{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XEP63FEVRLPFQQPEFSAZ32VKQP","short_pith_number":"pith:XEP63FEV","schema_version":"1.0","canonical_sha256":"b91fed94958ade5841e42c819deaaa83dfddfa527567c104a74ad1f74836df3c","source":{"kind":"arxiv","id":"2401.06431","version":2},"attestation_state":"computed","paper":{"title":"Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changrong Xiao, Kunpeng Zhang, Qi Fu, Qingping Song, Sean Xin Xu, Wenxing Ma, Yufang Wang","submitted_at":"2024-01-12T07:50:10Z","abstract_excerpt":"Receiving timely and personalized feedback is essential for second-language learners, especially when human instructors are unavailable. This study explores the effectiveness of Large Language Models (LLMs), including both proprietary and open-source models, for Automated Essay Scoring (AES). Through extensive experiments with public and private datasets, we find that while LLMs do not surpass conventional state-of-the-art (SOTA) grading models in performance, they exhibit notable consistency, generalizability, and explainability. We propose an open-source LLM-based AES system, inspired by the"},"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":"2401.06431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T07:50:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae61ca9d594712798f3b932b63a9f1dc074a9e578303d71e80a6d54adf1abd3b","abstract_canon_sha256":"58d09268e521f5ecec5eb00210a1f0384c0f0eb0cecc97818f8684455d206809"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:07.499172Z","signature_b64":"YnkNa1z7OuwfcOzi2kPk/x6+blk6wRNYKoqbkVRjNmEaP5pCAG4yqIVLS2pLJ83WCJ3lr2MnSTDu5h7KwSAmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b91fed94958ade5841e42c819deaaa83dfddfa527567c104a74ad1f74836df3c","last_reissued_at":"2026-07-05T10:18:07.498718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:07.498718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changrong Xiao, Kunpeng Zhang, Qi Fu, Qingping Song, Sean Xin Xu, Wenxing Ma, Yufang Wang","submitted_at":"2024-01-12T07:50:10Z","abstract_excerpt":"Receiving timely and personalized feedback is essential for second-language learners, especially when human instructors are unavailable. This study explores the effectiveness of Large Language Models (LLMs), including both proprietary and open-source models, for Automated Essay Scoring (AES). Through extensive experiments with public and private datasets, we find that while LLMs do not surpass conventional state-of-the-art (SOTA) grading models in performance, they exhibit notable consistency, generalizability, and explainability. We propose an open-source LLM-based AES system, inspired by the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06431","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/2401.06431/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":"2401.06431","created_at":"2026-07-05T10:18:07.498771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06431v2","created_at":"2026-07-05T10:18:07.498771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06431","created_at":"2026-07-05T10:18:07.498771+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEP63FEVRLPF","created_at":"2026-07-05T10:18:07.498771+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEP63FEVRLPFQQPE","created_at":"2026-07-05T10:18:07.498771+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEP63FEV","created_at":"2026-07-05T10:18:07.498771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24973","citing_title":"LLM Performance on a Real, Double-Marked GCSE Benchmark","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20152","citing_title":"From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17569","citing_title":"MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP","json":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP.json","graph_json":"https://pith.science/api/pith-number/XEP63FEVRLPFQQPEFSAZ32VKQP/graph.json","events_json":"https://pith.science/api/pith-number/XEP63FEVRLPFQQPEFSAZ32VKQP/events.json","paper":"https://pith.science/paper/XEP63FEV"},"agent_actions":{"view_html":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP","download_json":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP.json","view_paper":"https://pith.science/paper/XEP63FEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06431&json=true","fetch_graph":"https://pith.science/api/pith-number/XEP63FEVRLPFQQPEFSAZ32VKQP/graph.json","fetch_events":"https://pith.science/api/pith-number/XEP63FEVRLPFQQPEFSAZ32VKQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP/action/storage_attestation","attest_author":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP/action/author_attestation","sign_citation":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP/action/citation_signature","submit_replication":"https://pith.science/pith/XEP63FEVRLPFQQPEFSAZ32VKQP/action/replication_record"}},"created_at":"2026-07-05T10:18:07.498771+00:00","updated_at":"2026-07-05T10:18:07.498771+00:00"}