdef0a9c90a4375389be4758b23339d62d089945976069","last_reissued_at":"2026-07-05T10:27:19.763166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:19.763166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning Evaluation Metric Discrepancies across Programming Languages and Their Components: Need for Standardization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SE","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Arman Rahmim, Ghazal Mousavi, Ilker Hacihaliloglu, Mehrdad Oveisi, Mohammad R. Salmanpour, Morteza Alizadeh, Saba Sadeghi, Sajad Amiri","submitted_at":"2024-11-18T20:07:31Z","abstract_excerpt":"This study evaluates metrics for tasks such as classification, regression, clustering, correlation analysis, statistical tests, segmentation, and image-to-image (I2I) translation. Metrics were compared across Python libraries, R packages, and Matlab functions to assess their consistency and highlight discrepancies. The findings underscore the need for a unified roadmap to standardize metrics, ensuring reliable and reproducible ML evaluations across platforms. This study examined a wide range of evaluation metrics across various tasks and found only some to be consistent across platforms, such "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12032","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/2411.12032/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":"2411.12032","created_at":"2026-07-05T10:27:19.763274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12032v2","created_at":"2026-07-05T10:27:19.763274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12032","created_at":"2026-07-05T10:27:19.763274+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDIWXCPM2BGX","created_at":"2026-07-05T10:27:19.763274+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDIWXCPM2BGXXNP5","created_at":"2026-07-05T10:27:19.763274+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDIWXCPM","created_at":"2026-07-05T10:27:19.763274+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/QDIWXCPM2BGXXNP554FJZEFEG5","json":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5.json","graph_json":"https://pith.science/api/pith-number/QDIWXCPM2BGXXNP554FJZEFEG5/graph.json","events_json":"https://pith.science/api/pith-number/QDIWXCPM2BGXXNP554FJZEFEG5/events.json","paper":"https://pith.science/paper/QDIWXCPM"},"agent_actions":{"view_html":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5","download_json":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5.json","view_paper":"https://pith.science/paper/QDIWXCPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12032&json=true","fetch_graph":"https://pith.science/api/pith-number/QDIWXCPM2BGXXNP554FJZEFEG5/graph.json","fetch_events":"https://pith.science/api/pith-number/QDIWXCPM2BGXXNP554FJZEFEG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5/action/storage_attestation","attest_author":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5/action/author_attestation","sign_citation":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5/action/citation_signature","submit_replication":"https://pith.science/pith/QDIWXCPM2BGXXNP554FJZEFEG5/action/replication_record"}},"created_at":"2026-07-05T10:27:19.763274+00:00","updated_at":"2026-07-05T10:27:19.763274+00:00"}