{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RIMU3BX33II7U35AUSPPLQ5CDP","short_pith_number":"pith:RIMU3BX3","schema_version":"1.0","canonical_sha256":"8a194d86fbda11fa6fa0a49ef5c3a21bd8e30de10bdc794c48c91dbd3a56e756","source":{"kind":"arxiv","id":"2606.29033","version":1},"attestation_state":"computed","paper":{"title":"Human-in-the-Loop Nugget Annotation for Accountable LLM-as-a-Judge Evaluations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Laura Dietz","submitted_at":"2026-06-27T18:04:34Z","abstract_excerpt":"Evaluating AI/Agentic system outputs reliably requires human judgment, but how one incorporates the human determines whether one gets a real quality signal or expensive theater. The common approaches either accidentally anchor human experts (leading to rubber-stamping) or leave them unsupported in high-variance labeling tasks. We present a prototype annotation tool that implements a different division of labor: humans identify what information matters (nuggets), while LLMs handle high-volume matching of nuggets to system outputs. This plays to each party's strengths while maintaining genuine h"},"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":"2606.29033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-27T18:04:34Z","cross_cats_sorted":[],"title_canon_sha256":"74f510fa3f3afe401350d8b18c29b7f21bf428275b8e06537a68ebd9b44cd551","abstract_canon_sha256":"b671316ea334138c886704e0be7c9bf34b525fedf67e3bbe896acd6934d7be8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:50.208277Z","signature_b64":"dafAspBEko4Z3KwAedNhlOLjUeQ7hyLtso7ngmJcyNRB/lqxh9XbHbZvL7scpIAFrIzQ6h9tO/3vIwHyu3w0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a194d86fbda11fa6fa0a49ef5c3a21bd8e30de10bdc794c48c91dbd3a56e756","last_reissued_at":"2026-06-30T01:17:50.207810Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:50.207810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-in-the-Loop Nugget Annotation for Accountable LLM-as-a-Judge Evaluations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Laura Dietz","submitted_at":"2026-06-27T18:04:34Z","abstract_excerpt":"Evaluating AI/Agentic system outputs reliably requires human judgment, but how one incorporates the human determines whether one gets a real quality signal or expensive theater. The common approaches either accidentally anchor human experts (leading to rubber-stamping) or leave them unsupported in high-variance labeling tasks. We present a prototype annotation tool that implements a different division of labor: humans identify what information matters (nuggets), while LLMs handle high-volume matching of nuggets to system outputs. This plays to each party's strengths while maintaining genuine h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29033","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/2606.29033/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":"2606.29033","created_at":"2026-06-30T01:17:50.207877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29033v1","created_at":"2026-06-30T01:17:50.207877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29033","created_at":"2026-06-30T01:17:50.207877+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIMU3BX33II7","created_at":"2026-06-30T01:17:50.207877+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIMU3BX33II7U35A","created_at":"2026-06-30T01:17:50.207877+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIMU3BX3","created_at":"2026-06-30T01:17:50.207877+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/RIMU3BX33II7U35AUSPPLQ5CDP","json":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP.json","graph_json":"https://pith.science/api/pith-number/RIMU3BX33II7U35AUSPPLQ5CDP/graph.json","events_json":"https://pith.science/api/pith-number/RIMU3BX33II7U35AUSPPLQ5CDP/events.json","paper":"https://pith.science/paper/RIMU3BX3"},"agent_actions":{"view_html":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP","download_json":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP.json","view_paper":"https://pith.science/paper/RIMU3BX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29033&json=true","fetch_graph":"https://pith.science/api/pith-number/RIMU3BX33II7U35AUSPPLQ5CDP/graph.json","fetch_events":"https://pith.science/api/pith-number/RIMU3BX33II7U35AUSPPLQ5CDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP/action/storage_attestation","attest_author":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP/action/author_attestation","sign_citation":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP/action/citation_signature","submit_replication":"https://pith.science/pith/RIMU3BX33II7U35AUSPPLQ5CDP/action/replication_record"}},"created_at":"2026-06-30T01:17:50.207877+00:00","updated_at":"2026-06-30T01:17:50.207877+00:00"}