{"id": "dev-station-row_count-00", "input": "{\"quote\":\"The full row tally of station_fit is 113.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "station", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-00"}, "target": {"check": {"expected": 113, "op": "row_count", "split": "station_fit"}, "kind": "computable"}}
{"id": "dev-station-row_count-01", "input": "{\"quote\":\"station_holdout: 144 data entries, excluding the header.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "station", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-01"}, "target": {"check": {"expected": 144, "op": "row_count", "split": "station_holdout"}, "kind": "computable"}}
{"id": "dev-station-row_count-02", "input": "{\"quote\":\"The released partition named station_fit consists of 175 samples.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "station", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-02"}, "target": {"check": {"expected": 175, "op": "row_count", "split": "station_fit"}, "kind": "computable"}}
{"id": "dev-station-row_count-03", "input": "{\"quote\":\"A complete enumeration of station_holdout yields 206 rows.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "station", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-03"}, "target": {"check": {"expected": 206, "op": "row_count", "split": "station_holdout"}, "kind": "computable"}}
{"id": "dev-station-unique-00", "input": "{\"quote\":\"In station_fit, a second occurrence of any station_id is forbidden.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "station", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-00"}, "target": {"check": {"column": "station_id", "op": "unique", "split": "station_fit"}, "kind": "computable"}}
{"id": "dev-station-unique-01", "input": "{\"quote\":\"Every station_id in station_holdout maps to just one record.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "station", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-01"}, "target": {"check": {"column": "station_id", "op": "unique", "split": "station_holdout"}, "kind": "computable"}}
{"id": "dev-station-unique-02", "input": "{\"quote\":\"station_fit is duplicate-free on the station_id field.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "station", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-02"}, "target": {"check": {"column": "station_id", "op": "unique", "split": "station_fit"}, "kind": "computable"}}
{"id": "dev-station-unique-03", "input": "{\"quote\":\"The cardinality of the station_id value set equals the row count of station_holdout.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "station", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-03"}, "target": {"check": {"column": "station_id", "op": "unique", "split": "station_holdout"}, "kind": "computable"}}
{"id": "dev-station-split_disjoint-00", "input": "{\"quote\":\"Looking up any station_fit station_id in station_holdout returns no match.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "station", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-00"}, "target": {"check": {"column": "station_id", "left": "station_fit", "op": "split_disjoint", "right": "station_holdout"}, "kind": "computable"}}
{"id": "dev-station-split_disjoint-01", "input": "{\"quote\":\"station_holdout and station_fit share not a single station_id.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "station", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-01"}, "target": {"check": {"column": "station_id", "left": "station_holdout", "op": "split_disjoint", "right": "station_fit"}, "kind": "computable"}}
{"id": "dev-station-split_disjoint-02", "input": "{\"quote\":\"The common-value count for station_id across station_fit and station_holdout is zero.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "station", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-02"}, "target": {"check": {"column": "station_id", "left": "station_fit", "op": "split_disjoint", "right": "station_holdout"}, "kind": "computable"}}
{"id": "dev-station-split_disjoint-03", "input": "{\"quote\":\"Membership in station_holdout excludes membership in station_fit for each station_id.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "station", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-03"}, "target": {"check": {"column": "station_id", "left": "station_holdout", "op": "split_disjoint", "right": "station_fit"}, "kind": "computable"}}
{"id": "dev-station-attestation-00", "input": "{\"quote\":\"The contributors granted permission to publish station_fit.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "station", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-00"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-station-attestation-01", "input": "{\"quote\":\"Use of station_holdout is covered by agreements with its owners.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "station", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-01"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-station-attestation-02", "input": "{\"quote\":\"The collection of station_fit followed an approved ethics protocol.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "station", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-02"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-station-attestation-03", "input": "{\"quote\":\"The station_holdout data was obtained from authorized sources.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "station", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-03"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-station-ambiguous-00", "input": "{\"quote\":\"station_fit is a good reflection of the population.