{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:22XURPEFGAH4RGA4TZDH6BOG46","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":"9d5e25bb07ad90108ba2f3c1e85e157eb494bc4ef58bfac217bf4db9a51bad50","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:50:20Z","title_canon_sha256":"48db189b73d8a297a185b5d4cdb5c4b40855d810f55f09ca0e1d93235d855602"},"schema_version":"1.0","source":{"id":"2605.14292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14292","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14292v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14292","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"22XURPEFGAH4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"22XURPEFGAH4RGA4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"22XURPEF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:59dc0ff8e3b64da504548b4fdabd6dc9f948313fbf99f912d56bf54404bfdd67","target":"graph","created_at":"2026-05-17T23:39:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With λ = 0.5, α clears Bonferroni on two of the four (model, budget) cells (Qwen b=128 and Llama b=64), no cell is significantly negative, and the pre-registered Branch A triggers."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the pre-registered tuning on the development split and confirmation on the held-out split of MATH-500 with these two specific models generalizes beyond the tested regime and tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A one-function modification to the TriAttention retention scorer using greedy selection under a V-space redundancy penalty outperforms seven matched mechanisms on long-form math reasoning at budgets 64 and 128."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A one-function change adding a diversity penalty to the KV retention scorer outperforms seven other compression methods on mathematical reasoning at small budgets."}],"snapshot_sha256":"36dec26da357fcad31319f295ee60911215f9ba38c9dca9d8204c9e8afa480e9"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"d0018cf4532f107d63e42ac11e62e763a4d272f5a1e86392c8a1a1e0f12ef5c0"},"paper":{"abstract_excerpt":"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring. We study seven mechanisms across these five families under matched mean cache on long-form mathematical reasoning (MATH-500~\\cite{hendrycks2021math}) with two distilled-reasoning models (Qwen-7B and Llama-8B variants of DeepSeek-R1-Distill~\\cite{deepseek2025r1}) at budgets $b \\in \\{64, 128\\}$. All seven were rejected. We then propose $\\alpha$, a one-function modification to the TriAttention~\\cite{mao2026triattention","authors_text":"Libo Sun, Peixiong He, Po-Wei Harn, Xiao Qin","cross_cats":["cs.CL"],"headline":"A one-function change adding a diversity penalty to the KV retention scorer outperforms seven other compression methods on mathematical reasoning at small budgets.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:50:20Z","title":"Minimal-Intervention KV Retention: A Design-Space Study and a Diversity-Penalty Survivor"},"references":{"count":28,"internal_anchors":0,"resolved_work":28,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"LongBench: A bilingual, multitask benchmark for long context understanding","work_id":"5f38cf20-6ae2-4609-92f0-e8288b3a50e4","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Accounting for variance in machine learning benchmarks","work_id":"d82b95de-3307-4be8-abd8-9eb022ff5682","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Kelly, J. R. Reducing transformer key-value cache size with cross-layer attention, 2024","work_id":"22fddcfe-1474-4671-874e-7ef0328c416e","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"PyramidKV: Dynamic KV cache compression based on pyramidal information funneling, 2024","work_id":"4439c820-ec96-427f-9d23-6769184dddef","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"R-KV: Redundancy-aware KV cache compression for reasoning models","work_id":"881ebad1-d4d2-4bf4-ad80-1325f19526a8","year":2025}],"snapshot_sha256":"6a96c0f72a5cf01ba510244c3b4f52f2158f62e68fde578fc66ab23292ebc30e"},"source":{"id":"2605.14292","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:14:00.797973Z","id":"c0723674-7732-4c7a-95ea-f6f66c405430","model_set":{"reader":"grok-4.3"},"one_line_summary":"A one-function modification to the TriAttention retention scorer using greedy selection under a V-space redundancy penalty outperforms seven matched mechanisms on long-form math reasoning at budgets 64 and 128.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A one-function change adding a diversity penalty to the KV retention scorer outperforms seven other compression methods on mathematical reasoning at small budgets.","strongest_claim":"With λ = 0.5, α clears Bonferroni on two of the four (model, budget) cells (Qwen b=128 and Llama b=64), no cell is significantly negative, and the pre-registered Branch A triggers.","weakest_assumption":"That the pre-registered tuning on the development split and confirmation on the held-out split of MATH-500 with these two specific models generalizes beyond the tested regime and tasks."}},"verdict_id":"c0723674-7732-4c7a-95ea-f6f66c405430"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0834caea8539f0590706845317ec041648855f15852f811ac416b6720993640d","target":"record","created_at":"2026-05-17T23:39:10Z","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":"9d5e25bb07ad90108ba2f3c1e85e157eb494bc4ef58bfac217bf4db9a51bad50","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:50:20Z","title_canon_sha256":"48db189b73d8a297a185b5d4cdb5c4b40855d810f55f09ca0e1d93235d855602"},"schema_version":"1.0","source":{"id":"2605.14292","kind":"arxiv","version":1}},"canonical_sha256":"d6af48bc85300fc8981c9e467f05c6e7b672b3fece6aa6aab0b8fea7b439024b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6af48bc85300fc8981c9e467f05c6e7b672b3fece6aa6aab0b8fea7b439024b","first_computed_at":"2026-05-17T23:39:10.187767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.187767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9hQ518Wec+wjOnRfd10qJ2N/Nmx50MDPclQlg+Hi2WttiDkI4BudO/hqiQC+MXYLsorochB+sefpjR7/v1nPCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.188306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0834caea8539f0590706845317ec041648855f15852f811ac416b6720993640d","sha256:59dc0ff8e3b64da504548b4fdabd6dc9f948313fbf99f912d56bf54404bfdd67"],"state_sha256":"4b6efd637b79c812b86b5f2b61469df6e7bf638043e9213eda42b8f07b119d81"}