| { |
| "task": "NEW-1 pooling-operator vs encoder isolation for the no-binding theorem", |
| "backbone": "sentence-transformers/all-mpnet-base-v2", |
| "bonus_cls_encoder": "BAAI/bge-base-en-v1.5", |
| "n_sentences": 2000, |
| "n_examples": 4000, |
| "by_constr_examples": { |
| "active": 800, |
| "ditrans": 800, |
| "fronted": 800, |
| "passive": 800, |
| "relcl": 800 |
| }, |
| "guard_cos_operator_vs_mean": { |
| "cos_cls_vs_mean": 0.8784728050231934, |
| "cos_last_vs_mean": 0.8693444728851318, |
| "cos_cls_vs_last": 0.9117629528045654, |
| "note": "cos << 1 => operator carries info distinct from the mean (non-degenerate)." |
| }, |
| "preregistered": { |
| "mean_reproduces_no_binding": "mean-pool cross-construction thematic AUC <= 0.61", |
| "pooling_theorem_if": "CLS or last-token cross-construction thematic AUC > 0.70 => Law 2 is a MEAN-POOLING theorem", |
| "falsifier_if": "ALL operators <= 0.61 => no-binding is an encoder/training property, deeper than pooling" |
| }, |
| "surface_baseline": { |
| "within_each_cv": { |
| "active": { |
| "linear": 1.0, |
| "mlp": 0.836775 |
| }, |
| "ditrans": { |
| "linear": 0.9995499999999999, |
| "mlp": 0.93225 |
| }, |
| "fronted": { |
| "linear": 0.9997250000000001, |
| "mlp": 0.98280625 |
| }, |
| "passive": { |
| "linear": 1.0, |
| "mlp": 0.8163625000000001 |
| }, |
| "relcl": { |
| "linear": 0.9258250000000001, |
| "mlp": 0.9129375 |
| } |
| }, |
| "cross_construction": { |
| "linear": { |
| "passive": 0.0, |
| "relcl": 0.9273250000000001, |
| "ditrans": 0.99914375, |
| "fronted": 0.0, |
| "POOLED_nonactive": 0.480773828125 |
| }, |
| "mlp": { |
| "passive": 0.25751250000000003, |
| "relcl": 0.8426875, |
| "ditrans": 0.8655437500000002, |
| "fronted": 0.10442500000000002, |
| "POOLED_nonactive": 0.4946173828125 |
| } |
| }, |
| "within_active_cv": { |
| "linear": 1.0, |
| "mlp": 0.836775 |
| } |
| }, |
| "operators": { |
| "mean": { |
| "within_active_cv": { |
| "linear": 0.6548375000000001, |
| "mlp": 0.6864000000000001 |
| }, |
| "within_each_cv": { |
| "active": { |
| "linear": 0.6548375000000001, |
| "mlp": 0.6864000000000001 |
| }, |
| "ditrans": { |
| "linear": 0.8711125, |
| "mlp": 0.845525 |
| }, |
| "fronted": { |
| "linear": 0.9804187500000001, |
| "mlp": 0.9753999999999999 |
| }, |
| "passive": { |
| "linear": 0.5893125, |
| "mlp": 0.5954375 |
| }, |
| "relcl": { |
| "linear": 0.8155875, |
| "mlp": 0.8740125 |
| } |
| }, |
| "cross_construction": { |
| "linear": { |
| "passive": 0.458146875, |
| "relcl": 0.5148312500000001, |
| "ditrans": 0.6976812499999999, |
| "fronted": 0.315625, |
| "POOLED_nonactive": 0.500084375 |
| }, |
| "mlp": { |
| "passive": 0.48049375, |
| "relcl": 0.6474999999999999, |
| "ditrans": 0.7178625000000001, |
| "fronted": 0.3933625, |
| "POOLED_nonactive": 0.5506796875 |
| } |
| } |
| }, |
| "cls": { |
| "within_active_cv": { |
| "linear": 0.633928125, |
| "mlp": 0.6506375 |
| }, |
| "within_each_cv": { |
| "active": { |
| "linear": 0.633928125, |
| "mlp": 0.6506375 |
| }, |
| "ditrans": { |
| "linear": 0.8680374999999999, |
| "mlp": 0.83453125 |
| }, |
| "fronted": { |
| "linear": 0.98, |
| "mlp": 0.97469375 |
| }, |
| "passive": { |
| "linear": 0.56188125, |
| "mlp": 0.5670062499999999 |
| }, |
| "relcl": { |
