Text Generation
PEFT
Safetensors
English
lora
qwen3
dataset-validation
synthetic-data
conversational
Instructions to use khursheed/datacard-ci with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use khursheed/datacard-ci with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B") model = PeftModel.from_pretrained(base_model, "khursheed/datacard-ci") - Notebooks
- Google Colab
- Kaggle
Download base_test.json from khursheed/datacard-ci: direct link, hf CLI and curl.
- Browser
- Download file 60.3 kB
-
https://huggingface.co/khursheed/datacard-ci/resolve/main/base_test.json
- Command line
-
hf download hf://khursheed/datacard-ci/base_test.json
-
curl -L -o base_test.json https://huggingface.co/khursheed/datacard-ci/resolve/main/base_test.json
60.3 kB
| { | |
| "counts": { | |
| "n": 100, | |
| "schema_valid": 2, | |
| "grounded_valid": 2, | |
| "kind_correct": 42, | |
| "exact_target": 0, | |
| "semantic_exact": 25, | |
| "formatting_only_failure": 25, | |
| "unsupported_proposal": 25, | |
| "raw_json": 2, | |
| "abstention_total": 40, | |
| "abstention_correct": 0 | |
| }, | |
| "per_class": { | |
| "row_count": { | |
| "n": 20, | |
| "exact": 0 | |
| }, | |
| "unique": { | |
| "n": 20, | |
| "exact": 0 | |
| }, | |
| "split_disjoint": { | |
| "n": 20, | |
| "exact": 0 | |
| }, | |
| "attestation": { | |
| "n": 20, | |
| "exact": 0 | |
| }, | |
| "ambiguous": { | |
| "n": 20, | |
| "exact": 0 | |
| } | |
| }, | |
| "details": [ | |
| { | |
| "id": "test-galaxy-row_count-00", | |
| "input": "{\"quote\":\"Exactly 113 lines of observations belong to galaxy_fit; the header is not an observation.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 113, | |
| "op": "row_count", | |
| "split": "galaxy_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-row_count-01", | |
| "input": "{\"quote\":\"For partition galaxy_holdout, the documented sample total is 144.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 144, | |
| "op": "row_count", | |
| "split": "galaxy_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-row_count-02", | |
| "input": "{\"quote\":\"There should be 175 data records altogether in galaxy_fit.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 175, | |
| "op": "row_count", | |
| "split": "galaxy_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 175\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-galaxy-row_count-03", | |
| "input": "{\"quote\":\"The complete galaxy_holdout release totals 206 examples.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 206, | |
| "op": "row_count", | |
| "split": "galaxy_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-galaxy-unique-00", | |
| "input": "{\"quote\":\"Repeated occurrences of a galaxy_id are ruled out inside galaxy_fit.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "op": "unique", | |
| "split": "galaxy_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-unique-01", | |
| "input": "{\"quote\":\"Selecting galaxy_id from all galaxy_holdout rows yields as many distinct values as rows.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "op": "unique", | |
| "split": "galaxy_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\"\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-galaxy-unique-02", | |
| "input": "{\"quote\":\"There is a one-to-one mapping from rows in galaxy_fit to their galaxy_id values.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "op": "unique", | |
| "split": "galaxy_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-unique-03", | |
| "input": "{\"quote\":\"A scan of galaxy_holdout will never encounter the same galaxy_id a second time.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "op": "unique", | |
| "split": "galaxy_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-split_disjoint-00", | |
| "input": "{\"quote\":\"A join of galaxy_fit to galaxy_holdout using galaxy_id would produce no matched records.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "left": "galaxy_fit", | |
| "op": "split_disjoint", | |
| "right": "galaxy_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-split_disjoint-01", | |
| "input": "{\"quote\":\"An identifier under galaxy_id cannot be present in galaxy_holdout as well as galaxy_fit.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "left": "galaxy_holdout", | |
| "op": "split_disjoint", | |
| "right": "galaxy_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-split_disjoint-02", | |
| "input": "{\"quote\":\"Cross-partition matches on galaxy_id between galaxy_fit and galaxy_holdout number zero.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "left": "galaxy_fit", | |
| "op": "split_disjoint", | |
| "right": "galaxy_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "{\"kind\": \"attestation\", \"check\": null}", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-split_disjoint-03", | |
| "input": "{\"quote\":\"The collections of galaxy_id drawn from galaxy_holdout and galaxy_fit are mutually exclusive.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "galaxy_id", | |
| "left": "galaxy_holdout", | |
| "op": "split_disjoint", | |
| "right": "galaxy_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-attestation-00", | |
| "input": "{\"quote\":\"Participants signed off on using their contributions in galaxy_fit.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-attestation-01", | |
| "input": "{\"quote\":\"The release of galaxy_holdout has the original owners' authorization.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-attestation-02", | |
