{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XFP3WYZPJL4RFATOICNKXSUQA2","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":"437df2639b5a11d442cab29f3579cf4cdc18d8ff0427cf1e0fe0276289e84244","cross_cats_sorted":["cs.AI","cs.CL","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T16:57:34Z","title_canon_sha256":"ce38c6be55ca22e34be3d4cb8fe009299248b25531fc5635ffd6e4253ae33e32"},"schema_version":"1.0","source":{"id":"2505.18102","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18102","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18102v7","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18102","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"XFP3WYZPJL4R","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"XFP3WYZPJL4RFATO","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"XFP3WYZP","created_at":"2026-06-02T01:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:da49ca532c1cc1105f816733a5d7065af1a3354e328c582824e29e3b13f014b0","target":"graph","created_at":"2026-06-02T01:03:31Z","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/2505.18102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Publishing a large language model (LLM) benchmark (especially its ground-truth answers) on the Internet risks contaminating future LLMs and enabling evaluation gaming: it may be unintentionally (or intentionally) used to train or select a model, or exploited to overfit and hack leaderboards when labels are accessible. A common mitigation is to keep the benchmark private and let participants submit their models or predictions to the organizers, but this still permits test-set overfitting through feedback loops. To overcome this issue, we propose CapBencher, a way to publish benchmarks without f","authors_text":"Ikko Yamane, Takashi Ishida, Thanawat Lodkaew","cross_cats":["cs.AI","cs.CL","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T16:57:34Z","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18102","kind":"arxiv","version":7},"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":"sha256:18133423f00d28e8afd8cc3e0898f44efe9c5384495925e6e153180e2cb25de5","target":"record","created_at":"2026-06-02T01:03:31Z","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":"437df2639b5a11d442cab29f3579cf4cdc18d8ff0427cf1e0fe0276289e84244","cross_cats_sorted":["cs.AI","cs.CL","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T16:57:34Z","title_canon_sha256":"ce38c6be55ca22e34be3d4cb8fe009299248b25531fc5635ffd6e4253ae33e32"},"schema_version":"1.0","source":{"id":"2505.18102","kind":"arxiv","version":7}},"canonical_sha256":"b95fbb632f4af912826e409aabca9006b7bbe828ea9fccc8bb7e60f619f82f99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b95fbb632f4af912826e409aabca9006b7bbe828ea9fccc8bb7e60f619f82f99","first_computed_at":"2026-06-02T01:03:31.629048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:31.629048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4P/6UL4PTARZV6WQ81X+6z+c48FcAMDSiZxtSTCiAi2/SzX3dZr7S2ABWIX9suSlKBy1QzAsmpFQcpmu8fOBA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:31.629562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18102","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18133423f00d28e8afd8cc3e0898f44efe9c5384495925e6e153180e2cb25de5","sha256:da49ca532c1cc1105f816733a5d7065af1a3354e328c582824e29e3b13f014b0"],"state_sha256":"4bef76d36e16d7d9d90e89def826d37905cac58cd8bfe66c4d94397abe97cf42"}