{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AMZMQTIXJ7USALYQNZLWXPHVA5","short_pith_number":"pith:AMZMQTIX","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"},"canonical_sha256":"0332c84d174fe9202f106e576bbcf507598b5d203484f92e0a06ee66c84bd022","source":{"kind":"arxiv","id":"2607.24063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24063","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24063v1","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24063","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"AMZMQTIXJ7US","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"AMZMQTIXJ7USALYQ","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"AMZMQTIX","created_at":"2026-07-28T01:23:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AMZMQTIXJ7USALYQNZLWXPHVA5","target":"record","payload":{"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"},"canonical_sha256":"0332c84d174fe9202f106e576bbcf507598b5d203484f92e0a06ee66c84bd022","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"},"source_kind":"arxiv","source_id":"2607.24063","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dSFvkj3Iovm7zBLKQkq36yYsQo+Y2spzQ7pUZgaBLER7NhZ/q3ibIs0yY+n1Z/ed2DfsbBCFPacz2OCxILV8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:47:32.698663Z"},"content_sha256":"acdb32e7ba68ec76793b0feb873526b101a3ae4d295da283fdc5f6812c4f332b","schema_version":"1.0","event_id":"sha256:acdb32e7ba68ec76793b0feb873526b101a3ae4d295da283fdc5f6812c4f332b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AMZMQTIXJ7USALYQNZLWXPHVA5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvnNvYPdtibJgLFmFNh68apLbOklRS027u8li9H9fAQHvm6npAvVm7fYubvrr8yLpSpnXmJiCeyWf6W9prRWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:47:32.699268Z"},"content_sha256":"71e52f69fe2704212f9ed3ca5d8d835ad5f0b0c81cfad83dcc1f4c70251c9060","schema_version":"1.0","event_id":"sha256:71e52f69fe2704212f9ed3ca5d8d835ad5f0b0c81cfad83dcc1f4c70251c9060"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/bundle.json","state_url":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T18:47:32Z","links":{"resolver":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5","bundle":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/bundle.json","state":"https://pith.science/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMZMQTIXJ7USALYQNZLWXPHVA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AMZMQTIXJ7USALYQNZLWXPHVA5","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":"02c7c16e30768c986e18c5f1cc325b8208c928aa457dea5c8d58db057dcfee3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:05:11Z","title_canon_sha256":"a69b65a85c3aa7fb82e57daaf0409025e13d2af2ccd940b7eb83c9e956b44566"},"schema_version":"1.0","source":{"id":"2607.24063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24063","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24063v1","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24063","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"AMZMQTIXJ7US","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"AMZMQTIXJ7USALYQ","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"AMZMQTIX","created_at":"2026-07-28T01:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:71e52f69fe2704212f9ed3ca5d8d835ad5f0b0c81cfad83dcc1f4c70251c9060","target":"graph","created_at":"2026-07-28T01:23:43Z","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/2607.24063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dequan Wang, Jin Gao, Keyu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:05:11Z","title":"The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24063","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:acdb32e7ba68ec76793b0feb873526b101a3ae4d295da283fdc5f6812c4f332b","target":"record","created_at":"2026-07-28T01:23:43Z","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":"02c7c16e30768c986e18c5f1cc325b8208c928aa457dea5c8d58db057dcfee3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T07:05:11Z","title_canon_sha256":"a69b65a85c3aa7fb82e57daaf0409025e13d2af2ccd940b7eb83c9e956b44566"},"schema_version":"1.0","source":{"id":"2607.24063","kind":"arxiv","version":1}},"canonical_sha256":"0332c84d174fe9202f106e576bbcf507598b5d203484f92e0a06ee66c84bd022","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0332c84d174fe9202f106e576bbcf507598b5d203484f92e0a06ee66c84bd022","first_computed_at":"2026-07-28T01:23:43.520504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:43.520504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1vNu6UVJUHrMSBBruzQj32jA3l9AXx+Cbgo8TgvTSMcUt4MHp0tRTjzfsA10xqD0nTtNIV3Yg7Gl1Gt1e65HCg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:43.521383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acdb32e7ba68ec76793b0feb873526b101a3ae4d295da283fdc5f6812c4f332b","sha256:71e52f69fe2704212f9ed3ca5d8d835ad5f0b0c81cfad83dcc1f4c70251c9060"],"state_sha256":"2a2e4f552fc4c9c6a2e5f7e0a3ef144a44a21b4495e53d00fac1a654f7094209"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aisk/k3rOtMtfn2TJBK4L8DSoh9ByEMrFRYe1Eyc50fcwZMn/9NF3A7SE1zVGeb+HyDtUdN+PiWbMUr1I5+1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T18:47:32.705393Z","bundle_sha256":"8fa029f2d594c64e4dd634e481f553679bd49e3e9527b7634196e1378c15ad4f"}}