{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JTQVC6KX4Y46B3TCUXQFTGKOGS","short_pith_number":"pith:JTQVC6KX","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"},"canonical_sha256":"4ce1517957e639e0ee62a5e059994e34abf55ece435ee6d187003ca05daccc22","source":{"kind":"arxiv","id":"2606.16511","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16511","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16511v2","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16511","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"JTQVC6KX4Y46","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"JTQVC6KX4Y46B3TC","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"JTQVC6KX","created_at":"2026-07-02T01:18:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JTQVC6KX4Y46B3TCUXQFTGKOGS","target":"record","payload":{"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"},"canonical_sha256":"4ce1517957e639e0ee62a5e059994e34abf55ece435ee6d187003ca05daccc22","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"},"source_kind":"arxiv","source_id":"2606.16511","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7mwk7CSl/oKbUzIyPr40L359q0ypCJiftMK6E2En8JUB2xcYFYbOZ/bGsA+bKbZ2fCD2+uQAej8LOHJuT+1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:02:42.810531Z"},"content_sha256":"f35e091319f343dc5589b374c8d090cb9a1214257dfe2974134a7c9c5adcbe86","schema_version":"1.0","event_id":"sha256:f35e091319f343dc5589b374c8d090cb9a1214257dfe2974134a7c9c5adcbe86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JTQVC6KX4Y46B3TCUXQFTGKOGS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Svrj36JHTftqacfrMp7HGIsiNI5weOq0LP6i5BlkOfq/grwDcceKQeNA0iLUkrLhnTrEbrcPhb7kxloSkKVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:02:42.811447Z"},"content_sha256":"e98c09ac7db4b68426efcb55ae14ea57f6172bec05ab77ebdcc90df5b96e51fd","schema_version":"1.0","event_id":"sha256:e98c09ac7db4b68426efcb55ae14ea57f6172bec05ab77ebdcc90df5b96e51fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/bundle.json","state_url":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/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":"2026-08-19T14:02:42Z","links":{"resolver":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS","bundle":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/bundle.json","state":"https://pith.science/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTQVC6KX4Y46B3TCUXQFTGKOGS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JTQVC6KX4Y46B3TCUXQFTGKOGS","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":"b0ad4e4db5b481375a732ebeabd8ba3e44f0242a55aeebc1e3992db2b45610ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T10:13:54Z","title_canon_sha256":"543dd1881874f90dfa158399dd9334dcaed2270cd093e6d1bceebc8a9c307a4f"},"schema_version":"1.0","source":{"id":"2606.16511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16511","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16511v2","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16511","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"JTQVC6KX4Y46","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"JTQVC6KX4Y46B3TC","created_at":"2026-07-02T01:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"JTQVC6KX","created_at":"2026-07-02T01:18:19Z"}],"graph_snapshots":[{"event_id":"sha256:e98c09ac7db4b68426efcb55ae14ea57f6172bec05ab77ebdcc90df5b96e51fd","target":"graph","created_at":"2026-07-02T01:18:19Z","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/2606.16511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Luca Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T10:13:54Z","title":"Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16511","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:f35e091319f343dc5589b374c8d090cb9a1214257dfe2974134a7c9c5adcbe86","target":"record","created_at":"2026-07-02T01:18:19Z","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":"b0ad4e4db5b481375a732ebeabd8ba3e44f0242a55aeebc1e3992db2b45610ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T10:13:54Z","title_canon_sha256":"543dd1881874f90dfa158399dd9334dcaed2270cd093e6d1bceebc8a9c307a4f"},"schema_version":"1.0","source":{"id":"2606.16511","kind":"arxiv","version":2}},"canonical_sha256":"4ce1517957e639e0ee62a5e059994e34abf55ece435ee6d187003ca05daccc22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ce1517957e639e0ee62a5e059994e34abf55ece435ee6d187003ca05daccc22","first_computed_at":"2026-07-02T01:18:19.735227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:19.735227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2yoKqzoJobsOo6KRHWE/tpCR+zj7klV7cF8MmUsCbEfrfuf7a1/ONBMUtJBy2Hj4Gj2mQnaxPVroZTsC6sjAw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:19.735673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.16511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f35e091319f343dc5589b374c8d090cb9a1214257dfe2974134a7c9c5adcbe86","sha256:e98c09ac7db4b68426efcb55ae14ea57f6172bec05ab77ebdcc90df5b96e51fd"],"state_sha256":"df155fc389f5d77de3231e74b30b97a31d4d92c2809e3ec243cd2637e2ac8688"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJ/aDVUU2DyMi2oDKQQIQMpxre/t7rXm/LxUpWqvwRjx4x9kJqVdWkwUf2vd3ru5YQ9yx5O7WQSWGWospBsUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:02:42.819041Z","bundle_sha256":"9c25040673d4cf51fd0fc29a36ff2cc50eab0bd6ac5616920813aadaf7347b08"}}