{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OL7NRH2AVIIGSVPLFZQNM4DSZP","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":"ab35a2edda03a99555393a856a32677c0b8a91649a4681d5068e5f871e509671","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T15:00:41Z","title_canon_sha256":"2ddbfaf4e72c1d8a9849f33524e435701b29b23bc1b45a36e79601da5413f903"},"schema_version":"1.0","source":{"id":"2309.04369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04369","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04369v1","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04369","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"OL7NRH2AVIIG","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"pith_short_16","alias_value":"OL7NRH2AVIIGSVPL","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"pith_short_8","alias_value":"OL7NRH2A","created_at":"2026-07-05T06:48:58Z"}],"graph_snapshots":[{"event_id":"sha256:31243f3d65cd6bf0d577cebbbd85580668cd0f047ab4b2cb36edd2401eb340f9","target":"graph","created_at":"2026-07-05T06:48:58Z","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/2309.04369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have made progress in various real-world tasks, which stimulates requirements for the evaluation of LLMs. Existing LLM evaluation methods are mainly supervised signal-based which depends on static datasets and cannot evaluate the ability of LLMs in dynamic real-world scenarios where deep interaction widely exists. Other LLM evaluation methods are human-based which are costly and time-consuming and are incapable of large-scale evaluation of LLMs. To address the issues above, we propose a novel Deep Interaction-based LLM-evaluation framework. In our proposed framewor","authors_text":"Jiatong Li, Qi Liu, Rui Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T15:00:41Z","title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04369","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":"sha256:10ec8b9e175c80fce8f328dfc71b9f30b4b5fa50e4de8afe90bbcba00fdf39da","target":"record","created_at":"2026-07-05T06:48:58Z","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":"ab35a2edda03a99555393a856a32677c0b8a91649a4681d5068e5f871e509671","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T15:00:41Z","title_canon_sha256":"2ddbfaf4e72c1d8a9849f33524e435701b29b23bc1b45a36e79601da5413f903"},"schema_version":"1.0","source":{"id":"2309.04369","kind":"arxiv","version":1}},"canonical_sha256":"72fed89f40aa106955eb2e60d67072cbde80dae4c139f6a4b50f3c2442d122cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72fed89f40aa106955eb2e60d67072cbde80dae4c139f6a4b50f3c2442d122cf","first_computed_at":"2026-07-05T06:48:58.957672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:58.957672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TqKUOIZ+Em3tflX1UvNeyiqc4stgT/1+HuHbVMtjVd+MaR7DpzB6CrCmZ9YRZRo66AeRMiNbMv+aVMUKMt5bBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:58.958090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10ec8b9e175c80fce8f328dfc71b9f30b4b5fa50e4de8afe90bbcba00fdf39da","sha256:31243f3d65cd6bf0d577cebbbd85580668cd0f047ab4b2cb36edd2401eb340f9"],"state_sha256":"7b254e21ceb8bc30ad7e968d48fb2ddb2bec30b0d63326effb3d89167cc70cdd"}