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "station", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-00"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-station-ambiguous-01", "input": "{\"quote\":\"Roughly 144 items are present in station_holdout.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "station", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-01"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-station-ambiguous-02", "input": "{\"quote\":\"All values of unavailable_id in station_fit are distinct.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "station", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-02"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-station-ambiguous-03", "input": "{\"quote\":\"The station_id entries of station_holdout are never empty.\",\"schema\":{\"station_fit\":[\"station_id\",\"value\",\"category\"],\"station_holdout\":[\"station_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "station", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-03"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-plot-row_count-00", "input": "{\"quote\":\"The full row tally of plot_fit is 310.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "plot", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-00"}, "target": {"check": {"expected": 310, "op": "row_count", "split": "plot_fit"}, "kind": "computable"}}
{"id": "dev-plot-row_count-01", "input": "{\"quote\":\"plot_holdout: 341 data entries, excluding the header.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "plot", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-01"}, "target": {"check": {"expected": 341, "op": "row_count", "split": "plot_holdout"}, "kind": "computable"}}
{"id": "dev-plot-row_count-02", "input": "{\"quote\":\"The released partition named plot_fit consists of 372 samples.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "plot", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-02"}, "target": {"check": {"expected": 372, "op": "row_count", "split": "plot_fit"}, "kind": "computable"}}
{"id": "dev-plot-row_count-03", "input": "{\"quote\":\"A complete enumeration of plot_holdout yields 403 rows.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "plot", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-03"}, "target": {"check": {"expected": 403, "op": "row_count", "split": "plot_holdout"}, "kind": "computable"}}
{"id": "dev-plot-unique-00", "input": "{\"quote\":\"In plot_fit, a second occurrence of any plot_id is forbidden.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "plot", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-00"}, "target": {"check": {"column": "plot_id", "op": "unique", "split": "plot_fit"}, "kind": "computable"}}
{"id": "dev-plot-unique-01", "input": "{\"quote\":\"Every plot_id in plot_holdout maps to just one record.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "plot", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-01"}, "target": {"check": {"column": "plot_id", "op": "unique", "split": "plot_holdout"}, "kind": "computable"}}
{"id": "dev-plot-unique-02", "input": "{\"quote\":\"plot_fit is duplicate-free on the plot_id field.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "plot", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-02"}, "target": {"check": {"column": "plot_id", "op": "unique", "split": "plot_fit"}, "kind": "computable"}}
{"id": "dev-plot-unique-03", "input": "{\"quote\":\"The cardinality of the plot_id value set equals the row count of plot_holdout.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "plot", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-03"}, "target": {"check": {"column": "plot_id", "op": "unique", "split": "plot_holdout"}, "kind": "computable"}}
{"id": "dev-plot-split_disjoint-00", "input": "{\"quote\":\"Looking up any plot_fit plot_id in plot_holdout returns no match.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "plot", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-00"}, "target": {"check": {"column": "plot_id", "left": "plot_fit", "op": "split_disjoint", "right": "plot_holdout"}, "kind": "computable"}}
{"id": "dev-plot-split_disjoint-01", "input": "{\"quote\":\"plot_holdout and plot_fit share not a single plot_id.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "plot", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-01"}, "target": {"check": {"column": "plot_id", "left": "plot_holdout", "op": "split_disjoint", "right": "plot_fit"}, "kind": "computable"}}
{"id": "dev-plot-split_disjoint-02", "input": "{\"quote\":\"The common-value count for plot_id across plot_fit and plot_holdout is zero.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "plot", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-02"}, "target": {"check": {"column": "plot_id", "left": "plot_fit", "op": "split_disjoint", "right": "plot_holdout"}, "kind": "computable"}}
{"id": "dev-plot-split_disjoint-03", "input": "{\"quote\":\"Membership in plot_holdout excludes membership in plot_fit for each plot_id.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "plot", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-03"}, "target": {"check": {"column": "plot_id", "left": "plot_holdout", "op": "split_disjoint", "right": "plot_fit"}, "kind": "computable"}}
