{"dataset":"Research corpus data dictionary","dataset_id":"data-dictionary","description":"Field names, JSON types, nullability, and definitions for every tabular dataset.","method":"Inspect the generated records after all primary datasets have been built.","record_count":92,"records":[{"dataset_id":"opener-rankings","description":"Lowercase five-letter accepted guess.","field":"word","nullable":false,"type":"string"},{"dataset_id":"opener-rankings","description":"Mean turns among games solved within six under the fixed policy.","field":"average_guesses","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Percentage of simulated games solved within six turns.","field":"win_rate_percent","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Population standard deviation of turns among games solved within six.","field":"volatility","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Failed within six.","field":"failed_within_six","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Simulation answers solved on turn 1.","field":"solved_on_turn_1","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Simulation answers solved on turn 2.","field":"solved_on_turn_2","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Simulation answers solved on turn 3.","field":"solved_on_turn_3","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Simulation answers solved on turn 4.","field":"solved_on_turn_4","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Simulation answers solved on turn 5.","field":"solved_on_turn_5","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Simulation answers solved on turn 6.","field":"solved_on_turn_6","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Shannon entropy of the feedback partition, in bits.","field":"entropy_bits","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Expected candidate count after the represented guess or pair.","field":"expected_remaining","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Posterior entropy bits.","field":"posterior_entropy_bits","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Candidate count left by this measurement.","field":"effective_remaining","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Largest candidate bucket after the represented guess or pair.","field":"worst_remaining","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Probability bucket ge 4.","field":"probability_bucket_ge_4","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Probability bucket ge 6.","field":"probability_bucket_ge_6","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Probability solve now.","field":"probability_solve_now","nullable":false,"type":"number"},{"dataset_id":"opener-rankings","description":"Unique feedback patterns.","field":"unique_feedback_patterns","nullable":false,"type":"integer"},{"dataset_id":"opener-rankings","description":"Largest partition pattern.","field":"largest_partition_pattern","nullable":false,"type":"string"},{"dataset_id":"opener-rankings","description":"Information tier.","field":"information_tier","nullable":false,"type":"string"},{"dataset_id":"opener-rankings","description":"Boolean indicator for the named condition.","field":"is_answer_candidate","nullable":false,"type":"boolean"},{"dataset_id":"opener-rankings","description":"Rank within this dataset using the method documented for it.","field":"rank","nullable":false,"type":"integer"},{"dataset_id":"answer-history-summary","description":"Metric.","field":"metric","nullable":false,"type":"string"},{"dataset_id":"answer-history-summary","description":"Value.","field":"value","nullable":false,"type":"string"},{"dataset_id":"letter-frequency","description":"Scope.","field":"scope","nullable":false,"type":"string"},{"dataset_id":"letter-frequency","description":"Position.","field":"position","nullable":false,"type":"string"},{"dataset_id":"letter-frequency","description":"Letter.","field":"letter","nullable":false,"type":"string"},{"dataset_id":"letter-frequency","description":"Count.","field":"count","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"ISO 8601 date of a globally completed puzzle.","field":"date","nullable":false,"type":"string"},{"dataset_id":"puzzle-difficulty","description":"Puzzle number derived from the June 19, 2021 day-zero convention.","field":"puzzle_number","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Repeat number.","field":"repeat_number","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Boolean indicator for the named condition.","field":"is_repeat","nullable":false,"type":"boolean"},{"dataset_id":"puzzle-difficulty","description":"Optimal turns.","field":"optimal_turns","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Optimal turns imputed.","field":"optimal_turns_imputed","nullable":false,"type":"boolean"},{"dataset_id":"puzzle-difficulty","description":"Candidate count left by this measurement.","field":"crane_remaining","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Candidate count left by this measurement.","field":"slate_remaining","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Candidate count left by this measurement.","field":"adieu_remaining","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Candidate count left by this measurement.","field":"average_reference_remaining","nullable":false,"type":"number"},{"dataset_id":"puzzle-difficulty","description":"Size of the answer's largest one-slot family; the answer is omitted.","field":"trap_family_size","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Count represented by this field.","field":"repeated_letter_count","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Count represented by this field.","field":"vowel_count","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Midrank percentile within the released completed-puzzle rows.","field":"solver_pressure_percentile","nullable":false,"type":"integer"},{"dataset_id":"puzzle-difficulty","description":"Human-readable band for solver_pressure_percentile.","field":"solver_pressure_label","nullable":false,"type":"string"},{"dataset_id":"trap-families","description":"Rank within this dataset using the method documented for it.","field":"rank","nullable":false,"type":"integer"},{"dataset_id":"trap-families","description":"Five-character one-slot family pattern; underscore is the varying position.","field":"pattern","nullable":false,"type":"string"},{"dataset_id":"trap-families","description":"Varying position.","field":"varying_position","nullable":false,"type":"integer"},{"dataset_id":"trap-families","description":"Count represented by this field.","field":"family_size","nullable":false,"type":"integer"},{"dataset_id":"trap-families","description":"Alphabetical