{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V6TWSWFMSXXEIHP5OXBTOSG3U5","short_pith_number":"pith:V6TWSWFM","schema_version":"1.0","canonical_sha256":"afa76958ac95ee441dfd75c33748dba76a9b51f411af1ab9ed1885d48bedcac3","source":{"kind":"arxiv","id":"2605.19529","version":1},"attestation_state":"computed","paper":{"title":"Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Che Yee Lye, Grandee Lee, Luke Peh, Yue Wang","submitted_at":"2026-05-19T08:30:39Z","abstract_excerpt":"When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative Agreement (GEA), a validity criterion measuring whether an LLM's scoring function recovers the skill levels its generative function was instructed to produce. In the first direct measurement of GEA on a two-stage adaptive assessment, the model recovers roughly half the intended variance r = 0.698 with systematic positive bias. GEA is strong r > 0.7 for syntactically verifiable skills but near zero for design-level skills, and lo"},"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":"2605.19529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T08:30:39Z","cross_cats_sorted":[],"title_canon_sha256":"85c5dabcdc6c9b9379332c34ed0e96eab44c6c06eef7c05d7e5b1791332a69b5","abstract_canon_sha256":"31cb36027511b67903833fb67407aca22b6857d05ec390d0c09771e524ea0b36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:50.361202Z","signature_b64":"IYikEYZTldLqrxEofr0ypajjjxW3NY8HgamIgUDO8p2UkxieDxpIsdcgT+giGey/8P/3Ya7NwNU+P+1L7a7sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afa76958ac95ee441dfd75c33748dba76a9b51f411af1ab9ed1885d48bedcac3","last_reissued_at":"2026-05-20T01:05:50.360477Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:50.360477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Che Yee Lye, Grandee Lee, Luke Peh, Yue Wang","submitted_at":"2026-05-19T08:30:39Z","abstract_excerpt":"When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative Agreement (GEA), a validity criterion measuring whether an LLM's scoring function recovers the skill levels its generative function was instructed to produce. In the first direct measurement of GEA on a two-stage adaptive assessment, the model recovers roughly half the intended variance r = 0.698 with systematic positive bias. GEA is strong r > 0.7 for syntactically verifiable skills but near zero for design-level skills, and lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19529","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/2605.19529/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":"2605.19529","created_at":"2026-05-20T01:05:50.360589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19529v1","created_at":"2026-05-20T01:05:50.360589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19529","created_at":"2026-05-20T01:05:50.360589+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6TWSWFMSXXE","created_at":"2026-05-20T01:05:50.360589+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6TWSWFMSXXEIHP5","created_at":"2026-05-20T01:05:50.360589+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6TWSWFM","created_at":"2026-05-20T01:05:50.360589+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/V6TWSWFMSXXEIHP5OXBTOSG3U5","json":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5.json","graph_json":"https://pith.science/api/pith-number/V6TWSWFMSXXEIHP5OXBTOSG3U5/graph.json","events_json":"https://pith.science/api/pith-number/V6TWSWFMSXXEIHP5OXBTOSG3U5/events.json","paper":"https://pith.science/paper/V6TWSWFM"},"agent_actions":{"view_html":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5","download_json":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5.json","view_paper":"https://pith.science/paper/V6TWSWFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19529&json=true","fetch_graph":"https://pith.science/api/pith-number/V6TWSWFMSXXEIHP5OXBTOSG3U5/graph.json","fetch_events":"https://pith.science/api/pith-number/V6TWSWFMSXXEIHP5OXBTOSG3U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/action/storage_attestation","attest_author":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/action/author_attestation","sign_citation":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/action/citation_signature","submit_replication":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/action/replication_record"}},"created_at":"2026-05-20T01:05:50.360589+00:00","updated_at":"2026-05-20T01:05:50.360589+00:00"}