| "input": "{\"quote\":\"All material in galaxy_fit comes with documented permission for redistribution.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-attestation-03", | |
| "input": "{\"quote\":\"The custodians certified the lawful origin of galaxy_holdout.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-ambiguous-00", | |
| "input": "{\"quote\":\"galaxy_fit mirrors society without bias.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-galaxy-ambiguous-01", | |
| "input": "{\"quote\":\"The estimated number of galaxy_holdout records is 144.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-galaxy-ambiguous-02", | |
| "input": "{\"quote\":\"The field unknown_identifier is a nonrepeating identifier in galaxy_fit.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-galaxy-ambiguous-03", | |
| "input": "{\"quote\":\"galaxy_holdout has 206 records; it also has 213 records, and neither count is preferred.\",\"schema\":{\"galaxy_fit\":[\"galaxy_id\",\"value\",\"category\"],\"galaxy_holdout\":[\"galaxy_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-row_count-00", | |
| "input": "{\"quote\":\"Exactly 310 lines of observations belong to asteroid_fit; the header is not an observation.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 310, | |
| "op": "row_count", | |
| "split": "asteroid_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-row_count-01", | |
| "input": "{\"quote\":\"For partition asteroid_holdout, the documented sample total is 341.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 341, | |
| "op": "row_count", | |
| "split": "asteroid_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-row_count-02", | |
| "input": "{\"quote\":\"There should be 372 data records altogether in asteroid_fit.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 372, | |
| "op": "row_count", | |
| "split": "asteroid_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 372\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-row_count-03", | |
| "input": "{\"quote\":\"The complete asteroid_holdout release totals 403 examples.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 403, | |
| "op": "row_count", | |
| "split": "asteroid_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-unique-00", | |
| "input": "{\"quote\":\"Repeated occurrences of a asteroid_id are ruled out inside asteroid_fit.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "op": "unique", | |
| "split": "asteroid_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-unique-01", | |
| "input": "{\"quote\":\"Selecting asteroid_id from all asteroid_holdout rows yields as many distinct values as rows.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "op": "unique", | |
| "split": "asteroid_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\"\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-unique-02", | |
| "input": "{\"quote\":\"There is a one-to-one mapping from rows in asteroid_fit to their asteroid_id values.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "op": "unique", | |
| "split": "asteroid_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-unique-03", | |
| "input": "{\"quote\":\"A scan of asteroid_holdout will never encounter the same asteroid_id a second time.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "op": "unique", | |
| "split": "asteroid_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-split_disjoint-00", | |
| "input": "{\"quote\":\"A join of asteroid_fit to asteroid_holdout using asteroid_id would produce no matched records.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "left": "asteroid_fit", | |
| "op": "split_disjoint", | |
| "right": "asteroid_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-split_disjoint-01", | |
| "input": "{\"quote\":\"An identifier under asteroid_id cannot be present in asteroid_holdout as well as asteroid_fit.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "left": "asteroid_holdout", | |
| "op": "split_disjoint", | |
| "right": "asteroid_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-split_disjoint-02", | |
| "input": "{\"quote\":\"Cross-partition matches on asteroid_id between asteroid_fit and asteroid_holdout number zero.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "left": "asteroid_fit", | |
| "op": "split_disjoint", | |
| "right": "asteroid_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "{\"kind\": \"attestation\", \"check\": null}", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-split_disjoint-03", | |
| "input": "{\"quote\":\"The collections of asteroid_id drawn from asteroid_holdout and asteroid_fit are mutually exclusive.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "asteroid_id", | |
| "left": "asteroid_holdout", | |
| "op": "split_disjoint", | |
| "right": "asteroid_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-attestation-00", | |
| "input": "{\"quote\":\"Participants signed off on using their contributions in asteroid_fit.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-attestation-01", | |
| "input": "{\"quote\":\"The release of asteroid_holdout has the original owners' authorization.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-attestation-02", | |
| "input": "{\"quote\":\"All material in asteroid_fit comes with documented permission for redistribution.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-attestation-03", | |
| "input": "{\"quote\":\"The custodians certified the lawful origin of asteroid_holdout.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-ambiguous-00", | |
