{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LSVUOY7CWU2W6MNZDZWT37GNWV","short_pith_number":"pith:LSVUOY7C","schema_version":"1.0","canonical_sha256":"5cab4763e2b5356f31b91e6d3dfccdb54a12fed56449bc1c5d1f3c5477ee11cf","source":{"kind":"arxiv","id":"2605.23563","version":1},"attestation_state":"computed","paper":{"title":"MARS: Magnitude-Aware Rank Statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Afsaneh M. Nejad, Arthur Zimek, Muhammad Rajabinasab","submitted_at":"2026-05-22T12:29:53Z","abstract_excerpt":"Comprehensive evaluation of machine learning models is the key to make sure that they perform as robustly and consistently as desired. In order to summarize the experimental results and pick a winner, Critical Difference (CD) diagrams are used. Standard CD diagrams rely on discrete ranks, discarding the magnitude of performance gaps between models, raising an issue which we call magnitude-blindness. In order to address this issue, we propose Magnitude-Aware Rank Statistics (MARS) that incorporates a relative margin coefficient as a weight for the discrete ranks. This coefficient scales ranks b"},"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":"2605.23563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:29:53Z","cross_cats_sorted":[],"title_canon_sha256":"e24f6001dfa7c46460431e13e2a8533985415669a53b37a8caa828197105e335","abstract_canon_sha256":"60e0977e790ff12f98f353d208db92175834ea347a2d0efde271e1e3467f81a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:19.643228Z","signature_b64":"mnQfaFJT1uIp2a3LzXZVhLZM6+U+4cM8eRYUvvaF+VlnVjnZyFpU/DbQO8MJPIDRv5cOuezGZIE6NHzrsOuDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cab4763e2b5356f31b91e6d3dfccdb54a12fed56449bc1c5d1f3c5477ee11cf","last_reissued_at":"2026-05-25T02:02:19.642436Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:19.642436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARS: Magnitude-Aware Rank Statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Afsaneh M. Nejad, Arthur Zimek, Muhammad Rajabinasab","submitted_at":"2026-05-22T12:29:53Z","abstract_excerpt":"Comprehensive evaluation of machine learning models is the key to make sure that they perform as robustly and consistently as desired. In order to summarize the experimental results and pick a winner, Critical Difference (CD) diagrams are used. Standard CD diagrams rely on discrete ranks, discarding the magnitude of performance gaps between models, raising an issue which we call magnitude-blindness. In order to address this issue, we propose Magnitude-Aware Rank Statistics (MARS) that incorporates a relative margin coefficient as a weight for the discrete ranks. This coefficient scales ranks b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23563","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/2605.23563/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":"2605.23563","created_at":"2026-05-25T02:02:19.642553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23563v1","created_at":"2026-05-25T02:02:19.642553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23563","created_at":"2026-05-25T02:02:19.642553+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSVUOY7CWU2W","created_at":"2026-05-25T02:02:19.642553+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSVUOY7CWU2W6MNZ","created_at":"2026-05-25T02:02:19.642553+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSVUOY7C","created_at":"2026-05-25T02:02:19.642553+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/LSVUOY7CWU2W6MNZDZWT37GNWV","json":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV.json","graph_json":"https://pith.science/api/pith-number/LSVUOY7CWU2W6MNZDZWT37GNWV/graph.json","events_json":"https://pith.science/api/pith-number/LSVUOY7CWU2W6MNZDZWT37GNWV/events.json","paper":"https://pith.science/paper/LSVUOY7C"},"agent_actions":{"view_html":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV","download_json":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV.json","view_paper":"https://pith.science/paper/LSVUOY7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23563&json=true","fetch_graph":"https://pith.science/api/pith-number/LSVUOY7CWU2W6MNZDZWT37GNWV/graph.json","fetch_events":"https://pith.science/api/pith-number/LSVUOY7CWU2W6MNZDZWT37GNWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV/action/storage_attestation","attest_author":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV/action/author_attestation","sign_citation":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV/action/citation_signature","submit_replication":"https://pith.science/pith/LSVUOY7CWU2W6MNZDZWT37GNWV/action/replication_record"}},"created_at":"2026-05-25T02:02:19.642553+00:00","updated_at":"2026-05-25T02:02:19.642553+00:00"}