# Tend public evidence Public materials are curated summaries of committed result records. They are not original native traces, snapshots, execution archives, or an independent rerun. Private local paths and authorization records are omitted. ## Selected native learning comparison This is one selected native result, not a complete account of current research. In a bounded macOS pipe investigation, Tend learned a model of notifications, found a contradiction, and repaired it. That repair helped it choose a useful later observation sooner. Initial construction: 52 paid queries, 148 actions, 3 states. After repair: 86 queries, 362 actions, 4 states (cumulative). The later comparison in comparison.csv counts additional work after common history; it excludes preparation. Every method verifies the same four service jobs. - The source-aware ordinary procedure ties the repaired model. Superiority over the strongest ordinary method is not established. - The comparison measures additional investigation work after common history. It does not show that learning and repair pay for themselves over the complete lifecycle. - Both models achieve 64/64 predictions on the later catalogue. The demonstrated benefit is query selection at this endpoint, not higher prediction accuracy. - The interface, actions, reset contract and task predicates were supplied. Tend did not discover these representations. - The earlier two-versus-six comparison was invalid because its preceding-model control ignored an already paid prefix. The corrected, evidence-aware result is two versus three. - The producer receipt binds the aggregate result, not every individual supporting file. Later audits do not retroactively authenticate the entire producer chain. ## Separate installed recovery result In a tested macOS workflow, Tend retained its learned model and earlier verified result through a forced interruption, then continued the same job. macOS arm64; an owned nonblocking pipe and kqueue; a supplied fixed action plan. Continuation used the same job, executable, clock window and original limits. The interruption was a SIGKILL after a native action and before its journal commit. This demonstrates recovery at the exercised cut. It does not promise recovery at every instruction, after a reboot, under power loss, or after moving a job. It is engineering evidence, separate from the learning comparison. ## Selected research notes ### Generate alternatives from an earned model A Rust research prototype generated four alternatives from a model learned through observation. Each alternative changed one output in that two-state model and retained its parentage. In the authored example, a contrary observation refuted the parent and narrowed two possible target forecasts to one. A separate actual target observation was still required to establish the answer. Direct observation was cheaper: 2 queries and 6 attempted steps versus 3 queries and 8 steps with the diagnostic, for the same supported answer. Donor preparation cost another 10 queries and 22 steps. The mutation rules, output alphabet and question were supplied. The family stayed fixed after generation. This demonstrates model-descendant generation, not autonomous evolution or a proven improvement in later investigations. Research-only prototype; no supported runtime or installed release changed. Fifteen focused checks passed, but the producer retained a failed closeout after a stale excluded-test count. A separate saved-evidence reader checked the named passes and trace without rerunning them; the earlier compile failure remains recorded. Source: docs/bounded-model-variation-result-v1.md, revision a80bcbe3f1a29369983b85970c1f76ab86362857, blob f9c9abfd8fc8c76b57a746f1391c61d0852a047a. ### Different guidance can share the same blind spot In a study of how to allocate investigation time, guidance from past experience and current progress pointed to the same next action. A read-only reconstruction confirmed the agreement at both decisions under review. The nominations agreed before and after the shared affordability filter. A gate that only chooses between those nominees cannot change either action. Agreement also did not certify a good choice: one prior recorded outcome was worse than a competent ordinary procedure. The check reconstructed 27 saved decision views. It made no native calls, fitted no gate, and acquired no new observations. Retained preparation still carried 2,680.504419 recorded seconds of prior cost. This closes that particular two-ranking intervention, not the broader model-population or transfer idea. Earlier disagreements and unsupported current scores remain in the record; they did not establish an actionable difference at this selected boundary. This is a reconstruction of exposed saved evidence by one coordinator, not an independently executed applicability test, prospective learning result or installed acceptance. The broader question remains open: when advice agrees, what permitted observation could test a shared assumption before a useful later action? Source: docs/learning-curve-applicability-premise-result-v1.md, revision 06246f160e8ec8d4966cf0ba27a5fc7ec57c8b59, blob b7c064ab3444324b767bd5a0d7129f5d014bd4ca. ## Selected native source identification Repository jkordish/tend, revision 12255a772a54595200a97969aea63acdb59215f5. Original repository access is not required to read these public summaries. - docs/kqueue-prefix-service-result-v2.md (blob ac3825541f43c88eadcef97c1541ad5c5898eba1) - docs/native-service-session-result-v1.md (blob ad682955ae8435519e159e52e61a5947d0d8f1c8) - research/native-service-release-v1/installed-v2-result.json (blob 8448b699aba9fa78312b1c555f8839b4694994de) - research/native-service-release-v1/completion-audit-v3-result.json (blob 4a6da561505144ee05fd21a51688b0b1cceef7b7) Is Tend an LLM? No. Tend’s current predictive core learns explicit models from structured actions and observed outcomes, without pretrained language-model weights. Predictions guide tests; actual observations support answers. Models and evidence remain inspectable and reusable. Today, people still supply the interfaces and task boundaries. Core-description source: README.md, blob aaebe20fa3a26586c0e9b20a88cb4b4864964287. ## Research direction We’re exploring whether learned models of systems—little worlds of how things work—can become a useful collection: alternatives Tend can test, connect and draw on during later investigations. A longer-term ambition is for Tend to learn to understand and communicate about those worlds through experience. Connected world models, learned language and general self-improvement are research ambitions, not established capabilities. No scientific experiment or release qualification was rerun for this website update.