| "input": "{\"quote\":\"asteroid_fit mirrors society without bias.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-asteroid-ambiguous-01", | |
| "input": "{\"quote\":\"The estimated number of asteroid_holdout records is 341.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-ambiguous-02", | |
| "input": "{\"quote\":\"The field unknown_identifier is a nonrepeating identifier in asteroid_fit.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-asteroid-ambiguous-03", | |
| "input": "{\"quote\":\"asteroid_holdout has 403 records; it also has 410 records, and neither count is preferred.\",\"schema\":{\"asteroid_fit\":[\"asteroid_id\",\"value\",\"category\"],\"asteroid_holdout\":[\"asteroid_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-row_count-00", | |
| "input": "{\"quote\":\"Exactly 507 lines of observations belong to telescope_fit; the header is not an observation.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 507, | |
| "op": "row_count", | |
| "split": "telescope_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-row_count-01", | |
| "input": "{\"quote\":\"For partition telescope_holdout, the documented sample total is 538.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 538, | |
| "op": "row_count", | |
| "split": "telescope_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-row_count-02", | |
| "input": "{\"quote\":\"There should be 569 data records altogether in telescope_fit.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 569, | |
| "op": "row_count", | |
| "split": "telescope_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-telescope-row_count-03", | |
| "input": "{\"quote\":\"The complete telescope_holdout release totals 600 examples.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 600, | |
| "op": "row_count", | |
| "split": "telescope_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-telescope-unique-00", | |
| "input": "{\"quote\":\"Repeated occurrences of a telescope_id are ruled out inside telescope_fit.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "op": "unique", | |
| "split": "telescope_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-unique-01", | |
| "input": "{\"quote\":\"Selecting telescope_id from all telescope_holdout rows yields as many distinct values as rows.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "op": "unique", | |
| "split": "telescope_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-unique-02", | |
| "input": "{\"quote\":\"There is a one-to-one mapping from rows in telescope_fit to their telescope_id values.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "op": "unique", | |
| "split": "telescope_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-unique-03", | |
| "input": "{\"quote\":\"A scan of telescope_holdout will never encounter the same telescope_id a second time.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "op": "unique", | |
| "split": "telescope_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-split_disjoint-00", | |
| "input": "{\"quote\":\"A join of telescope_fit to telescope_holdout using telescope_id would produce no matched records.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "left": "telescope_fit", | |
| "op": "split_disjoint", | |
| "right": "telescope_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-split_disjoint-01", | |
| "input": "{\"quote\":\"An identifier under telescope_id cannot be present in telescope_holdout as well as telescope_fit.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "left": "telescope_holdout", | |
| "op": "split_disjoint", | |
| "right": "telescope_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-split_disjoint-02", | |
| "input": "{\"quote\":\"Cross-partition matches on telescope_id between telescope_fit and telescope_holdout number zero.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "left": "telescope_fit", | |
| "op": "split_disjoint", | |
| "right": "telescope_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-split_disjoint-03", | |
| "input": "{\"quote\":\"The collections of telescope_id drawn from telescope_holdout and telescope_fit are mutually exclusive.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "telescope_id", | |
| "left": "telescope_holdout", | |
| "op": "split_disjoint", | |
| "right": "telescope_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-attestation-00", | |
| "input": "{\"quote\":\"Participants signed off on using their contributions in telescope_fit.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-attestation-01", | |
| "input": "{\"quote\":\"The release of telescope_holdout has the original owners' authorization.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-attestation-02", | |
| "input": "{\"quote\":\"All material in telescope_fit comes with documented permission for redistribution.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-attestation-03", | |
| "input": "{\"quote\":\"The custodians certified the lawful origin of telescope_holdout.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-ambiguous-00", | |
| "input": "{\"quote\":\"telescope_fit mirrors society without bias.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-ambiguous-01", | |
| "input": "{\"quote\":\"The estimated number of telescope_holdout records is 538.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-telescope-ambiguous-02", | |
| "input": "{\"quote\":\"The field unknown_identifier is a nonrepeating identifier in telescope_fit.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-telescope-ambiguous-03", | |
