{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J5DLNCPKXAKTMZRLCUPCLGCJ6L","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":"9f9d6e0fad31de0125cbfc86b5488f014842cb14229786c31de5c239f2eb5f59","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-11T22:59:37Z","title_canon_sha256":"aebbf9d621be432f193ad773db95f6ff499f87cc2ef6bb71050995fd6975fe5b"},"schema_version":"1.0","source":{"id":"2501.06658","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06658","created_at":"2026-07-05T10:00:07Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06658v1","created_at":"2026-07-05T10:00:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06658","created_at":"2026-07-05T10:00:07Z"},{"alias_kind":"pith_short_12","alias_value":"J5DLNCPKXAKT","created_at":"2026-07-05T10:00:07Z"},{"alias_kind":"pith_short_16","alias_value":"J5DLNCPKXAKTMZRL","created_at":"2026-07-05T10:00:07Z"},{"alias_kind":"pith_short_8","alias_value":"J5DLNCPK","created_at":"2026-07-05T10:00:07Z"}],"graph_snapshots":[{"event_id":"sha256:ac608f5be1659942fa44d066cd0436a63312bf7df87bad359ec1f87cd1280ba0","target":"graph","created_at":"2026-07-05T10:00:07Z","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/2501.06658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Assessing learners in ill-defined domains, such as scenario-based human tutoring training, is an area of limited research. Equity training requires a nuanced understanding of context, but do contemporary large language models (LLMs) have a knowledge base that can navigate these nuances? Legacy transformer models like BERT, in contrast, have less real-world knowledge but can be more easily fine-tuned than commercial LLMs. Here, we study whether fine-tuning BERT on human annotations outperforms state-of-the-art LLMs (GPT-4o and GPT-4-Turbo) with few-shot prompting and instruction. We evaluate pe","authors_text":"Conrad Borchers, Danielle Thomas, Kenneth R. Koedinger, Sanjit Kakarla, Shambhavi Bhushan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-11T22:59:37Z","title":"Comparing Few-Shot Prompting of GPT-4 LLMs with BERT Classifiers for Open-Response Assessment in Tutor Equity Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06658","kind":"arxiv","version":1},"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":"sha256:5f83d6305bd49f3dbd160ed753f4924d7f95d8be75bc242efcc6b2c992206fcb","target":"record","created_at":"2026-07-05T10:00:07Z","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":"9f9d6e0fad31de0125cbfc86b5488f014842cb14229786c31de5c239f2eb5f59","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-11T22:59:37Z","title_canon_sha256":"aebbf9d621be432f193ad773db95f6ff499f87cc2ef6bb71050995fd6975fe5b"},"schema_version":"1.0","source":{"id":"2501.06658","kind":"arxiv","version":1}},"canonical_sha256":"4f46b689eab81536662b151e259849f2c4936e3687b4b7f1f7ecfb5530049237","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f46b689eab81536662b151e259849f2c4936e3687b4b7f1f7ecfb5530049237","first_computed_at":"2026-07-05T10:00:07.942516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:07.942516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mikvibe1Pn/HKQFPaMO6r2q9sfEmalpzmPiAPr0U7ePCDPh/jt6zLhxEIlb6hYLLKdV/dHizuO0KyAoBBFoiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:07.942919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06658","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f83d6305bd49f3dbd160ed753f4924d7f95d8be75bc242efcc6b2c992206fcb","sha256:ac608f5be1659942fa44d066cd0436a63312bf7df87bad359ec1f87cd1280ba0"],"state_sha256":"39be1ed2984c656d7f5cd74e14b9cfd246bc45787b04ac99681d472ce59d2650"}