{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V6TWSWFMSXXEIHP5OXBTOSG3U5","short_pith_number":"pith:V6TWSWFM","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"},"canonical_sha256":"afa76958ac95ee441dfd75c33748dba76a9b51f411af1ab9ed1885d48bedcac3","source":{"kind":"arxiv","id":"2605.19529","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19529","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19529v1","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19529","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"V6TWSWFMSXXE","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"V6TWSWFMSXXEIHP5","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"V6TWSWFM","created_at":"2026-05-20T01:05:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V6TWSWFMSXXEIHP5OXBTOSG3U5","target":"record","payload":{"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"},"canonical_sha256":"afa76958ac95ee441dfd75c33748dba76a9b51f411af1ab9ed1885d48bedcac3","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"},"source_kind":"arxiv","source_id":"2605.19529","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCQ7nH0QXlv1B7ZSYZXYNWgSbiKtN3YM0NQoippEWzXWibuoGTcz1fOdQmkCIcsKYzvbrWEReqthxEPNAjVbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T15:09:58.823271Z"},"content_sha256":"78dd5fc9fab42b7f5fb973dc292f7d1253806d8c27a191438c6a7b22de970829","schema_version":"1.0","event_id":"sha256:78dd5fc9fab42b7f5fb973dc292f7d1253806d8c27a191438c6a7b22de970829"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V6TWSWFMSXXEIHP5OXBTOSG3U5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYEn3th0WWdgwZ1O5PFgg+pnIMGm8k4aPKuV7dCYbF6m3Z8NBXFxQDZiBWilBHEia7ZrtHxoiXEvUwW3qnFhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T15:09:58.823672Z"},"content_sha256":"6935c51600149abde849ee3e5251280f8abee2a4fc10c337edc570590089a2ad","schema_version":"1.0","event_id":"sha256:6935c51600149abde849ee3e5251280f8abee2a4fc10c337edc570590089a2ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/bundle.json","state_url":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/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":"2026-05-22T15:09:58Z","links":{"resolver":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5","bundle":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/bundle.json","state":"https://pith.science/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6TWSWFMSXXEIHP5OXBTOSG3U5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V6TWSWFMSXXEIHP5OXBTOSG3U5","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":"31cb36027511b67903833fb67407aca22b6857d05ec390d0c09771e524ea0b36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T08:30:39Z","title_canon_sha256":"85c5dabcdc6c9b9379332c34ed0e96eab44c6c06eef7c05d7e5b1791332a69b5"},"schema_version":"1.0","source":{"id":"2605.19529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19529","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19529v1","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19529","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"V6TWSWFMSXXE","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"V6TWSWFMSXXEIHP5","created_at":"2026-05-20T01:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"V6TWSWFM","created_at":"2026-05-20T01:05:50Z"}],"graph_snapshots":[{"event_id":"sha256:6935c51600149abde849ee3e5251280f8abee2a4fc10c337edc570590089a2ad","target":"graph","created_at":"2026-05-20T01:05:50Z","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/2605.19529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Che Yee Lye, Grandee Lee, Luke Peh, Yue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T08:30:39Z","title":"Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19529","kind":"arxiv","version":1},"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":"sha256:78dd5fc9fab42b7f5fb973dc292f7d1253806d8c27a191438c6a7b22de970829","target":"record","created_at":"2026-05-20T01:05:50Z","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":"31cb36027511b67903833fb67407aca22b6857d05ec390d0c09771e524ea0b36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T08:30:39Z","title_canon_sha256":"85c5dabcdc6c9b9379332c34ed0e96eab44c6c06eef7c05d7e5b1791332a69b5"},"schema_version":"1.0","source":{"id":"2605.19529","kind":"arxiv","version":1}},"canonical_sha256":"afa76958ac95ee441dfd75c33748dba76a9b51f411af1ab9ed1885d48bedcac3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afa76958ac95ee441dfd75c33748dba76a9b51f411af1ab9ed1885d48bedcac3","first_computed_at":"2026-05-20T01:05:50.360477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:50.360477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IYikEYZTldLqrxEofr0ypajjjxW3NY8HgamIgUDO8p2UkxieDxpIsdcgT+giGey/8P/3Ya7NwNU+P+1L7a7sCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:50.361202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78dd5fc9fab42b7f5fb973dc292f7d1253806d8c27a191438c6a7b22de970829","sha256:6935c51600149abde849ee3e5251280f8abee2a4fc10c337edc570590089a2ad"],"state_sha256":"b398b89a2f7ce5e1f9887e37d574a1478b2d3d8adf5eda4cf0c1a3522498c334"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpEKJ0Q8OyjVdk/qNkaidn7twm0n6am7pqxP2aIRPjTJq8NuEte1+kzHFpWDKldeq/+L2mcJnepMxkeUylM0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T15:09:58.826406Z","bundle_sha256":"1ee6f0940087b7b4c3074957fccc5a6b6575c4914abfbcdc9d37bae8aa15e8a7"}}