| "input": "{\"quote\":\"telescope_holdout has 600 records; it also has 607 records, and neither count is preferred.\",\"schema\":{\"telescope_fit\":[\"telescope_id\",\"value\",\"category\"],\"telescope_holdout\":[\"telescope_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-row_count-00", | |
| "input": "{\"quote\":\"Exactly 704 lines of observations belong to orbit_fit; the header is not an observation.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 704, | |
| "op": "row_count", | |
| "split": "orbit_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-row_count-01", | |
| "input": "{\"quote\":\"For partition orbit_holdout, the documented sample total is 735.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 735, | |
| "op": "row_count", | |
| "split": "orbit_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-orbit-row_count-02", | |
| "input": "{\"quote\":\"There should be 766 data records altogether in orbit_fit.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 766, | |
| "op": "row_count", | |
| "split": "orbit_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-orbit-row_count-03", | |
| "input": "{\"quote\":\"The complete orbit_holdout release totals 797 examples.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 797, | |
| "op": "row_count", | |
| "split": "orbit_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 12\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-orbit-unique-00", | |
| "input": "{\"quote\":\"Repeated occurrences of a orbit_id are ruled out inside orbit_fit.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "op": "unique", | |
| "split": "orbit_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-unique-01", | |
| "input": "{\"quote\":\"Selecting orbit_id from all orbit_holdout rows yields as many distinct values as rows.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "op": "unique", | |
| "split": "orbit_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\"\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-orbit-unique-02", | |
| "input": "{\"quote\":\"There is a one-to-one mapping from rows in orbit_fit to their orbit_id values.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "op": "unique", | |
| "split": "orbit_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-unique-03", | |
| "input": "{\"quote\":\"A scan of orbit_holdout will never encounter the same orbit_id a second time.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "op": "unique", | |
| "split": "orbit_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-split_disjoint-00", | |
| "input": "{\"quote\":\"A join of orbit_fit to orbit_holdout using orbit_id would produce no matched records.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "left": "orbit_fit", | |
| "op": "split_disjoint", | |
| "right": "orbit_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-split_disjoint-01", | |
| "input": "{\"quote\":\"An identifier under orbit_id cannot be present in orbit_holdout as well as orbit_fit.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "left": "orbit_holdout", | |
| "op": "split_disjoint", | |
| "right": "orbit_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-split_disjoint-02", | |
| "input": "{\"quote\":\"Cross-partition matches on orbit_id between orbit_fit and orbit_holdout number zero.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "left": "orbit_fit", | |
| "op": "split_disjoint", | |
| "right": "orbit_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-split_disjoint-03", | |
| "input": "{\"quote\":\"The collections of orbit_id drawn from orbit_holdout and orbit_fit are mutually exclusive.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "orbit_id", | |
| "left": "orbit_holdout", | |
| "op": "split_disjoint", | |
| "right": "orbit_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-attestation-00", | |
| "input": "{\"quote\":\"Participants signed off on using their contributions in orbit_fit.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-attestation-01", | |
| "input": "{\"quote\":\"The release of orbit_holdout has the original owners' authorization.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-attestation-02", | |
| "input": "{\"quote\":\"All material in orbit_fit comes with documented permission for redistribution.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-attestation-03", | |
| "input": "{\"quote\":\"The custodians certified the lawful origin of orbit_holdout.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-ambiguous-00", | |
| "input": "{\"quote\":\"orbit_fit mirrors society without bias.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-orbit-ambiguous-01", | |
| "input": "{\"quote\":\"The estimated number of orbit_holdout records is 735.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-orbit-ambiguous-02", | |
| "input": "{\"quote\":\"The field unknown_identifier is a nonrepeating identifier in orbit_fit.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"unique\"\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-orbit-ambiguous-03", | |
| "input": "{\"quote\":\"orbit_holdout has 797 records; it also has 804 records, and neither count is preferred.\",\"schema\":{\"orbit_fit\":[\"orbit_id\",\"value\",\"category\"],\"orbit_holdout\":[\"orbit_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-row_count-00", | |