list of working-pool members in the family.","field":"member_words","nullable":false,"type":"array"},{"dataset_id":"trap-families","description":"Varying letters.","field":"varying_letters","nullable":false,"type":"array"},{"dataset_id":"trap-families","description":"Recorded appearances through cutoff.","field":"recorded_appearances_through_cutoff","nullable":false,"type":"integer"},{"dataset_id":"trap-families","description":"Best probe.","field":"best_probe","nullable":false,"type":"string"},{"dataset_id":"trap-families","description":"Best probe can be answer.","field":"best_probe_can_be_answer","nullable":false,"type":"boolean"},{"dataset_id":"trap-families","description":"Candidate count left by this measurement.","field":"best_probe_expected_remaining","nullable":false,"type":"number"},{"dataset_id":"trap-families","description":"Candidate count left by this measurement.","field":"best_probe_worst_remaining","nullable":false,"type":"integer"},{"dataset_id":"trap-families","description":"Best probe entropy bits.","field":"best_probe_entropy_bits","nullable":false,"type":"number"},{"dataset_id":"trap-families","description":"Candidate only guess.","field":"candidate_only_guess","nullable":false,"type":"string"},{"dataset_id":"trap-families","description":"Candidate count left by this measurement.","field":"candidate_only_expected_remaining","nullable":false,"type":"number"},{"dataset_id":"trap-families","description":"Candidate count left by this measurement.","field":"candidate_only_worst_remaining","nullable":false,"type":"integer"},{"dataset_id":"trap-families","description":"Count represented by this field.","field":"probe_search_count","nullable":false,"type":"integer"},{"dataset_id":"opener-feedback-branches","description":"Opener.","field":"opener","nullable":false,"type":"string"},{"dataset_id":"opener-feedback-branches","description":"Opener overall rank.","field":"opener_overall_rank","nullable":false,"type":"integer"},{"dataset_id":"opener-feedback-branches","description":"Branch rank.","field":"branch_rank","nullable":false,"type":"integer"},{"dataset_id":"opener-feedback-branches","description":"Five feedback digits: 0 gray, 1 yellow, and 2 green.","field":"feedback","nullable":false,"type":"string"},{"dataset_id":"opener-feedback-branches","description":"Working-pool answers that produce this exact feedback.","field":"remaining_answers","nullable":false,"type":"integer"},{"dataset_id":"opener-feedback-branches","description":"Branch frequency under a uniform working-answer prior.","field":"probability_percent","nullable":false,"type":"number"},{"dataset_id":"opener-feedback-branches","description":"Boolean indicator for the named condition.","field":"is_all_gray","nullable":false,"type":"boolean"},{"dataset_id":"opener-feedback-branches","description":"Boolean indicator for the named condition.","field":"is_solved","nullable":false,"type":"boolean"},{"dataset_id":"familiar-opener-benchmark","description":"Familiar rank.","field":"familiar_rank","nullable":false,"type":"integer"},{"dataset_id":"familiar-opener-benchmark","description":"Overall rank.","field":"overall_rank","nullable":false,"type":"integer"},{"dataset_id":"familiar-opener-benchmark","description":"Lowercase five-letter accepted guess.","field":"word","nullable":false,"type":"string"},{"dataset_id":"familiar-opener-benchmark","description":"Reason the word passes the site's player-facing vocabulary screen.","field":"vocabulary_class","nullable":false,"type":"string"},{"dataset_id":"familiar-opener-benchmark","description":"Boolean indicator for the named condition.","field":"is_answer_candidate","nullable":false,"type":"boolean"},{"dataset_id":"familiar-opener-benchmark","description":"True because Hard Mode imposes no prior-hint constraint on turn one.","field":"hard_mode_opening_legal","nullable":false,"type":"boolean"},{"dataset_id":"familiar-opener-benchmark","description":"Mode used by the six-turn continuation simulation columns.","field":"six_turn_continuation_mode","nullable":false,"type":"string"},{"dataset_id":"familiar-opener-benchmark","description":"Mean turns among games solved within six under the fixed policy.","field":"average_guesses","nullable":false,"type":"number"},{"dataset_id":"familiar-opener-benchmark","description":"Percentage of simulated games solved within six turns.","field":"win_rate_percent","nullable":false,"type":"number"},{"dataset_id":"familiar-opener-benchmark","description":"Population standard deviation of turns among games solved within six.","field":"volatility","nullable":false,"type":"number"},{"dataset_id":"familiar-opener-benchmark","description":"Shannon entropy of the feedback partition, in bits.","field":"entropy_bits","nullable":false,"type":"number"},{"dataset_id":"familiar-opener-benchmark","description":"Expected candidate count after the represented guess or pair.","field":"expected_remaining","nullable":false,"type":"number"},{"dataset_id":"familiar-opener-benchmark","description":"Largest candidate bucket after the represented guess or pair.","field":"worst_remaining","nullable":false,"type":"integer"},{"dataset_id":"opening-pair-frontier","description":"Joint entropy rank.","field":"joint_entropy_rank","nullable":false,"type":"integer"},{"dataset_id":"opening-pair-frontier","description":"Word 1.","field":"word_1","nullable":false,"type":"string"},{"dataset_id":"opening-pair-frontier","description":"Word 2.","field":"word_2","nullable":false,"type":"string"},{"dataset_id":"opening-pair-frontier","description":"Shannon entropy of the pair's joint feedback signature, in bits.","field":"joint_entropy_bits","nullable":false,"type":"number"},{"dataset_id":"opening-pair-frontier","description":"Expected candidate count after the represented guess or pair.","field":"expected_remaining","nullable":false,"type":"number"},{"dataset_id":"opening-pair-frontier","description":"Largest candidate bucket after the represented guess or pair.","field":"worst_remaining","nullable":false,"type":"integer"},{"dataset_id":"opening-pair-frontier","description":"Unique joint patterns.","field":"unique_joint_patterns","nullable":false,"type":"integer"},{"dataset_id":"opening-pair-frontier","description":"Distinct letters.","field":"distinct_letters","nullable":false,"type":"integer"},{"dataset_id":"opening-pair-frontier","description":"Shared letters.","field":"shared_letters","nullable":false,"type":"string"},{"dataset_id":"opening-pair-frontier","description":"Whether no evaluated pair is better on both expected and worst remainder.","field":"expected_worst_pareto","nullable":false,"type":"boolean"}],"release":"v2026-07-15","schema_version":1}