{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SN7XSC6RTJK4XLAIM5WJH4M2CV","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":"cc637abaa082bcf28faf63926252d799a3185cd54eb525f010112a3f3c8ef532","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T17:58:14Z","title_canon_sha256":"19939f381c16638e2e3827aa59e2a520f38f5a70ac2065ea55a1fd33a91a37aa"},"schema_version":"1.0","source":{"id":"2507.17747","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17747","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17747v2","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17747","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"SN7XSC6RTJK4","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"SN7XSC6RTJK4XLAI","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"SN7XSC6R","created_at":"2026-07-05T11:50:38Z"}],"graph_snapshots":[{"event_id":"sha256:6c5adb2273b5a8cd0447cdae969f50b740091c262218b310ed8f34e9f7d2557d","target":"graph","created_at":"2026-07-05T11:50:38Z","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/2507.17747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As frontier language models increasingly saturate standard QA benchmarks, concerns about data contamination, memorization, and escalating dataset creation costs persist. We propose a debate-driven evaluation paradigm that transforms any existing QA dataset into structured adversarial debates--where one model is given the official answer to defend, and another constructs and defends an alternative answer--adjudicated by a judge model blind to the correct solution. By forcing multi-round argumentation, this approach substantially increases difficulty while penalizing shallow memorization, yet re","authors_text":"Jinman Zhao, Linbo Cao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T17:58:14Z","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17747","kind":"arxiv","version":2},"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":"sha256:834e6dcbef4e9fddf2e287c45306290d76e6033fde94e339a76adba54a86beca","target":"record","created_at":"2026-07-05T11:50:38Z","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":"cc637abaa082bcf28faf63926252d799a3185cd54eb525f010112a3f3c8ef532","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T17:58:14Z","title_canon_sha256":"19939f381c16638e2e3827aa59e2a520f38f5a70ac2065ea55a1fd33a91a37aa"},"schema_version":"1.0","source":{"id":"2507.17747","kind":"arxiv","version":2}},"canonical_sha256":"937f790bd19a55cbac08676c93f19a1575622f151d88ea4941a47c35de86c07a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"937f790bd19a55cbac08676c93f19a1575622f151d88ea4941a47c35de86c07a","first_computed_at":"2026-07-05T11:50:38.801164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:38.801164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SwRb4a60zzO2PhzZs7WlCOk7JHZQK3G49kX4GTHyU7jTeX8M8OkypIQi4B6pF4B8hj3s3KXcXvQ3Lc68EYTAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:38.801665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17747","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:834e6dcbef4e9fddf2e287c45306290d76e6033fde94e339a76adba54a86beca","sha256:6c5adb2273b5a8cd0447cdae969f50b740091c262218b310ed8f34e9f7d2557d"],"state_sha256":"5078edaf76ebeddadca30d7f905c75f5f7ef0a1e375ffc6c37388d2439ba4fc2"}