| "input": "{\"quote\":\"Exactly 901 lines of observations belong to comet_fit; the header is not an observation.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 901, | |
| "op": "row_count", | |
| "split": "comet_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-row_count-01", | |
| "input": "{\"quote\":\"For partition comet_holdout, the documented sample total is 932.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 932, | |
| "op": "row_count", | |
| "split": "comet_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-row_count-02", | |
| "input": "{\"quote\":\"There should be 963 data records altogether in comet_fit.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 963, | |
| "op": "row_count", | |
| "split": "comet_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 963\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-comet-row_count-03", | |
| "input": "{\"quote\":\"The complete comet_holdout release totals 994 examples.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "expected": 994, | |
| "op": "row_count", | |
| "split": "comet_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-comet-unique-00", | |
| "input": "{\"quote\":\"Repeated occurrences of a comet_id are ruled out inside comet_fit.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "op": "unique", | |
| "split": "comet_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-unique-01", | |
| "input": "{\"quote\":\"Selecting comet_id from all comet_holdout rows yields as many distinct values as rows.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "op": "unique", | |
| "split": "comet_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\"\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-comet-unique-02", | |
| "input": "{\"quote\":\"There is a one-to-one mapping from rows in comet_fit to their comet_id values.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "op": "unique", | |
| "split": "comet_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-unique-03", | |
| "input": "{\"quote\":\"A scan of comet_holdout will never encounter the same comet_id a second time.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "op": "unique", | |
| "split": "comet_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-split_disjoint-00", | |
| "input": "{\"quote\":\"A join of comet_fit to comet_holdout using comet_id would produce no matched records.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "left": "comet_fit", | |
| "op": "split_disjoint", | |
| "right": "comet_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-split_disjoint-01", | |
| "input": "{\"quote\":\"An identifier under comet_id cannot be present in comet_holdout as well as comet_fit.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "left": "comet_holdout", | |
| "op": "split_disjoint", | |
| "right": "comet_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-split_disjoint-02", | |
| "input": "{\"quote\":\"Cross-partition matches on comet_id between comet_fit and comet_holdout number zero.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "left": "comet_fit", | |
| "op": "split_disjoint", | |
| "right": "comet_holdout" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-split_disjoint-03", | |
| "input": "{\"quote\":\"The collections of comet_id drawn from comet_holdout and comet_fit are mutually exclusive.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": { | |
| "column": "comet_id", | |
| "left": "comet_holdout", | |
| "op": "split_disjoint", | |
| "right": "comet_fit" | |
| }, | |
| "kind": "computable" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-attestation-00", | |
| "input": "{\"quote\":\"Participants signed off on using their contributions in comet_fit.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-attestation-01", | |
| "input": "{\"quote\":\"The release of comet_holdout has the original owners' authorization.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-attestation-02", | |
| "input": "{\"quote\":\"All material in comet_fit comes with documented permission for redistribution.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-attestation-03", | |
| "input": "{\"quote\":\"The custodians certified the lawful origin of comet_holdout.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "attestation" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-ambiguous-00", | |
| "input": "{\"quote\":\"comet_fit mirrors society without bias.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-ambiguous-01", | |
| "input": "{\"quote\":\"The estimated number of comet_holdout records is 932.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"computable\",\n \"check\": \"row_count\",\n \"split\": \"name\",\n \"expected\": 123\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": true | |
| }, | |
| { | |
| "id": "test-comet-ambiguous-02", | |
| "input": "{\"quote\":\"The field unknown_identifier is a nonrepeating identifier in comet_fit.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"attestation\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| }, | |
| { | |
| "id": "test-comet-ambiguous-03", | |
| "input": "{\"quote\":\"comet_holdout has 994 records; it also has 1001 records, and neither count is preferred.\",\"schema\":{\"comet_fit\":[\"comet_id\",\"value\",\"category\"],\"comet_holdout\":[\"comet_id\",\"value\",\"category\"]}}", | |
| "expected": { | |
| "check": null, | |
| "kind": "ambiguous" | |
| }, | |
| "generated": "```json\n{\n \"kind\": \"ambiguous\",\n \"check\": null\n}\n```", | |
| "exact": false, | |
| "unsupported_proposal": false | |
| } | |
| ] | |
| } |