{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:767QURK7E6FABR3YQ53ZBLYKMV","short_pith_number":"pith:767QURK7","schema_version":"1.0","canonical_sha256":"ffbf0a455f278a00c778877790af0a656baf21fe9164fd7d99ae3be97334e67c","source":{"kind":"arxiv","id":"2504.02323","version":4},"attestation_state":"computed","paper":{"title":"CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashwin T S, Clayton Cohn, Gautam Biswas, Naveeduddin Mohammed","submitted_at":"2025-04-03T06:53:34Z","abstract_excerpt":"Large language models (LLMs) have created new opportunities to assist teachers and support student learning. While researchers have explored various prompt engineering approaches in educational contexts, the degree to which these approaches generalize across domains--such as science, computing, and engineering--remains underexplored. In this paper, we introduce Chain-of-Thought Prompting + Active Learning (CoTAL), an LLM-based approach to formative assessment scoring that (1) leverages Evidence-Centered Design (ECD) to align assessments and rubrics with curriculum goals, (2) applies human-in-t"},"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":"2504.02323","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T06:53:34Z","cross_cats_sorted":[],"title_canon_sha256":"d7166c080c08231ac6f76370bb62bc67abcdf2300349c783fb9fe774d9e53b30","abstract_canon_sha256":"6f8475e299082039a8a990cb02d6ed8e31179f1166bd323f82a76f6fe283ec22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:55.881219Z","signature_b64":"uGsQNKqr58H7wpjZQspag+k9wSc5ko/cm6alIFL4+NFR7Qg8NWtQcXXcujgBQpNo9TKuy4V+EQkw06ieE4ExAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbf0a455f278a00c778877790af0a656baf21fe9164fd7d99ae3be97334e67c","last_reissued_at":"2026-06-10T01:10:55.880120Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:55.880120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashwin T S, Clayton Cohn, Gautam Biswas, Naveeduddin Mohammed","submitted_at":"2025-04-03T06:53:34Z","abstract_excerpt":"Large language models (LLMs) have created new opportunities to assist teachers and support student learning. While researchers have explored various prompt engineering approaches in educational contexts, the degree to which these approaches generalize across domains--such as science, computing, and engineering--remains underexplored. In this paper, we introduce Chain-of-Thought Prompting + Active Learning (CoTAL), an LLM-based approach to formative assessment scoring that (1) leverages Evidence-Centered Design (ECD) to align assessments and rubrics with curriculum goals, (2) applies human-in-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02323","kind":"arxiv","version":4},"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/2504.02323/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":"2504.02323","created_at":"2026-06-10T01:10:55.880292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02323v4","created_at":"2026-06-10T01:10:55.880292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02323","created_at":"2026-06-10T01:10:55.880292+00:00"},{"alias_kind":"pith_short_12","alias_value":"767QURK7E6FA","created_at":"2026-06-10T01:10:55.880292+00:00"},{"alias_kind":"pith_short_16","alias_value":"767QURK7E6FABR3Y","created_at":"2026-06-10T01:10:55.880292+00:00"},{"alias_kind":"pith_short_8","alias_value":"767QURK7","created_at":"2026-06-10T01:10:55.880292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2505.17238","citing_title":"Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05410","citing_title":"LaTA: A Drop-in, FERPA-Compliant Local-LLM Autograder for Upper-Division STEM Coursework","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV","json":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV.json","graph_json":"https://pith.science/api/pith-number/767QURK7E6FABR3YQ53ZBLYKMV/graph.json","events_json":"https://pith.science/api/pith-number/767QURK7E6FABR3YQ53ZBLYKMV/events.json","paper":"https://pith.science/paper/767QURK7"},"agent_actions":{"view_html":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV","download_json":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV.json","view_paper":"https://pith.science/paper/767QURK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02323&json=true","fetch_graph":"https://pith.science/api/pith-number/767QURK7E6FABR3YQ53ZBLYKMV/graph.json","fetch_events":"https://pith.science/api/pith-number/767QURK7E6FABR3YQ53ZBLYKMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV/action/storage_attestation","attest_author":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV/action/author_attestation","sign_citation":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV/action/citation_signature","submit_replication":"https://pith.science/pith/767QURK7E6FABR3YQ53ZBLYKMV/action/replication_record"}},"created_at":"2026-06-10T01:10:55.880292+00:00","updated_at":"2026-06-10T01:10:55.880292+00:00"}