mixle.reason.cycle_consistency module

Cycle-consistency diagnostics for cross-modal calibration and abstention.

A forward transport’s reported confidence can miss an observation function that maps several latent states to the same observed value. Round-trip closure adds a self-supervised check: draw independent posterior samples of the latent given the observation, project them through the invariant content, and measure self-agreement. Low self-agreement indicates a region where the transport should abstain or escalate even if its marginal confidence is high.

The diagnostic uses NeuralConditionalDensity and build_mdn fitted via mixle.inference.optimize(); it does not add a new transport family.

fit_cycle_transport(given, target, *, k=3, hidden=32, layers=2, max_its=30, m_steps=80, lr=3e-3, seed=0, delta=1.0e-9, reuse_estep_ll=True)[source]

Fit p(target | given) via a mixture density network.

given/target are (n, d) arrays of paired observations. delta/reuse_estep_ll default to optimize()’s own early-stopping; pass delta=None, reuse_estep_ll=False for a harder, more multimodal target.

Parameters:
Return type:

Any

cycle_inconsistency(sampler, given_value, *, n_draws=20, forward=None)[source]

Return disagreement among posterior target samples for one observation.

A well-determined posterior yields draws that agree closely. A collapsed observation region yields draws that disagree, without needing the true target at serving time. If forward is supplied, agreement is checked in observation space rather than raw target space.

Parameters:
Return type:

float

posterior_mean_estimate(sampler, given_value, *, n_draws=20)[source]

Return the posterior-sample mean of the target given given_value.

Parameters:
Return type:

ndarray

joint_cycle_consistency_receipt(joint, source, target, *, backward_joint=None, n_round_trip=300, n_kl_samples=500, seed=0)[source]

Cross-modal generalization (workstream L2) of this module’s round-trip closure signal.

cycle_inconsistency above measures round-trip closure (A -> B -> A) for a NEURAL transport, where the true target is unknown at serving time and self-AGREEMENT among repeated draws is the only available proxy. A CrossModalJoint is a typed grammar object, not an opaque transport: its true marginal p(source) is available in closed form (CrossModalJoint.infer() with no observations), so the round-trip receipt here compares the round-trip estimate DIRECTLY against that true marginal, rather than against itself.

Two ways to arrive at a belief about source through the joint: (1) directly, its own marginal p(source); (2) via a round trip, p(source) -> infer p(target | source) -> infer p(source | target) back, averaged over many draws into one aggregate “round-trip” belief. This receipt is a Monte-Carlo KL-divergence estimate between (2) and (1); a well-specified joint recovers its own marginal on a round trip (the receipt is ~0 up to Monte-Carlo noise), while a deliberately mis-specified backward projection (backward_joint – e.g. a joint whose target-given-regime distributions have been shuffled relative to joint’s, standing in for a broken/incompatible A<-B projection) breaks that identity and the receipt becomes clearly, measurably elevated.

Parameters:

  • joint (CrossModalJoint)

  • source (str)

  • target (str)

  • backward_joint (CrossModalJoint | None)

  • n_round_trip (int)

  • n_kl_samples (int)

  • seed (int)

Return type:

float

selective_error(errors, abstain_scores, keep_frac)[source]

Return mean error on examples kept by the lowest abstention scores.

Lower is better: a useful abstention signal keeps examples the policy can answer and escalates examples with higher expected error.

Parameters:
Return type:

float