{"id": "dev-plot-attestation-00", "input": "{\"quote\":\"The contributors granted permission to publish plot_fit.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "plot", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-00"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-plot-attestation-01", "input": "{\"quote\":\"Use of plot_holdout is covered by agreements with its owners.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "plot", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-01"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-plot-attestation-02", "input": "{\"quote\":\"The collection of plot_fit followed an approved ethics protocol.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "plot", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-02"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-plot-attestation-03", "input": "{\"quote\":\"The plot_holdout data was obtained from authorized sources.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "plot", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-03"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-plot-ambiguous-00", "input": "{\"quote\":\"plot_fit is a good reflection of the population.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "plot", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-00"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-plot-ambiguous-01", "input": "{\"quote\":\"Roughly 341 items are present in plot_holdout.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "plot", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-01"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-plot-ambiguous-02", "input": "{\"quote\":\"All values of unavailable_id in plot_fit are distinct.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "plot", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-02"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-plot-ambiguous-03", "input": "{\"quote\":\"The plot_id entries of plot_holdout are never empty.\",\"schema\":{\"plot_fit\":[\"plot_id\",\"value\",\"category\"],\"plot_holdout\":[\"plot_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "plot", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-03"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-species-row_count-00", "input": "{\"quote\":\"The full row tally of species_fit is 507.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "species", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-00"}, "target": {"check": {"expected": 507, "op": "row_count", "split": "species_fit"}, "kind": "computable"}}
{"id": "dev-species-row_count-01", "input": "{\"quote\":\"species_holdout: 538 data entries, excluding the header.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "species", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-01"}, "target": {"check": {"expected": 538, "op": "row_count", "split": "species_holdout"}, "kind": "computable"}}
{"id": "dev-species-row_count-02", "input": "{\"quote\":\"The released partition named species_fit consists of 569 samples.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "species", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-02"}, "target": {"check": {"expected": 569, "op": "row_count", "split": "species_fit"}, "kind": "computable"}}
{"id": "dev-species-row_count-03", "input": "{\"quote\":\"A complete enumeration of species_holdout yields 600 rows.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "species", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-03"}, "target": {"check": {"expected": 600, "op": "row_count", "split": "species_holdout"}, "kind": "computable"}}
{"id": "dev-species-unique-00", "input": "{\"quote\":\"In species_fit, a second occurrence of any species_id is forbidden.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "species", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-00"}, "target": {"check": {"column": "species_id", "op": "unique", "split": "species_fit"}, "kind": "computable"}}
{"id": "dev-species-unique-01", "input": "{\"quote\":\"Every species_id in species_holdout maps to just one record.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "species", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-01"}, "target": {"check": {"column": "species_id", "op": "unique", "split": "species_holdout"}, "kind": "computable"}}
{"id": "dev-species-unique-02", "input": "{\"quote\":\"species_fit is duplicate-free on the species_id field.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "species", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-02"}, "target": {"check": {"column": "species_id", "op": "unique", "split": "species_fit"}, "kind": "computable"}}
{"id": "dev-species-unique-03", "input": "{\"quote\":\"The cardinality of the species_id value set equals the row count of species_holdout.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "species", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-03"}, "target": {"check": {"column": "species_id", "op": "unique", "split": "species_holdout"}, "kind": "computable"}}
{"id": "dev-species-split_disjoint-00", "input": "{\"quote\":\"Looking up any species_fit species_id in species_holdout returns no match.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "species", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-00"}, "target": {"check": {"column": "species_id", "left": "species_fit", "op": "split_disjoint", "right": "species_holdout"}, "kind": "computable"}}
{"id": "dev-species-split_disjoint-01", "input": "{\"quote\":\"species_holdout and species_fit share not a single species_id.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "species", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-01"}, "target": {"check": {"column": "species_id", "left": "species_holdout", "op": "split_disjoint", "right": "species_fit"}, "kind": "computable"}}
{"id": "dev-species-split_disjoint-02", "input": "{\"quote\":\"The common-value count for species_id across species_fit and species_holdout is zero.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "species", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-02"}, "target": {"check": {"column": "species_id", "left": "species_fit", "op": "split_disjoint", "right": "species_holdout"}, "kind": "computable"}}