| "linear": 0.8091718749999999, |
| "mlp": 0.8657718750000001 |
| } |
| }, |
| "cross_construction": { |
| "linear": { |
| "passive": 0.47651249999999995, |
| "relcl": 0.53600625, |
| "ditrans": 0.7081468750000001, |
| "fronted": 0.268915625, |
| "POOLED_nonactive": 0.5063806640624999 |
| }, |
| "mlp": { |
| "passive": 0.4758375, |
| "relcl": 0.700725, |
| "ditrans": 0.71361875, |
| "fronted": 0.35950000000000004, |
| "POOLED_nonactive": 0.5515187500000001 |
| } |
| } |
| }, |
| "last": { |
| "within_active_cv": { |
| "linear": 0.64555, |
| "mlp": 0.6686562500000002 |
| }, |
| "within_each_cv": { |
| "active": { |
| "linear": 0.64555, |
| "mlp": 0.6686562500000002 |
| }, |
| "ditrans": { |
| "linear": 0.86766875, |
| "mlp": 0.84595 |
| }, |
| "fronted": { |
| "linear": 0.978665625, |
| "mlp": 0.9749 |
| }, |
| "passive": { |
| "linear": 0.563221875, |
| "mlp": 0.587625 |
| }, |
| "relcl": { |
| "linear": 0.80785625, |
| "mlp": 0.8823656249999999 |
| } |
| }, |
| "cross_construction": { |
| "linear": { |
| "passive": 0.461471875, |
| "relcl": 0.51744375, |
| "ditrans": 0.6858906249999999, |
| "fronted": 0.30709375, |
| "POOLED_nonactive": 0.5020439453125001 |
| }, |
| "mlp": { |
| "passive": 0.4782687499999999, |
| "relcl": 0.73876875, |
| "ditrans": 0.7032749999999999, |
| "fronted": 0.338225, |
| "POOLED_nonactive": 0.559987890625 |
| } |
| } |
| } |
| }, |
| "bonus_cls_trained_encoder": { |
| "within_active_cv": { |
| "linear": 0.682478125, |
| "mlp": 0.6686312499999999 |
| }, |
| "within_each_cv": { |
| "active": { |
| "linear": 0.682478125, |
| "mlp": 0.6686312499999999 |
| }, |
| "ditrans": { |
| "linear": 0.874225, |
| "mlp": 0.8711187499999999 |
| }, |
| "fronted": { |
| "linear": 0.97695, |
| "mlp": 0.9747750000000001 |
| }, |
| "passive": { |
| "linear": 0.566890625, |
| "mlp": 0.57204375 |
| }, |
| "relcl": { |
| "linear": 0.805015625, |
| "mlp": 0.8629 |
| } |
| }, |
| "cross_construction": { |
| "linear": { |
| "passive": 0.4721375, |
| "relcl": 0.6523000000000001, |
| "ditrans": 0.686903125, |
| "fronted": 0.324421875, |
| "POOLED_nonactive": 0.5425126953125 |
| }, |
| "mlp": { |
| "passive": 0.4706375, |
| "relcl": 0.7557375, |
| "ditrans": 0.7462, |
| "fronted": 0.48858124999999997, |
| "POOLED_nonactive": 0.6027312499999999 |
| } |
| }, |
| "cos_cls_vs_self_mean_guard": 0.9725103974342346 |
| }, |
| "scored": { |
| "mean_cross_pooled_best": 0.5506796875, |
| "cls_cross_pooled_best": 0.5515187500000001, |
| "last_cross_pooled_best": 0.559987890625, |
| "bonus_cls_trained_cross_pooled_best": 0.6027312499999999, |
| "surface_cross_pooled_linear": 0.480773828125, |
| "surface_within_active_linear": 1.0, |
| "mean_reproduces_no_binding": true, |
| "nonpooled_binds_pooling_theorem": false, |
| "all_operators_stay_low_encoder_property": true |
| }, |
| "landing": "ENCODER/TRAINING PROPERTY: ALL operators (mean, CLS, last-token, CLS-trained retrieval) stay <= 0.61 cross-construction => no-binding is NOT about pooling. It is a deeper property of sentence-embedding encoders/training. This RESCOPES the theory frame: the mean-pool generative model is a convenient parameterization, but the absence of abstract agent/patient binding is intrinsic to the encoder, not the pooling operator." |
| } |
