{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7BGL4DYGLG6T7T6TJXYPQ3ILQA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2069e20484b54b33b41c3be0123881596685f3bf5bb19bc2c14e9da93bf0ec67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T13:40:00Z","title_canon_sha256":"7132f337f380bad2a733d8c7be6e0985d642dbc78947ae6053db52c6d5785a1d"},"schema_version":"1.0","source":{"id":"2605.23628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23628","created_at":"2026-05-25T02:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23628v1","created_at":"2026-05-25T02:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23628","created_at":"2026-05-25T02:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"7BGL4DYGLG6T","created_at":"2026-05-25T02:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"7BGL4DYGLG6T7T6T","created_at":"2026-05-25T02:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"7BGL4DYG","created_at":"2026-05-25T02:02:22Z"}],"graph_snapshots":[{"event_id":"sha256:0c7f0277b7f0c86b88bf92abf0b4a7200a4a2e1d08aba5c3bd9b693506161882","target":"graph","created_at":"2026-05-25T02:02:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.23628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task benchmarks have become a central pillar of machine learning research, yet their growing influence has incentivised benchmark gaming -- strategic actions taken to improve the leaderboard rank of a specific model. Treating datasets as voters and models as candidates, we consider benchmark-specific training -- the inclusion of benchmark data in training -- as a form of election manipulation. For any ordinal benchmark, the problem of choosing datasets to train on so that a target model becomes top-ranked corresponds to shift bribery, a class of manipulation problems from computational s","authors_text":"Christoph Jansen, Frauke Kreuter, Georg Schollmeyer, Polina Gordienko","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T13:40:00Z","title":"How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23628","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2b312458442f22fe2cb7cdd019ad48ec818a28b13aeca283792208a85d85804","target":"record","created_at":"2026-05-25T02:02:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2069e20484b54b33b41c3be0123881596685f3bf5bb19bc2c14e9da93bf0ec67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T13:40:00Z","title_canon_sha256":"7132f337f380bad2a733d8c7be6e0985d642dbc78947ae6053db52c6d5785a1d"},"schema_version":"1.0","source":{"id":"2605.23628","kind":"arxiv","version":1}},"canonical_sha256":"f84cbe0f0659bd3fcfd34df0f86d0b8016c4dac579dc1ca3484577296124927a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f84cbe0f0659bd3fcfd34df0f86d0b8016c4dac579dc1ca3484577296124927a","first_computed_at":"2026-05-25T02:02:22.761578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:22.761578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SUDTXec8XB7JW0XaPk/mXIuDdJ2VWtM9gUwHeqfXu3zK4YJy5lQthof0BhkAOhFQdPGkUT+nvrGRwcBKtoQ2Dw==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:22.762228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2b312458442f22fe2cb7cdd019ad48ec818a28b13aeca283792208a85d85804","sha256:0c7f0277b7f0c86b88bf92abf0b4a7200a4a2e1d08aba5c3bd9b693506161882"],"state_sha256":"f6f32f095373036bc4905796d61244f74398abbeda5e2a99ae3d50ab64ac0709"}