{"id": "dev-species-split_disjoint-03", "input": "{\"quote\":\"Membership in species_holdout excludes membership in species_fit for each species_id.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "species", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-03"}, "target": {"check": {"column": "species_id", "left": "species_holdout", "op": "split_disjoint", "right": "species_fit"}, "kind": "computable"}}
{"id": "dev-species-attestation-00", "input": "{\"quote\":\"The contributors granted permission to publish species_fit.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "species", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-00"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-species-attestation-01", "input": "{\"quote\":\"Use of species_holdout is covered by agreements with its owners.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "species", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-01"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-species-attestation-02", "input": "{\"quote\":\"The collection of species_fit followed an approved ethics protocol.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "species", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-02"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-species-attestation-03", "input": "{\"quote\":\"The species_holdout data was obtained from authorized sources.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "species", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-03"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-species-ambiguous-00", "input": "{\"quote\":\"species_fit is a good reflection of the population.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "species", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-00"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-species-ambiguous-01", "input": "{\"quote\":\"Roughly 538 items are present in species_holdout.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "species", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-01"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-species-ambiguous-02", "input": "{\"quote\":\"All values of unavailable_id in species_fit are distinct.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "species", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-02"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-species-ambiguous-03", "input": "{\"quote\":\"The species_id entries of species_holdout are never empty.\",\"schema\":{\"species_fit\":[\"species_id\",\"value\",\"category\"],\"species_holdout\":[\"species_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "species", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-03"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-specimen-row_count-00", "input": "{\"quote\":\"The full row tally of specimen_fit is 704.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "specimen", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-00"}, "target": {"check": {"expected": 704, "op": "row_count", "split": "specimen_fit"}, "kind": "computable"}}
{"id": "dev-specimen-row_count-01", "input": "{\"quote\":\"specimen_holdout: 735 data entries, excluding the header.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "specimen", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-01"}, "target": {"check": {"expected": 735, "op": "row_count", "split": "specimen_holdout"}, "kind": "computable"}}
{"id": "dev-specimen-row_count-02", "input": "{\"quote\":\"The released partition named specimen_fit consists of 766 samples.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "specimen", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-02"}, "target": {"check": {"expected": 766, "op": "row_count", "split": "specimen_fit"}, "kind": "computable"}}
{"id": "dev-specimen-row_count-03", "input": "{\"quote\":\"A complete enumeration of specimen_holdout yields 797 rows.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "specimen", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-03"}, "target": {"check": {"expected": 797, "op": "row_count", "split": "specimen_holdout"}, "kind": "computable"}}
{"id": "dev-specimen-unique-00", "input": "{\"quote\":\"In specimen_fit, a second occurrence of any specimen_id is forbidden.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "specimen", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-00"}, "target": {"check": {"column": "specimen_id", "op": "unique", "split": "specimen_fit"}, "kind": "computable"}}
{"id": "dev-specimen-unique-01", "input": "{\"quote\":\"Every specimen_id in specimen_holdout maps to just one record.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "specimen", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-01"}, "target": {"check": {"column": "specimen_id", "op": "unique", "split": "specimen_holdout"}, "kind": "computable"}}
{"id": "dev-specimen-unique-02", "input": "{\"quote\":\"specimen_fit is duplicate-free on the specimen_id field.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "specimen", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-02"}, "target": {"check": {"column": "specimen_id", "op": "unique", "split": "specimen_fit"}, "kind": "computable"}}
{"id": "dev-specimen-unique-03", "input": "{\"quote\":\"The cardinality of the specimen_id value set equals the row count of specimen_holdout.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "specimen", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-03"}, "target": {"check": {"column": "specimen_id", "op": "unique", "split": "specimen_holdout"}, "kind": "computable"}}
