mirror of
https://github.com/Imbad0202/academic-research-skills.git
synced 2026-09-14 13:51:17 +08:00
Edward Cheng-I Wu
86bf0e5c2c
Refs #660. Measurement and issue closure follow in the separately preregistered post-main mechanical conformance PR.
219 lines
5.8 KiB
JSON
219 lines
5.8 KiB
JSON
{
|
|
"schema_version": "tortured-phrase-seed-expectations/1.0",
|
|
"snapshot_id": "ars-synthetic-conformance-2026-08-10",
|
|
"snapshot_sha256": "962879909bfdd338047dc4569ff42188c4200fcd56a0a459b0e0f9169f2446c4",
|
|
"label_scope": "mechanical_matcher_conformance_only",
|
|
"empirical_accuracy_claimed": false,
|
|
"contextual_false_positive_labels_provided": false,
|
|
"contextual_false_negative_labels_provided": false,
|
|
"inputs": [
|
|
{
|
|
"path": "own_draft.md",
|
|
"expected_counts": {
|
|
"matched_rule_count": 14,
|
|
"rule_match_count": 15,
|
|
"unique_instance_count": 14
|
|
},
|
|
"expected_matches": [
|
|
{
|
|
"rule_id": "syn_literal_author",
|
|
"count": 1,
|
|
"context": "author_prose"
|
|
},
|
|
{
|
|
"rule_id": "syn_all_segment",
|
|
"count": 1,
|
|
"context": "author_prose"
|
|
},
|
|
{
|
|
"rule_id": "syn_any_segment",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"matched_alternative_index": 0
|
|
},
|
|
{
|
|
"rule_id": "syn_near_ordered",
|
|
"count": 1,
|
|
"context": "author_prose"
|
|
},
|
|
{
|
|
"rule_id": "syn_exclude_segment",
|
|
"count": 1,
|
|
"context": "quote"
|
|
},
|
|
{
|
|
"rule_id": "syn_overlap_long",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"overlap_group": "md-overlap-1"
|
|
},
|
|
{
|
|
"rule_id": "syn_overlap_short",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"overlap_group": "md-overlap-1"
|
|
},
|
|
{
|
|
"rule_id": "syn_nfkc_casefold",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"normalization_case": "nfkc_casefold"
|
|
},
|
|
{
|
|
"rule_id": "syn_dash_same_line",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"normalization_case": "same_line_dash_separator"
|
|
},
|
|
{
|
|
"rule_id": "syn_soft_hyphen",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"normalization_case": "soft_hyphen_join"
|
|
},
|
|
{
|
|
"rule_id": "syn_hyphen_line_break",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"normalization_case": "line_break_hyphen_join"
|
|
},
|
|
{
|
|
"rule_id": "syn_context_quote",
|
|
"count": 1,
|
|
"context": "quote"
|
|
},
|
|
{
|
|
"rule_id": "syn_context_code",
|
|
"count": 2,
|
|
"context": "code_or_verbatim"
|
|
},
|
|
{
|
|
"rule_id": "syn_context_reference",
|
|
"count": 1,
|
|
"context": "reference_entry"
|
|
}
|
|
],
|
|
"expected_suppressions": [
|
|
{
|
|
"rule_id": "syn_exclude_segment",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"reason": "exclude_if_within_token_window"
|
|
}
|
|
],
|
|
"expected_non_matches": [
|
|
{
|
|
"rule_id": "syn_boundary_orb",
|
|
"reason": "token_boundary"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"path": "own_draft.tex",
|
|
"expected_counts": {
|
|
"matched_rule_count": 5,
|
|
"rule_match_count": 5,
|
|
"unique_instance_count": 5
|
|
},
|
|
"expected_matches": [
|
|
{
|
|
"rule_id": "syn_literal_author",
|
|
"count": 1,
|
|
"context": "author_prose"
|
|
},
|
|
{
|
|
"rule_id": "syn_dash_same_line",
|
|
"count": 1,
|
|
"context": "author_prose",
|
|
"normalization_case": "same_line_dash_separator"
|
|
},
|
|
{
|
|
"rule_id": "syn_context_quote",
|
|
"count": 1,
|
|
"context": "quote"
|
|
},
|
|
{
|
|
"rule_id": "syn_context_code",
|
|
"count": 1,
|
|
"context": "code_or_verbatim"
|
|
},
|
|
{
|
|
"rule_id": "syn_context_reference",
|
|
"count": 1,
|
|
"context": "reference_entry"
|
|
}
|
|
],
|
|
"expected_suppressions": [],
|
|
"expected_non_matches": []
|
|
},
|
|
{
|
|
"path": "corpus_input.yaml",
|
|
"records": [
|
|
{
|
|
"citation_key": "fixture_complete_2026",
|
|
"surfaces": {
|
|
"title": {
|
|
"check_status": "checked",
|
|
"reason": "CHECK_COMPLETED",
|
|
"expected_rule_ids": [
|
|
"syn_context_reference"
|
|
]
|
|
},
|
|
"abstract": {
|
|
"check_status": "checked",
|
|
"reason": "CHECK_COMPLETED",
|
|
"expected_rule_ids": [
|
|
"syn_corpus_abstract"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"citation_key": "fixture_missing_2026",
|
|
"surfaces": {
|
|
"title": {
|
|
"check_status": "checked",
|
|
"reason": "CHECK_COMPLETED",
|
|
"expected_rule_ids": [
|
|
"syn_corpus_missing_abstract_title"
|
|
]
|
|
},
|
|
"abstract": {
|
|
"check_status": "not_checked",
|
|
"reason": "ABSTRACT_MISSING",
|
|
"expected_rule_ids": []
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"citation_key": "fixture_negative_2026",
|
|
"surfaces": {
|
|
"title": {
|
|
"check_status": "checked",
|
|
"reason": "CHECK_COMPLETED",
|
|
"expected_rule_ids": [],
|
|
"non_match_reasons": [
|
|
{
|
|
"rule_id": "syn_boundary_orb",
|
|
"reason": "token_boundary"
|
|
}
|
|
]
|
|
},
|
|
"abstract": {
|
|
"check_status": "checked",
|
|
"reason": "CHECK_COMPLETED",
|
|
"expected_rule_ids": [],
|
|
"non_match_reasons": [
|
|
{
|
|
"rule_id": "syn_exclude_segment",
|
|
"reason": "exclude_if_in_same_segment"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|