{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4CWCNFARMZU4O6NJ3VRNHAZZZY","short_pith_number":"pith:4CWCNFAR","schema_version":"1.0","canonical_sha256":"e0ac2694116669c779a9dd62d38339ce3f6ed6ad6aaa6f6766a9ee6469785a3c","source":{"kind":"arxiv","id":"2605.23701","version":1},"attestation_state":"computed","paper":{"title":"Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kan Shao","submitted_at":"2026-05-22T14:52:32Z","abstract_excerpt":"We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only shortcut checks answer a different question, namely whether outputs are predictable from metadata priors. We therefore combine a metadata statistic, the Metadata Prior Dominance Score (MPDS), with an evidence-intervention statistic, {\\Delta}Evi, measuring sensitivity to evidence identity under cross-item shuffling. Synthetic HotpotQA gives a constructed counterexample to metadata-only screening: MPDS is only moderate (0.643), yet {\\Delta}Evi is z"},"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":"2605.23701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T14:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"63f4f2325af8bbca71d9a5073552aca243ce107dde1930c3ffdce2e0a2dd46e2","abstract_canon_sha256":"cf36cfdc4dbdd265cdd153b1e34349d433487aeb8156d996a22782720865e549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:27.109263Z","signature_b64":"IAhtDj7raUV5Chco1SAsrth3Vsawrgv+nB8jcr96MtpHZsKedwYDZSMOcgQConLfvmYWH4imyFYUsAUU6k3vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0ac2694116669c779a9dd62d38339ce3f6ed6ad6aaa6f6766a9ee6469785a3c","last_reissued_at":"2026-05-25T02:02:27.108665Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:27.108665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kan Shao","submitted_at":"2026-05-22T14:52:32Z","abstract_excerpt":"We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only shortcut checks answer a different question, namely whether outputs are predictable from metadata priors. We therefore combine a metadata statistic, the Metadata Prior Dominance Score (MPDS), with an evidence-intervention statistic, {\\Delta}Evi, measuring sensitivity to evidence identity under cross-item shuffling. Synthetic HotpotQA gives a constructed counterexample to metadata-only screening: MPDS is only moderate (0.643), yet {\\Delta}Evi is z"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23701","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/2605.23701/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":"2605.23701","created_at":"2026-05-25T02:02:27.108744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23701v1","created_at":"2026-05-25T02:02:27.108744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23701","created_at":"2026-05-25T02:02:27.108744+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CWCNFARMZU4","created_at":"2026-05-25T02:02:27.108744+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CWCNFARMZU4O6NJ","created_at":"2026-05-25T02:02:27.108744+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CWCNFAR","created_at":"2026-05-25T02:02:27.108744+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/4CWCNFARMZU4O6NJ3VRNHAZZZY","json":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY.json","graph_json":"https://pith.science/api/pith-number/4CWCNFARMZU4O6NJ3VRNHAZZZY/graph.json","events_json":"https://pith.science/api/pith-number/4CWCNFARMZU4O6NJ3VRNHAZZZY/events.json","paper":"https://pith.science/paper/4CWCNFAR"},"agent_actions":{"view_html":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY","download_json":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY.json","view_paper":"https://pith.science/paper/4CWCNFAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23701&json=true","fetch_graph":"https://pith.science/api/pith-number/4CWCNFARMZU4O6NJ3VRNHAZZZY/graph.json","fetch_events":"https://pith.science/api/pith-number/4CWCNFARMZU4O6NJ3VRNHAZZZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY/action/storage_attestation","attest_author":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY/action/author_attestation","sign_citation":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY/action/citation_signature","submit_replication":"https://pith.science/pith/4CWCNFARMZU4O6NJ3VRNHAZZZY/action/replication_record"}},"created_at":"2026-05-25T02:02:27.108744+00:00","updated_at":"2026-05-25T02:02:27.108744+00:00"}