{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5WYWGHUUNVJMB57KQM4RVS2EJT","short_pith_number":"pith:5WYWGHUU","schema_version":"1.0","canonical_sha256":"edb1631e946d52c0f7ea83391acb444cfe87c6191e13d1391fb091b17a9fd6fb","source":{"kind":"arxiv","id":"2606.05170","version":1},"attestation_state":"computed","paper":{"title":"ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason Z Wang","submitted_at":"2026-04-15T09:22:46Z","abstract_excerpt":"At matched accuracy, open-weight LLMs differ substantially in the shape of their error severity distribution -- a difference invisible to the scalar error rate. Hallucination benchmarks report a single error count and treat all errors as equivalent, yet a wrong date and a fabricated court ruling differ by orders of magnitude. We introduce Errorquake-10k, a 10,000-query benchmark scoring each response on a continuous 0-4 severity scale across 8 domains and 5 difficulty tiers, and we fit per-model severity distributions for 21 open-weight models. For each model we estimate a severity distributio"},"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":"2606.05170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T09:22:46Z","cross_cats_sorted":[],"title_canon_sha256":"27fc618ffc07a9e4c63efa529f28a3df5b0cc5a51839f32b6b05206452a3770c","abstract_canon_sha256":"af0cd0bf47c7dac657a178192773cfcd0a9430b98f2d27acebcd9f6fa39f1807"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:47.565659Z","signature_b64":"lHwgo2ehL+5ARAZY14MVirs0kVf/8btRfIZWb75rEDiiQvRFxpbwcZSm9PqVv/gBiD1bwhlZzfdUUN5Q30PABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb1631e946d52c0f7ea83391acb444cfe87c6191e13d1391fb091b17a9fd6fb","last_reissued_at":"2026-06-05T00:13:47.565122Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:47.565122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason Z Wang","submitted_at":"2026-04-15T09:22:46Z","abstract_excerpt":"At matched accuracy, open-weight LLMs differ substantially in the shape of their error severity distribution -- a difference invisible to the scalar error rate. Hallucination benchmarks report a single error count and treat all errors as equivalent, yet a wrong date and a fabricated court ruling differ by orders of magnitude. We introduce Errorquake-10k, a 10,000-query benchmark scoring each response on a continuous 0-4 severity scale across 8 domains and 5 difficulty tiers, and we fit per-model severity distributions for 21 open-weight models. For each model we estimate a severity distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05170","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/2606.05170/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":"2606.05170","created_at":"2026-06-05T00:13:47.565199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05170v1","created_at":"2026-06-05T00:13:47.565199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05170","created_at":"2026-06-05T00:13:47.565199+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WYWGHUUNVJM","created_at":"2026-06-05T00:13:47.565199+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WYWGHUUNVJMB57K","created_at":"2026-06-05T00:13:47.565199+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WYWGHUU","created_at":"2026-06-05T00:13:47.565199+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/5WYWGHUUNVJMB57KQM4RVS2EJT","json":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT.json","graph_json":"https://pith.science/api/pith-number/5WYWGHUUNVJMB57KQM4RVS2EJT/graph.json","events_json":"https://pith.science/api/pith-number/5WYWGHUUNVJMB57KQM4RVS2EJT/events.json","paper":"https://pith.science/paper/5WYWGHUU"},"agent_actions":{"view_html":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT","download_json":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT.json","view_paper":"https://pith.science/paper/5WYWGHUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05170&json=true","fetch_graph":"https://pith.science/api/pith-number/5WYWGHUUNVJMB57KQM4RVS2EJT/graph.json","fetch_events":"https://pith.science/api/pith-number/5WYWGHUUNVJMB57KQM4RVS2EJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT/action/storage_attestation","attest_author":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT/action/author_attestation","sign_citation":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT/action/citation_signature","submit_replication":"https://pith.science/pith/5WYWGHUUNVJMB57KQM4RVS2EJT/action/replication_record"}},"created_at":"2026-06-05T00:13:47.565199+00:00","updated_at":"2026-06-05T00:13:47.565199+00:00"}