{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OL7NRH2AVIIGSVPLFZQNM4DSZP","short_pith_number":"pith:OL7NRH2A","schema_version":"1.0","canonical_sha256":"72fed89f40aa106955eb2e60d67072cbde80dae4c139f6a4b50f3c2442d122cf","source":{"kind":"arxiv","id":"2309.04369","version":1},"attestation_state":"computed","paper":{"title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiatong Li, Qi Liu, Rui Li","submitted_at":"2023-09-08T15:00:41Z","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"},"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":"2309.04369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T15:00:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ddbfaf4e72c1d8a9849f33524e435701b29b23bc1b45a36e79601da5413f903","abstract_canon_sha256":"ab35a2edda03a99555393a856a32677c0b8a91649a4681d5068e5f871e509671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:58.958090Z","signature_b64":"TqKUOIZ+Em3tflX1UvNeyiqc4stgT/1+HuHbVMtjVd+MaR7DpzB6CrCmZ9YRZRo66AeRMiNbMv+aVMUKMt5bBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72fed89f40aa106955eb2e60d67072cbde80dae4c139f6a4b50f3c2442d122cf","last_reissued_at":"2026-07-05T06:48:58.957672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:58.957672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiatong Li, Qi Liu, Rui Li","submitted_at":"2023-09-08T15:00:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04369","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/2309.04369/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":"2309.04369","created_at":"2026-07-05T06:48:58.957735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04369v1","created_at":"2026-07-05T06:48:58.957735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04369","created_at":"2026-07-05T06:48:58.957735+00:00"},{"alias_kind":"pith_short_12","alias_value":"OL7NRH2AVIIG","created_at":"2026-07-05T06:48:58.957735+00:00"},{"alias_kind":"pith_short_16","alias_value":"OL7NRH2AVIIGSVPL","created_at":"2026-07-05T06:48:58.957735+00:00"},{"alias_kind":"pith_short_8","alias_value":"OL7NRH2A","created_at":"2026-07-05T06:48:58.957735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19377","citing_title":"The Evaluation Game: Beyond Static LLM Benchmarking","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP","json":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP.json","graph_json":"https://pith.science/api/pith-number/OL7NRH2AVIIGSVPLFZQNM4DSZP/graph.json","events_json":"https://pith.science/api/pith-number/OL7NRH2AVIIGSVPLFZQNM4DSZP/events.json","paper":"https://pith.science/paper/OL7NRH2A"},"agent_actions":{"view_html":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP","download_json":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP.json","view_paper":"https://pith.science/paper/OL7NRH2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04369&json=true","fetch_graph":"https://pith.science/api/pith-number/OL7NRH2AVIIGSVPLFZQNM4DSZP/graph.json","fetch_events":"https://pith.science/api/pith-number/OL7NRH2AVIIGSVPLFZQNM4DSZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP/action/storage_attestation","attest_author":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP/action/author_attestation","sign_citation":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP/action/citation_signature","submit_replication":"https://pith.science/pith/OL7NRH2AVIIGSVPLFZQNM4DSZP/action/replication_record"}},"created_at":"2026-07-05T06:48:58.957735+00:00","updated_at":"2026-07-05T06:48:58.957735+00:00"}