{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:76GERYO5NN6HEVSYZEDF47PZP6","short_pith_number":"pith:76GERYO5","schema_version":"1.0","canonical_sha256":"ff8c48e1dd6b7c725658c9065e7df97f981c6cd5e97b9efed1398db8ed98ef7a","source":{"kind":"arxiv","id":"2506.01793","version":1},"attestation_state":"computed","paper":{"title":"Human-Centric Evaluation for Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunyi Li, Farong Wen, Guangtao Zhai, Junying Wang, Kaiyuan Ji, Xiaorong Zhu, Yijin Guo, Zicheng Zhang","submitted_at":"2025-06-02T15:33:29Z","abstract_excerpt":"Currently, nearly all evaluations of foundation models focus on objective metrics, emphasizing quiz performance to define model capabilities. While this model-centric approach enables rapid performance assessment, it fails to reflect authentic human experiences. To address this gap, we propose a Human-Centric subjective Evaluation (HCE) framework, focusing on three core dimensions: problem-solving ability, information quality, and interaction experience. Through experiments involving Deepseek R1, OpenAI o3 mini, Grok 3, and Gemini 2.5, we conduct over 540 participant-driven evaluations, where "},"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":"2506.01793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T15:33:29Z","cross_cats_sorted":[],"title_canon_sha256":"3da39a2c377fc87a3e0ce53fd1ae6e8c0226cc8bbc5d64a66b6b577baf398d82","abstract_canon_sha256":"b774717fe995c06038947cca31536cf7c055113f077e4b64b98ddf740f543860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:19.412752Z","signature_b64":"35eqLCYQm/9so/ri6P9nGWt7F8XbyslTWj09z8RTUHfSGuOU4iK5c2aJBt43zN+mAeS9Whbjbqe6rFSyHn0FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff8c48e1dd6b7c725658c9065e7df97f981c6cd5e97b9efed1398db8ed98ef7a","last_reissued_at":"2026-07-05T11:14:19.412270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:19.412270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Centric Evaluation for Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunyi Li, Farong Wen, Guangtao Zhai, Junying Wang, Kaiyuan Ji, Xiaorong Zhu, Yijin Guo, Zicheng Zhang","submitted_at":"2025-06-02T15:33:29Z","abstract_excerpt":"Currently, nearly all evaluations of foundation models focus on objective metrics, emphasizing quiz performance to define model capabilities. While this model-centric approach enables rapid performance assessment, it fails to reflect authentic human experiences. To address this gap, we propose a Human-Centric subjective Evaluation (HCE) framework, focusing on three core dimensions: problem-solving ability, information quality, and interaction experience. Through experiments involving Deepseek R1, OpenAI o3 mini, Grok 3, and Gemini 2.5, we conduct over 540 participant-driven evaluations, where "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01793","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/2506.01793/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":"2506.01793","created_at":"2026-07-05T11:14:19.412329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01793v1","created_at":"2026-07-05T11:14:19.412329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01793","created_at":"2026-07-05T11:14:19.412329+00:00"},{"alias_kind":"pith_short_12","alias_value":"76GERYO5NN6H","created_at":"2026-07-05T11:14:19.412329+00:00"},{"alias_kind":"pith_short_16","alias_value":"76GERYO5NN6HEVSY","created_at":"2026-07-05T11:14:19.412329+00:00"},{"alias_kind":"pith_short_8","alias_value":"76GERYO5","created_at":"2026-07-05T11:14:19.412329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18038","citing_title":"First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6","json":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6.json","graph_json":"https://pith.science/api/pith-number/76GERYO5NN6HEVSYZEDF47PZP6/graph.json","events_json":"https://pith.science/api/pith-number/76GERYO5NN6HEVSYZEDF47PZP6/events.json","paper":"https://pith.science/paper/76GERYO5"},"agent_actions":{"view_html":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6","download_json":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6.json","view_paper":"https://pith.science/paper/76GERYO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01793&json=true","fetch_graph":"https://pith.science/api/pith-number/76GERYO5NN6HEVSYZEDF47PZP6/graph.json","fetch_events":"https://pith.science/api/pith-number/76GERYO5NN6HEVSYZEDF47PZP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6/action/storage_attestation","attest_author":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6/action/author_attestation","sign_citation":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6/action/citation_signature","submit_replication":"https://pith.science/pith/76GERYO5NN6HEVSYZEDF47PZP6/action/replication_record"}},"created_at":"2026-07-05T11:14:19.412329+00:00","updated_at":"2026-07-05T11:14:19.412329+00:00"}