{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X7OOZEGRIOGGXBZ6GYHF6KGO7W","short_pith_number":"pith:X7OOZEGR","canonical_record":{"source":{"id":"2402.15043","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T01:30:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"83b76ebdd1e9e9ecbb58ef6c482821c48d360bd5e3b4e353e8b9d39f81e1c1a2","abstract_canon_sha256":"00bcc7edb17c08b4fd33d0bffec235638b0074544169290a6232e0d3b91e1752"},"schema_version":"1.0"},"canonical_sha256":"bfdcec90d1438c6b873e360e5f28cefdbf9a9db637ebd017c9d5ee7b95c9bf0a","source":{"kind":"arxiv","id":"2402.15043","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15043","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15043v2","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15043","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"X7OOZEGRIOGG","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"X7OOZEGRIOGGXBZ6","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"X7OOZEGR","created_at":"2026-07-05T08:26:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X7OOZEGRIOGGXBZ6GYHF6KGO7W","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15043","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T01:30:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"83b76ebdd1e9e9ecbb58ef6c482821c48d360bd5e3b4e353e8b9d39f81e1c1a2","abstract_canon_sha256":"00bcc7edb17c08b4fd33d0bffec235638b0074544169290a6232e0d3b91e1752"},"schema_version":"1.0"},"canonical_sha256":"bfdcec90d1438c6b873e360e5f28cefdbf9a9db637ebd017c9d5ee7b95c9bf0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:20.448310Z","signature_b64":"veqk04FsVqiBp3T6YxAxlqATS1xxSCA3sky6tgLNXcjC9F+x33mT9RLSgLgUao2wV0iMpsBP3efDAtxfh7CCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfdcec90d1438c6b873e360e5f28cefdbf9a9db637ebd017c9d5ee7b95c9bf0a","last_reissued_at":"2026-07-05T08:26:20.447834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:20.447834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15043","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vDShvY1sZOTsLQbmXutJQUAyDIj7XULTaPx1IvAVSJChdGqc8m6yIio87K/S/huj0ZU7Er38gExv2QZusf3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:30:47.396559Z"},"content_sha256":"480fb9e86d910ce8b669c61bc62de37dc392b80f5b55ef10d4222a2b14ed9bbb","schema_version":"1.0","event_id":"sha256:480fb9e86d910ce8b669c61bc62de37dc392b80f5b55ef10d4222a2b14ed9bbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X7OOZEGRIOGGXBZ6GYHF6KGO7W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chang Gao, Jindong Wang, Shikun Zhang, Wei Ye, Wenjin Yao, Xing Xie, Yidong Wang, Yue Zhang, Zhuohao Yu","submitted_at":"2024-02-23T01:30:39Z","abstract_excerpt":"Automatic evaluation methods for large language models (LLMs) are hindered by data contamination, leading to inflated assessments of their effectiveness. Existing strategies, which aim to detect contaminated texts, focus on quantifying contamination status instead of accurately gauging model performance. In this paper, we introduce KIEval, a Knowledge-grounded Interactive Evaluation framework, which incorporates an LLM-powered \"interactor\" role for the first time to accomplish a dynamic contamination-resilient evaluation. Starting with a question in a conventional LLM benchmark involving domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15043","kind":"arxiv","version":2},"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/2402.15043/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":"2026-07-05T08:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FNH12v7C7Zvp1ilIEMeZp8Souvg4y+zf1M1eS466AXOUEB5geSBjosFLaw3O8VMdnzyHVASRozhWYUT235NCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:30:47.397106Z"},"content_sha256":"ab8ace8ecaa81f1a7c81e4152036198efe9edf70cbd2664f24c735f9dcda6346","schema_version":"1.0","event_id":"sha256:ab8ace8ecaa81f1a7c81e4152036198efe9edf70cbd2664f24c735f9dcda6346"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W/bundle.json","state_url":"https://pith.science/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W/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":"2026-08-09T06:30:47Z","links":{"resolver":"https://pith.science/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W","bundle":"https://pith.science/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W/bundle.json","state":"https://pith.science/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7OOZEGRIOGGXBZ6GYHF6KGO7W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X7OOZEGRIOGGXBZ6GYHF6KGO7W","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":"00bcc7edb17c08b4fd33d0bffec235638b0074544169290a6232e0d3b91e1752","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T01:30:39Z","title_canon_sha256":"83b76ebdd1e9e9ecbb58ef6c482821c48d360bd5e3b4e353e8b9d39f81e1c1a2"},"schema_version":"1.0","source":{"id":"2402.15043","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15043","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15043v2","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15043","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"X7OOZEGRIOGG","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"X7OOZEGRIOGGXBZ6","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"X7OOZEGR","created_at":"2026-07-05T08:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:ab8ace8ecaa81f1a7c81e4152036198efe9edf70cbd2664f24c735f9dcda6346","target":"graph","created_at":"2026-07-05T08:26:20Z","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/2402.15043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic evaluation methods for large language models (LLMs) are hindered by data contamination, leading to inflated assessments of their effectiveness. Existing strategies, which aim to detect contaminated texts, focus on quantifying contamination status instead of accurately gauging model performance. In this paper, we introduce KIEval, a Knowledge-grounded Interactive Evaluation framework, which incorporates an LLM-powered \"interactor\" role for the first time to accomplish a dynamic contamination-resilient evaluation. Starting with a question in a conventional LLM benchmark involving domai","authors_text":"Chang Gao, Jindong Wang, Shikun Zhang, Wei Ye, Wenjin Yao, Xing Xie, Yidong Wang, Yue Zhang, Zhuohao Yu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T01:30:39Z","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15043","kind":"arxiv","version":2},"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":"sha256:480fb9e86d910ce8b669c61bc62de37dc392b80f5b55ef10d4222a2b14ed9bbb","target":"record","created_at":"2026-07-05T08:26:20Z","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":"00bcc7edb17c08b4fd33d0bffec235638b0074544169290a6232e0d3b91e1752","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T01:30:39Z","title_canon_sha256":"83b76ebdd1e9e9ecbb58ef6c482821c48d360bd5e3b4e353e8b9d39f81e1c1a2"},"schema_version":"1.0","source":{"id":"2402.15043","kind":"arxiv","version":2}},"canonical_sha256":"bfdcec90d1438c6b873e360e5f28cefdbf9a9db637ebd017c9d5ee7b95c9bf0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfdcec90d1438c6b873e360e5f28cefdbf9a9db637ebd017c9d5ee7b95c9bf0a","first_computed_at":"2026-07-05T08:26:20.447834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:20.447834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"veqk04FsVqiBp3T6YxAxlqATS1xxSCA3sky6tgLNXcjC9F+x33mT9RLSgLgUao2wV0iMpsBP3efDAtxfh7CCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:20.448310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15043","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:480fb9e86d910ce8b669c61bc62de37dc392b80f5b55ef10d4222a2b14ed9bbb","sha256:ab8ace8ecaa81f1a7c81e4152036198efe9edf70cbd2664f24c735f9dcda6346"],"state_sha256":"ab81920dd791adddb68d44f5d853a8f431fbf7c1d713a008794c732344a055ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hoHJlstiA4NYKdbZ1lj/QT1EvgmjU7NV7uZE1HCzQ3fm5g7EPuPqQt/kg2he/7wEz+YAkvOYT+fUuIY6o+41Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:30:47.403556Z","bundle_sha256":"43e92fcb2d93b3305ef8450b76a72c81b6773656b8f4ec731be187cb944534cc"}}