{"paper":{"title":"Does Deep Knowledge Tracing Learn Semantic Relations Between Knowledge Components?","arxiv_id":"2611.16323","primary_cat":"cs.LG","submitted_at":"2026-11-12T05:47:46+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Deep Knowledge Tracing (DKT) is a knowledge tracing (KT) model that updates a shared latent state from sequences of interactions, each pairing a knowledge component (KC) with a response.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.98,"id":"s1","own":false,"role":"background","text":"An interaction with one KC can therefore affect predictions for other KCs.","hedge":{"p":0.56,"label":"hedged_possibility"},"own_p":0.08,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.0,"background":0.98,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":2,"p":0.79,"id":"s2","own":false,"role":"gap","text":"We ask: Are the KC relations learned by DKT semantic?","hedge":{"p":0.96,"label":"unclear"},"own_p":0.2,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.79,"method":0.0,"result":0.0,"background":0.09,"limitation":0.0,"future_work":0.0,"contribution":0.12,"interpretation":0.0}},{"i":3,"p":0.91,"id":"s3","own":true,"role":"method","text":"We construct text-derived semantic KC representations using nine pipelines to test whether the conclusions hold across alternative ways of constructing those representations.","hedge":{"p":0.89,"label":"asserted"},"own_p":0.94,"main_claim_p":0.02,"quantitative":true,"quantitative_p":0.79,"role_probabilities":{"gap":0.0,"method":0.91,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.09,"interpretation":0.0}},{"i":4,"p":0.96,"id":"s4","own":true,"role":"method","text":"The first test compares DKT-derived KC relation graphs with semantic relation structures induced by pairwise cosine similarities among the KC representations.","hedge":{"p":0.73,"label":"asserted"},"own_p":0.87,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.62,"role_probabilities":{"gap":0.0,"method":0.96,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"Across the evaluated datasets, embedding models, and pipelines, the two structures align only weakly and inconsistently.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.28,"quantitative":true,"quantitative_p":0.69,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":0.95,"id":"s6","own":true,"role":"result","text":"The second test introduces semantic information into DKT; the pretrained text-derived representations do not consistently outperform the standard DKT baseline.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.95,"main_claim_p":0.09,"quantitative":true,"quantitative_p":0.79,"role_probabilities":{"gap":0.0,"method":0.03,"result":0.95,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"In the reduced-data experiments, semantic initialization yields a higher test area under the ROC curve (AUC) than the baseline at eight of nine nested sample sizes for ASSISTments 2017.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.8,"id":"s8","own":true,"role":"result","text":"KC-supervised fine-tuned BERT produces small positive AUC differences in some matched comparisons, but the study does not establish their stability across runs.","hedge":{"p":0.91,"label":"asserted"},"own_p":0.93,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.7,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.8,"background":0.0,"limitation":0.2,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":0.66,"id":"s9","own":true,"role":"result","text":"These effects remain limited and inconsistent.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.88,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.12,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.66,"background":0.0,"limitation":0.09,"future_work":0.0,"contribution":0.0,"interpretation":0.25}},{"i":10,"p":1.0,"id":"s10","own":true,"role":"interpretation","text":"The findings suggest that behavioral, temporal, structural, or psychometric signals may also shape DKT's learned relations.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.63,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}},{"i":11,"p":0.65,"id":"s11","own":true,"role":"interpretation","text":"DKT-derived relations are not primarily semantic: the tested text-derived semantic structures do not strongly recover the DKT-derived relation structure.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.94,"quantitative":false,"quantitative_p":0.3,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.35,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.65}}]},"compiled":{"main_claim":{"p":1.0,"text":"DKT-derived relations are not primarily semantic: the tested text-derived semantic structures do not strongly recover the DKT-derived relation structure.","location":"abstract s11","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":8722,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.03,"states_limitation":0.94,"human_participants":0.16,"controlled_comparison":0.95,"randomized_assignment":0.02,"states_quantitative_result":0.95,"compares_with_prior_results":0.94,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.63,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.28,"observation_or_experiment":0.63,"simulation_or_computation":0.09}},"contribution_type":{"p":1.0,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":1.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.84,"text":"We construct text-derived semantic KC representations using nine pipelines to test whether the conclusions hold across alternative ways of constructing those representations.","location":"abstract s3"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":12,"sentences_in_abstract":12},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}