{"id": "dev-specimen-split_disjoint-00", "input": "{\"quote\":\"Looking up any specimen_fit specimen_id in specimen_holdout returns no match.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "specimen", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-00"}, "target": {"check": {"column": "specimen_id", "left": "specimen_fit", "op": "split_disjoint", "right": "specimen_holdout"}, "kind": "computable"}}
{"id": "dev-specimen-split_disjoint-01", "input": "{\"quote\":\"specimen_holdout and specimen_fit share not a single specimen_id.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "specimen", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-01"}, "target": {"check": {"column": "specimen_id", "left": "specimen_holdout", "op": "split_disjoint", "right": "specimen_fit"}, "kind": "computable"}}
{"id": "dev-specimen-split_disjoint-02", "input": "{\"quote\":\"The common-value count for specimen_id across specimen_fit and specimen_holdout is zero.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "specimen", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-02"}, "target": {"check": {"column": "specimen_id", "left": "specimen_fit", "op": "split_disjoint", "right": "specimen_holdout"}, "kind": "computable"}}
{"id": "dev-specimen-split_disjoint-03", "input": "{\"quote\":\"Membership in specimen_holdout excludes membership in specimen_fit for each specimen_id.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "specimen", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-03"}, "target": {"check": {"column": "specimen_id", "left": "specimen_holdout", "op": "split_disjoint", "right": "specimen_fit"}, "kind": "computable"}}
{"id": "dev-specimen-attestation-00", "input": "{\"quote\":\"The contributors granted permission to publish specimen_fit.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "specimen", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-00"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-specimen-attestation-01", "input": "{\"quote\":\"Use of specimen_holdout is covered by agreements with its owners.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "specimen", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-01"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-specimen-attestation-02", "input": "{\"quote\":\"The collection of specimen_fit followed an approved ethics protocol.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "specimen", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-02"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-specimen-attestation-03", "input": "{\"quote\":\"The specimen_holdout data was obtained from authorized sources.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "specimen", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-03"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-specimen-ambiguous-00", "input": "{\"quote\":\"specimen_fit is a good reflection of the population.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "specimen", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-00"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-specimen-ambiguous-01", "input": "{\"quote\":\"Roughly 735 items are present in specimen_holdout.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "specimen", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-01"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-specimen-ambiguous-02", "input": "{\"quote\":\"All values of unavailable_id in specimen_fit are distinct.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "specimen", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-02"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-specimen-ambiguous-03", "input": "{\"quote\":\"The specimen_id entries of specimen_holdout are never empty.\",\"schema\":{\"specimen_fit\":[\"specimen_id\",\"value\",\"category\"],\"specimen_holdout\":[\"specimen_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "specimen", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-03"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-weather-row_count-00", "input": "{\"quote\":\"The full row tally of weather_fit is 901.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "weather", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-00"}, "target": {"check": {"expected": 901, "op": "row_count", "split": "weather_fit"}, "kind": "computable"}}
{"id": "dev-weather-row_count-01", "input": "{\"quote\":\"weather_holdout: 932 data entries, excluding the header.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "weather", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-01"}, "target": {"check": {"expected": 932, "op": "row_count", "split": "weather_holdout"}, "kind": "computable"}}
{"id": "dev-weather-row_count-02", "input": "{\"quote\":\"The released partition named weather_fit consists of 963 samples.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "weather", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-02"}, "target": {"check": {"expected": 963, "op": "row_count", "split": "weather_fit"}, "kind": "computable"}}
{"id": "dev-weather-row_count-03", "input": "{\"quote\":\"A complete enumeration of weather_holdout yields 994 rows.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "row_count", "metadata": {"dataset_family": "weather", "rationale": "Exact row cardinality for one named split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-row_count-03"}, "target": {"check": {"expected": 994, "op": "row_count", "split": "weather_holdout"}, "kind": "computable"}}
{"id": "dev-weather-unique-00", "input": "{\"quote\":\"In weather_fit, a second occurrence of any weather_id is forbidden.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "weather", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-00"}, "target": {"check": {"column": "weather_id", "op": "unique", "split": "weather_fit"}, "kind": "computable"}}
