{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FYZ7LPVWVH7B5L5PWNKCPXUJ33","short_pith_number":"pith:FYZ7LPVW","schema_version":"1.0","canonical_sha256":"2e33f5beb6a9fe1eafafb35427de89def8a7104947fc75ec2ae166b690939c6f","source":{"kind":"arxiv","id":"2606.07492","version":1},"attestation_state":"computed","paper":{"title":"Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Alexander Derevyagin, Anton Lysenko, Askar Tsyganov, Daria Korovaitceva, Ekaterina Grishina, Evgeny Frolov, Ilya Ivanov, Margarita Rusanova, Sergey Samsonov, Stepan Kuznetsov, Uliana Parkina","submitted_at":"2026-06-05T17:46:36Z","abstract_excerpt":"The ranking of recommendation algorithms is a challenging problem since model performance is sensitive to dataset characteristics such as sparsity, sequential structure, and scale. This drives a demand for a proper methodology for fair comparison between algorithms. Naive aggregation of performance metrics (e.g., averaging NDCG over benchmarks) can yield misleading rankings, undermining practical selection. To address this problem, we introduce a novel, data-driven ranking methodology based on Bradley-Terry (BT) model. We demonstrate that the obtained ranking depends on key dataset statistics."},"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":"2606.07492","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-05T17:46:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ef8d6da8f2e849d9080b446a6a67f429a1646a66e51b3d922062a2ab4567cc5b","abstract_canon_sha256":"1437b107f214b96972cb3c7b7e8c7e9a711d3ad5a131c6c1f61263f378b73f24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:30.151332Z","signature_b64":"7v5H0vbEuhTHf/be6M60C8OySzz7OPF/IaQcfnpan4csU1XQO8L+ghdtWJu7oS7B8rfJvI+Ubj06i1t8/rPXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e33f5beb6a9fe1eafafb35427de89def8a7104947fc75ec2ae166b690939c6f","last_reissued_at":"2026-06-08T01:05:30.150723Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:30.150723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Alexander Derevyagin, Anton Lysenko, Askar Tsyganov, Daria Korovaitceva, Ekaterina Grishina, Evgeny Frolov, Ilya Ivanov, Margarita Rusanova, Sergey Samsonov, Stepan Kuznetsov, Uliana Parkina","submitted_at":"2026-06-05T17:46:36Z","abstract_excerpt":"The ranking of recommendation algorithms is a challenging problem since model performance is sensitive to dataset characteristics such as sparsity, sequential structure, and scale. This drives a demand for a proper methodology for fair comparison between algorithms. Naive aggregation of performance metrics (e.g., averaging NDCG over benchmarks) can yield misleading rankings, undermining practical selection. To address this problem, we introduce a novel, data-driven ranking methodology based on Bradley-Terry (BT) model. We demonstrate that the obtained ranking depends on key dataset statistics."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07492","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/2606.07492/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":"2606.07492","created_at":"2026-06-08T01:05:30.150816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07492v1","created_at":"2026-06-08T01:05:30.150816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07492","created_at":"2026-06-08T01:05:30.150816+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYZ7LPVWVH7B","created_at":"2026-06-08T01:05:30.150816+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYZ7LPVWVH7B5L5P","created_at":"2026-06-08T01:05:30.150816+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYZ7LPVW","created_at":"2026-06-08T01:05:30.150816+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/FYZ7LPVWVH7B5L5PWNKCPXUJ33","json":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33.json","graph_json":"https://pith.science/api/pith-number/FYZ7LPVWVH7B5L5PWNKCPXUJ33/graph.json","events_json":"https://pith.science/api/pith-number/FYZ7LPVWVH7B5L5PWNKCPXUJ33/events.json","paper":"https://pith.science/paper/FYZ7LPVW"},"agent_actions":{"view_html":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33","download_json":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33.json","view_paper":"https://pith.science/paper/FYZ7LPVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07492&json=true","fetch_graph":"https://pith.science/api/pith-number/FYZ7LPVWVH7B5L5PWNKCPXUJ33/graph.json","fetch_events":"https://pith.science/api/pith-number/FYZ7LPVWVH7B5L5PWNKCPXUJ33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33/action/storage_attestation","attest_author":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33/action/author_attestation","sign_citation":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33/action/citation_signature","submit_replication":"https://pith.science/pith/FYZ7LPVWVH7B5L5PWNKCPXUJ33/action/replication_record"}},"created_at":"2026-06-08T01:05:30.150816+00:00","updated_at":"2026-06-08T01:05:30.150816+00:00"}