{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B6IZE23FHJ5JW2OYZISTQOKZZC","short_pith_number":"pith:B6IZE23F","schema_version":"1.0","canonical_sha256":"0f91926b653a7a9b69d8ca25383959c8896cdb23227969b66c467363903f8ce5","source":{"kind":"arxiv","id":"2606.17507","version":1},"attestation_state":"computed","paper":{"title":"LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Chen Wang, Jacky Jiang, Liming Zhu, Mohan Dhall, Phil Yang, Qian Fu, Wenjie Zhang, Xiwei Xu","submitted_at":"2026-06-16T04:33:20Z","abstract_excerpt":"Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines that systematically ground model outputs in authorised curriculum artefacts and marking guidelines issued by education authorities. This paper presents a curriculum-grounded, configurable LLM-as-Judge pipeline for question-level marking, co-developed with an industrial partner, to support exam preparation for university admission. The pipeline ide"},"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":"2606.17507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T04:33:20Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"df2e877f5fa84b9636ce9851cd61ef1703e0b67bd60c12f451b8bdd401771bdf","abstract_canon_sha256":"694267893cee89a60e93425e17bd875038d9b39fdbffbf9c092ecd84d365db1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:14.662101Z","signature_b64":"5gTOh5h98DnBmLHQsLKOCtwZjVy9joR/4r+ikMo+Mgxtd7VwnU4dKfvuoMs+HJSKgv3EiHS//DL0sGyRG/aaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f91926b653a7a9b69d8ca25383959c8896cdb23227969b66c467363903f8ce5","last_reissued_at":"2026-06-19T16:10:14.661696Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:14.661696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Chen Wang, Jacky Jiang, Liming Zhu, Mohan Dhall, Phil Yang, Qian Fu, Wenjie Zhang, Xiwei Xu","submitted_at":"2026-06-16T04:33:20Z","abstract_excerpt":"Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines that systematically ground model outputs in authorised curriculum artefacts and marking guidelines issued by education authorities. This paper presents a curriculum-grounded, configurable LLM-as-Judge pipeline for question-level marking, co-developed with an industrial partner, to support exam preparation for university admission. The pipeline ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17507","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/2606.17507/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":"2606.17507","created_at":"2026-06-19T16:10:14.661761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17507v1","created_at":"2026-06-19T16:10:14.661761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17507","created_at":"2026-06-19T16:10:14.661761+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6IZE23FHJ5J","created_at":"2026-06-19T16:10:14.661761+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6IZE23FHJ5JW2OY","created_at":"2026-06-19T16:10:14.661761+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6IZE23F","created_at":"2026-06-19T16:10:14.661761+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/B6IZE23FHJ5JW2OYZISTQOKZZC","json":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC.json","graph_json":"https://pith.science/api/pith-number/B6IZE23FHJ5JW2OYZISTQOKZZC/graph.json","events_json":"https://pith.science/api/pith-number/B6IZE23FHJ5JW2OYZISTQOKZZC/events.json","paper":"https://pith.science/paper/B6IZE23F"},"agent_actions":{"view_html":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC","download_json":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC.json","view_paper":"https://pith.science/paper/B6IZE23F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17507&json=true","fetch_graph":"https://pith.science/api/pith-number/B6IZE23FHJ5JW2OYZISTQOKZZC/graph.json","fetch_events":"https://pith.science/api/pith-number/B6IZE23FHJ5JW2OYZISTQOKZZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC/action/storage_attestation","attest_author":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC/action/author_attestation","sign_citation":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC/action/citation_signature","submit_replication":"https://pith.science/pith/B6IZE23FHJ5JW2OYZISTQOKZZC/action/replication_record"}},"created_at":"2026-06-19T16:10:14.661761+00:00","updated_at":"2026-06-19T16:10:14.661761+00:00"}