{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:43DE4JPF2RMKXAUW4OUAL3WVRH","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":"84fd6ad64a6399db954730f98893705851773c73cc9a7fcbd54c7b547ed882dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-07T00:17:24Z","title_canon_sha256":"04d0efd7c7ef0711a52f657261967a822dda15526104052f38d7022488c175e2"},"schema_version":"1.0","source":{"id":"2407.05216","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05216","created_at":"2026-07-05T09:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05216v2","created_at":"2026-07-05T09:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05216","created_at":"2026-07-05T09:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"43DE4JPF2RMK","created_at":"2026-07-05T09:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"43DE4JPF2RMKXAUW","created_at":"2026-07-05T09:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"43DE4JPF","created_at":"2026-07-05T09:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:a294641f49e2db5fc3a152a9a5cd2ecd9030faf59fe795b872dcdb6380aad956","target":"graph","created_at":"2026-07-05T09:10:01Z","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/2407.05216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. However, it is unclear whether these LLM-based evaluators can be applied in real-world classrooms to assess student assignments. This empirical report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students. Based on student responses, we find that LLM-based assignment evaluators are generally acceptable to students when students have free access to these LLM-based evaluators. However, students also noted that the LLM sometimes f","authors_text":"Cheng-Han Chiang, Chienchou Yang, Chun-Yi Kuan, Hung-yi Lee, Wei-Chih Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-07T00:17:24Z","title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05216","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":"sha256:28e604f095ccf99b9f4dc21aebfffe2133a0abd3c3fed59ae5fa7a0f932931f9","target":"record","created_at":"2026-07-05T09:10:01Z","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":"84fd6ad64a6399db954730f98893705851773c73cc9a7fcbd54c7b547ed882dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-07T00:17:24Z","title_canon_sha256":"04d0efd7c7ef0711a52f657261967a822dda15526104052f38d7022488c175e2"},"schema_version":"1.0","source":{"id":"2407.05216","kind":"arxiv","version":2}},"canonical_sha256":"e6c64e25e5d458ab8296e3a805eed589ef82bb7d4b6fb8bfb86a1329b8badb84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6c64e25e5d458ab8296e3a805eed589ef82bb7d4b6fb8bfb86a1329b8badb84","first_computed_at":"2026-07-05T09:10:01.487836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:01.487836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tpsdQfSaZU/2jr1994Uri+VC6DTLpliUSzxb6/8BAGacUOa/B3ByOI7OmjrhwmoWH1dZWnDJjHfTiLSnooPtDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:01.488303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05216","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28e604f095ccf99b9f4dc21aebfffe2133a0abd3c3fed59ae5fa7a0f932931f9","sha256:a294641f49e2db5fc3a152a9a5cd2ecd9030faf59fe795b872dcdb6380aad956"],"state_sha256":"324c90e6dacf3b3d0d803aad135cf7d60ebd7d078e841b34bb2d152ee09bc5ad"}