{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7PSRDRVIFUCQ4RGPDL2ZRFTJ4R","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":"105e9a22547ee43022a7a04b736fde54cd556baebbccf9ae714542cabcdbf80d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T09:21:33Z","title_canon_sha256":"a62c7b9dc0c8600cf90d3ccb8937680f251faecbae6d5fc7f2c8d872eded21de"},"schema_version":"1.0","source":{"id":"2605.15761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15761","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15761v1","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15761","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"7PSRDRVIFUCQ","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"7PSRDRVIFUCQ4RGP","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"7PSRDRVI","created_at":"2026-05-20T00:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:2c1b060c307371f0982d524fded8f7be75a2ed3670fed5142ac53bcf74e0ad15","target":"graph","created_at":"2026-05-20T00:01:16Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.763431Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.955091Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15761/integrity.json","findings":[],"snapshot_sha256":"27cbd802131d70fec3a5c691dd163ff9ea8faa6066fbb2c5d5036ce017d4595c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluation leaderboards such as LMArena play a central role in benchmarking large language models by aggregating pairwise human preferences into model rankings, yet the robustness of these rankings remains poorly understood. We present a unified perturbation framework for analyzing Bradley-Terry leaderboards under structured data modifications using influence-based approximations. Our framework studies three match-level perturbations -- Drop, Add, and Flip -- together with player removal, and evaluates their effects on top-k membership, global ranking consistency via Kendall's tau, and confide","authors_text":"Amir-Hossein Karimi, Hosna Oyarhoseini, Jimmy Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T09:21:33Z","title":"A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15761","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:f5a39b3dfaf592d3ab84540b1c48b7fb33ceac1916ba941c231823c574af5d93","target":"record","created_at":"2026-05-20T00:01:16Z","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":"105e9a22547ee43022a7a04b736fde54cd556baebbccf9ae714542cabcdbf80d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T09:21:33Z","title_canon_sha256":"a62c7b9dc0c8600cf90d3ccb8937680f251faecbae6d5fc7f2c8d872eded21de"},"schema_version":"1.0","source":{"id":"2605.15761","kind":"arxiv","version":1}},"canonical_sha256":"fbe511c6a82d050e44cf1af5989669e47e53a8eb0a3e73f21bf120805a73b5b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbe511c6a82d050e44cf1af5989669e47e53a8eb0a3e73f21bf120805a73b5b5","first_computed_at":"2026-05-20T00:01:16.827020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:16.827020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OsaVekoYATDPY0X3keC/TyNvfkeA0xg2XNdfSEXys1QKg6XcWRkJNIAM7FWfY1Nevh95TSMSEMU0IpNOz/azBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:16.827670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5a39b3dfaf592d3ab84540b1c48b7fb33ceac1916ba941c231823c574af5d93","sha256:2c1b060c307371f0982d524fded8f7be75a2ed3670fed5142ac53bcf74e0ad15"],"state_sha256":"37bf6ce579ee78e2fb0a049c6df525a961a42a16f51eb4529dda8748a42bc3d4"}