{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YALD7SI7HVSNBO5NVBD2HVYBTN","short_pith_number":"pith:YALD7SI7","schema_version":"1.0","canonical_sha256":"c0163fc91f3d64d0bbada847a3d7019b54f3a5c5c6b7cf1d9eb160cec98b66d1","source":{"kind":"arxiv","id":"2310.18373","version":2},"attestation_state":"computed","paper":{"title":"Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bill Roberts, Joshua McGrane, Libby Hills, Owen Henkel","submitted_at":"2023-10-26T17:05:40Z","abstract_excerpt":"Open-ended questions, which require students to produce multi-word, nontrivial responses, are a popular tool for formative assessment as they provide more specific insights into what students do and don't know. However, grading open-ended questions can be time-consuming leading teachers to resort to simpler question formats or conduct fewer formative assessments. While there has been a longstanding interest in automating of short-answer grading (ASAG), but previous approaches have been technically complex, limiting their use in formative assessment contexts. The newest generation of Large Lang"},"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":"2310.18373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:05:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d60116fa3ee176263712e754723110acb30b20347252cee0deb6ee6101c2b6c7","abstract_canon_sha256":"f4853c132269e975a591ab6b97bc6449d18189a567d60d132fb6d69d123c1df3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:41.075419Z","signature_b64":"zlP0rN7IdkPiMTVQibwzrWV4hkNBO4b9ftxKrNUPFINogpAvZWmJUg4xIjbkrpoDEWl28eUItyVH6EByA0cCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0163fc91f3d64d0bbada847a3d7019b54f3a5c5c6b7cf1d9eb160cec98b66d1","last_reissued_at":"2026-07-05T08:15:41.074921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:41.074921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bill Roberts, Joshua McGrane, Libby Hills, Owen Henkel","submitted_at":"2023-10-26T17:05:40Z","abstract_excerpt":"Open-ended questions, which require students to produce multi-word, nontrivial responses, are a popular tool for formative assessment as they provide more specific insights into what students do and don't know. However, grading open-ended questions can be time-consuming leading teachers to resort to simpler question formats or conduct fewer formative assessments. While there has been a longstanding interest in automating of short-answer grading (ASAG), but previous approaches have been technically complex, limiting their use in formative assessment contexts. The newest generation of Large Lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18373","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/2310.18373/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":"2310.18373","created_at":"2026-07-05T08:15:41.074982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18373v2","created_at":"2026-07-05T08:15:41.074982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18373","created_at":"2026-07-05T08:15:41.074982+00:00"},{"alias_kind":"pith_short_12","alias_value":"YALD7SI7HVSN","created_at":"2026-07-05T08:15:41.074982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YALD7SI7HVSNBO5N","created_at":"2026-07-05T08:15:41.074982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YALD7SI7","created_at":"2026-07-05T08:15:41.074982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12422","citing_title":"Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering","ref_index":249,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN","json":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN.json","graph_json":"https://pith.science/api/pith-number/YALD7SI7HVSNBO5NVBD2HVYBTN/graph.json","events_json":"https://pith.science/api/pith-number/YALD7SI7HVSNBO5NVBD2HVYBTN/events.json","paper":"https://pith.science/paper/YALD7SI7"},"agent_actions":{"view_html":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN","download_json":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN.json","view_paper":"https://pith.science/paper/YALD7SI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18373&json=true","fetch_graph":"https://pith.science/api/pith-number/YALD7SI7HVSNBO5NVBD2HVYBTN/graph.json","fetch_events":"https://pith.science/api/pith-number/YALD7SI7HVSNBO5NVBD2HVYBTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN/action/storage_attestation","attest_author":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN/action/author_attestation","sign_citation":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN/action/citation_signature","submit_replication":"https://pith.science/pith/YALD7SI7HVSNBO5NVBD2HVYBTN/action/replication_record"}},"created_at":"2026-07-05T08:15:41.074982+00:00","updated_at":"2026-07-05T08:15:41.074982+00:00"}