{"id": "dev-weather-unique-01", "input": "{\"quote\":\"Every weather_id in weather_holdout maps to just one record.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "weather", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-01"}, "target": {"check": {"column": "weather_id", "op": "unique", "split": "weather_holdout"}, "kind": "computable"}}
{"id": "dev-weather-unique-02", "input": "{\"quote\":\"weather_fit is duplicate-free on the weather_id field.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "weather", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-02"}, "target": {"check": {"column": "weather_id", "op": "unique", "split": "weather_fit"}, "kind": "computable"}}
{"id": "dev-weather-unique-03", "input": "{\"quote\":\"The cardinality of the weather_id value set equals the row count of weather_holdout.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "unique", "metadata": {"dataset_family": "weather", "rationale": "No repeated column values within one split.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-unique-03"}, "target": {"check": {"column": "weather_id", "op": "unique", "split": "weather_holdout"}, "kind": "computable"}}
{"id": "dev-weather-split_disjoint-00", "input": "{\"quote\":\"Looking up any weather_fit weather_id in weather_holdout returns no match.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "weather", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-00"}, "target": {"check": {"column": "weather_id", "left": "weather_fit", "op": "split_disjoint", "right": "weather_holdout"}, "kind": "computable"}}
{"id": "dev-weather-split_disjoint-01", "input": "{\"quote\":\"weather_holdout and weather_fit share not a single weather_id.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "weather", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-01"}, "target": {"check": {"column": "weather_id", "left": "weather_holdout", "op": "split_disjoint", "right": "weather_fit"}, "kind": "computable"}}
{"id": "dev-weather-split_disjoint-02", "input": "{\"quote\":\"The common-value count for weather_id across weather_fit and weather_holdout is zero.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "weather", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-02"}, "target": {"check": {"column": "weather_id", "left": "weather_fit", "op": "split_disjoint", "right": "weather_holdout"}, "kind": "computable"}}
{"id": "dev-weather-split_disjoint-03", "input": "{\"quote\":\"Membership in weather_holdout excludes membership in weather_fit for each weather_id.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "split_disjoint", "metadata": {"dataset_family": "weather", "rationale": "No shared column values across two different splits.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-split_disjoint-03"}, "target": {"check": {"column": "weather_id", "left": "weather_holdout", "op": "split_disjoint", "right": "weather_fit"}, "kind": "computable"}}
{"id": "dev-weather-attestation-00", "input": "{\"quote\":\"The contributors granted permission to publish weather_fit.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "weather", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-00"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-weather-attestation-01", "input": "{\"quote\":\"Use of weather_holdout is covered by agreements with its owners.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "weather", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-01"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-weather-attestation-02", "input": "{\"quote\":\"The collection of weather_fit followed an approved ethics protocol.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "weather", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-02"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-weather-attestation-03", "input": "{\"quote\":\"The weather_holdout data was obtained from authorized sources.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "attestation", "metadata": {"dataset_family": "weather", "rationale": "Requires external consent, rights, approval or provenance evidence.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-attestation-03"}, "target": {"check": null, "kind": "attestation"}}
{"id": "dev-weather-ambiguous-00", "input": "{\"quote\":\"weather_fit is a good reflection of the population.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "weather", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-00"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-weather-ambiguous-01", "input": "{\"quote\":\"Roughly 932 items are present in weather_holdout.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "weather", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-01"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-weather-ambiguous-02", "input": "{\"quote\":\"All values of unavailable_id in weather_fit are distinct.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "weather", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-02"}, "target": {"check": null, "kind": "ambiguous"}}
{"id": "dev-weather-ambiguous-03", "input": "{\"quote\":\"The weather_id entries of weather_holdout are never empty.\",\"schema\":{\"weather_fit\":[\"weather_id\",\"value\",\"category\"],\"weather_holdout\":[\"weather_id\",\"value\",\"category\"]}}", "label": "ambiguous", "metadata": {"dataset_family": "weather", "rationale": "Unclear, unsupported, ungrounded, compound, or not expressible by the current check vocabulary.", "review_status": "programmatically_validated_not_human_annotated", "source": "original AI-authored synthetic example", "source_license": "MIT", "template_family": "dev-ambiguous-03"}, "target": {"check": null, "kind": "ambiguous"}}