{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AMZMQTIXJ7USALYQNZLWXPHVA5","short_pith_number":"pith:AMZMQTIX","schema_version":"1.0","canonical_sha256":"0332c84d174fe9202f106e576bbcf507598b5d203484f92e0a06ee66c84bd022","source":{"kind":"arxiv","id":"2607.24063","version":1},"attestation_state":"computed","paper":{"title":"The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dequan Wang, Jin Gao, Keyu Li","submitted_at":"2026-07-27T07:05:11Z","abstract_excerpt":"On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is toward how much compute that factuality costs. Static leaderboards score factuality in isolation and treat compute as free, so they cannot tell a genuinely better system apart from one that simply spends more. Consider a ranking reversal. A brute-force Best-of-4 agent posts the higher raw factuality score (H-Score 0.9169 vs 0.9103) and would top a static leaderboard, but once cost is counted it is the worse system, losing on Q-Score (0.5169 vs 0.5"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.24063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"a69b65a85c3aa7fb82e57daaf0409025e13d2af2ccd940b7eb83c9e956b44566","abstract_canon_sha256":"02c7c16e30768c986e18c5f1cc325b8208c928aa457dea5c8d58db057dcfee3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:43.521383Z","signature_b64":"1vNu6UVJUHrMSBBruzQj32jA3l9AXx+Cbgo8TgvTSMcUt4MHp0tRTjzfsA10xqD0nTtNIV3Yg7Gl1Gt1e65HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0332c84d174fe9202f106e576bbcf507598b5d203484f92e0a06ee66c84bd022","last_reissued_at":"2026-07-28T01:23:43.520504Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:43.520504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dequan Wang, Jin Gao, Keyu Li","submitted_at":"2026-07-27T07:05:11Z","abstract_excerpt":"On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is toward how much compute that factuality costs. Static leaderboards score factuality in isolation and treat compute as free, so they cannot tell a genuinely better system apart from one that simply spends more. Consider a ranking reversal. A brute-force Best-of-4 agent posts the higher raw factuality score (H-Score 0.9169 vs 0.9103) and would top a static leaderboard, but once cost is counted it is the worse system, losing on Q-Score (0.5169 vs 0.5"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24063","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.24063/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.24063","created_at":"2026-07-28T01:23:43.520969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24063v1","created_at":"2026-07-28T01:23:43.520969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24063","created_at":"2026-07-28T01:23:43.520969+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMZMQTIXJ7US","created_at":"2026-07-28T01:23:43.520969+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMZMQTIXJ7USALYQ","created_at":"2026-07-28T01:23:43.520969+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMZMQTIX","created_at":"2026-07-28T01:23:43.520969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5","json":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5.json","graph_json":"https://pith.science/api/pith-number/AMZMQTIXJ7USALYQNZLWXPHVA5/graph.json","events_json":"https://pith.science/api/pith-number/AMZMQTIXJ7USALYQNZLWXPHVA5/events.json","paper":"https://pith.science/paper/AMZMQTIX"},"agent_actions":{"view_html":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5","download_json":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5.json","view_paper":"https://pith.science/paper/AMZMQTIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24063&json=true","fetch_graph":"https://pith.science/api/pith-number/AMZMQTIXJ7USALYQNZLWXPHVA5/graph.json","fetch_events":"https://pith.science/api/pith-number/AMZMQTIXJ7USALYQNZLWXPHVA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/action/storage_attestation","attest_author":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/action/author_attestation","sign_citation":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/action/citation_signature","submit_replication":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/action/replication_record"}},"created_at":"2026-07-28T01:23:43.520969+00:00","updated_at":"2026-07-28T01:23:43.520969+00:00"}