{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HFKFWDX44B7NOJRBF4CH3P43VP","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":"383536ba663111d838022b30f69eb87b3982378138e25f86c19fe4c75e6285d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T03:19:38Z","title_canon_sha256":"f9407f7fcbe0cef586f64b7aeed5f34ddd8396678c7efcccfd9ce9a82a3bb094"},"schema_version":"1.0","source":{"id":"2605.18840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18840","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18840v1","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18840","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"pith_short_12","alias_value":"HFKFWDX44B7N","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"pith_short_16","alias_value":"HFKFWDX44B7NOJRB","created_at":"2026-05-20T00:06:25Z"},{"alias_kind":"pith_short_8","alias_value":"HFKFWDX4","created_at":"2026-05-20T00:06:25Z"}],"graph_snapshots":[{"event_id":"sha256:54a7d2bbd13b5e02ca6662f91c254446c20646c7e322d511619113c4b0498701","target":"graph","created_at":"2026-05-20T00:06:25Z","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/2605.18840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the frontier, this interaction is the more informative signal. We decompose paired SWE-bench and GPQA Diamond scores into a population coupling trend and per-release residual ($h$-field) that diagnoses capability emphasis and identifies which measurement or stress test is most informative next. Across 34 models from 10 labs (2024--2026), capabilities cooperate ($r = +0.72$, $p < 10^{-6}$), but cooperation varies by lab and over time: DeepSeek reversed fr","authors_text":"Adil Amin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T03:19:38Z","title":"The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18840","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:a33d5990b1972d89ba7731dadfd96bd6deb47b9127ca6634d7cdac2c38acb6d8","target":"record","created_at":"2026-05-20T00:06:25Z","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":"383536ba663111d838022b30f69eb87b3982378138e25f86c19fe4c75e6285d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T03:19:38Z","title_canon_sha256":"f9407f7fcbe0cef586f64b7aeed5f34ddd8396678c7efcccfd9ce9a82a3bb094"},"schema_version":"1.0","source":{"id":"2605.18840","kind":"arxiv","version":1}},"canonical_sha256":"39545b0efce07ed726212f047dbf9babfaf892fffa8ebbf2959e3f074708d2bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39545b0efce07ed726212f047dbf9babfaf892fffa8ebbf2959e3f074708d2bc","first_computed_at":"2026-05-20T00:06:25.236543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:25.236543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QcDZw/bvlIGOzt8PSU07w2J0pi0KDIgiJJT333QQEWPdDRGspYkLugyjLOZmJ2u0SA35DPJzvUDgcyE0wGi4DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:25.237360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a33d5990b1972d89ba7731dadfd96bd6deb47b9127ca6634d7cdac2c38acb6d8","sha256:54a7d2bbd13b5e02ca6662f91c254446c20646c7e322d511619113c4b0498701"],"state_sha256":"736209ac026f93182c9130ef4fe8d1e25568490517ef05cc3c3293a637efaaff"}