{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JTQVC6KX4Y46B3TCUXQFTGKOGS","short_pith_number":"pith:JTQVC6KX","schema_version":"1.0","canonical_sha256":"4ce1517957e639e0ee62a5e059994e34abf55ece435ee6d187003ca05daccc22","source":{"kind":"arxiv","id":"2606.16511","version":2},"attestation_state":"computed","paper":{"title":"Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Luca Zhou","submitted_at":"2026-06-15T10:13:54Z","abstract_excerpt":"Recent work motivates moving large language model (LLM) evaluation from mean-based to tail-aware metrics, including conditional value-at-risk and tail-index estimates of reward-model error. We ask whether the canonical extreme-value-theory tail-index parameter, which isolates how heavy a tail is from how large the tail mass is, adds discriminative information beyond the mean and a standard tail-magnitude statistic in LLM evaluation. We pre-register a protocol covering admissibility, goodness-of-fit, threshold-stability, and effect-size requirements for any positive tail-shape claim. The protoc"},"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":"2606.16511","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T10:13:54Z","cross_cats_sorted":[],"title_canon_sha256":"543dd1881874f90dfa158399dd9334dcaed2270cd093e6d1bceebc8a9c307a4f","abstract_canon_sha256":"b0ad4e4db5b481375a732ebeabd8ba3e44f0242a55aeebc1e3992db2b45610ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:19.735673Z","signature_b64":"F2yoKqzoJobsOo6KRHWE/tpCR+zj7klV7cF8MmUsCbEfrfuf7a1/ONBMUtJBy2Hj4Gj2mQnaxPVroZTsC6sjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce1517957e639e0ee62a5e059994e34abf55ece435ee6d187003ca05daccc22","last_reissued_at":"2026-07-02T01:18:19.735227Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:19.735227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Luca Zhou","submitted_at":"2026-06-15T10:13:54Z","abstract_excerpt":"Recent work motivates moving large language model (LLM) evaluation from mean-based to tail-aware metrics, including conditional value-at-risk and tail-index estimates of reward-model error. We ask whether the canonical extreme-value-theory tail-index parameter, which isolates how heavy a tail is from how large the tail mass is, adds discriminative information beyond the mean and a standard tail-magnitude statistic in LLM evaluation. We pre-register a protocol covering admissibility, goodness-of-fit, threshold-stability, and effect-size requirements for any positive tail-shape claim. The protoc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16511","kind":"arxiv","version":2},"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/2606.16511/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":"2606.16511","created_at":"2026-07-02T01:18:19.735284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.16511v2","created_at":"2026-07-02T01:18:19.735284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16511","created_at":"2026-07-02T01:18:19.735284+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTQVC6KX4Y46","created_at":"2026-07-02T01:18:19.735284+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTQVC6KX4Y46B3TC","created_at":"2026-07-02T01:18:19.735284+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTQVC6KX","created_at":"2026-07-02T01:18:19.735284+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/JTQVC6KX4Y46B3TCUXQFTGKOGS","json":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS.json","graph_json":"https://pith.science/api/pith-number/JTQVC6KX4Y46B3TCUXQFTGKOGS/graph.json","events_json":"https://pith.science/api/pith-number/JTQVC6KX4Y46B3TCUXQFTGKOGS/events.json","paper":"https://pith.science/paper/JTQVC6KX"},"agent_actions":{"view_html":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS","download_json":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS.json","view_paper":"https://pith.science/paper/JTQVC6KX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.16511&json=true","fetch_graph":"https://pith.science/api/pith-number/JTQVC6KX4Y46B3TCUXQFTGKOGS/graph.json","fetch_events":"https://pith.science/api/pith-number/JTQVC6KX4Y46B3TCUXQFTGKOGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/action/storage_attestation","attest_author":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/action/author_attestation","sign_citation":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/action/citation_signature","submit_replication":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/action/replication_record"}},"created_at":"2026-07-02T01:18:19.735284+00:00","updated_at":"2026-07-02T01:18:19.735284+00:00"}