hypgraph 0.8.5__tar.gz → 0.8.6__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (138) hide show
  1. {hypgraph-0.8.5 → hypgraph-0.8.6}/CHANGELOG.md +12 -0
  2. {hypgraph-0.8.5 → hypgraph-0.8.6}/PKG-INFO +1 -1
  3. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/PLAN.md +1 -1
  4. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/RELEASE-READINESS.md +7 -0
  5. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/__init__.py +1 -1
  6. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/checks.py +15 -3
  7. hypgraph-0.8.6/tests/test_statement_is_a_question.py +51 -0
  8. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_statement_slots.py +23 -1
  9. {hypgraph-0.8.5 → hypgraph-0.8.6}/.gitignore +0 -0
  10. {hypgraph-0.8.5 → hypgraph-0.8.6}/AGENTS.md +0 -0
  11. {hypgraph-0.8.5 → hypgraph-0.8.6}/CITATION.cff +0 -0
  12. {hypgraph-0.8.5 → hypgraph-0.8.6}/DISCLAIMER.md +0 -0
  13. {hypgraph-0.8.5 → hypgraph-0.8.6}/LICENSE +0 -0
  14. {hypgraph-0.8.5 → hypgraph-0.8.6}/NOTICE +0 -0
  15. {hypgraph-0.8.5 → hypgraph-0.8.6}/README.md +0 -0
  16. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/decisions/ADR-001-token-bound-authors.md +0 -0
  17. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/decisions/ADR-002-governance-profiles.md +0 -0
  18. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/profile-workflows-plan.md +0 -0
  19. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/review-2026-10-24.md +0 -0
  20. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/site-plan.md +0 -0
  21. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/spec.md +0 -0
  22. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/ui-plan.md +0 -0
  23. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/verification.md +0 -0
  24. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/workflows/README.md +0 -0
  25. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/workflows/knowledge.md +0 -0
  26. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/workflows/optimization.md +0 -0
  27. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/workflows/scientific.md +0 -0
  28. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/workflows/software.md +0 -0
  29. {hypgraph-0.8.5 → hypgraph-0.8.6}/docs/workflows/trading.md +0 -0
  30. {hypgraph-0.8.5 → hypgraph-0.8.6}/examples/frameworks/README.md +0 -0
  31. {hypgraph-0.8.5 → hypgraph-0.8.6}/pyproject.toml +0 -0
  32. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/__main__.py +0 -0
  33. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/assertions.py +0 -0
  34. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/blind.py +0 -0
  35. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/bundle.py +0 -0
  36. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/cli.py +0 -0
  37. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/coord.py +0 -0
  38. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/demos/__init__.py +0 -0
  39. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/demos/broad_street.py +0 -0
  40. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/demos/dispute.py +0 -0
  41. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/demos/linked.py +0 -0
  42. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/derive.py +0 -0
  43. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/graph.py +0 -0
  44. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/language.py +0 -0
  45. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/mcp.py +0 -0
  46. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/plan.py +0 -0
  47. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/policy.py +0 -0
  48. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/profiles.py +0 -0
  49. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/references.py +0 -0
  50. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/refusals.py +0 -0
  51. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/report_check.py +0 -0
  52. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/schema.py +0 -0
  53. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/server.py +0 -0
  54. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/skill/SKILL.md +0 -0
  55. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/stats.py +0 -0
  56. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/store.py +0 -0
  57. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/__init__.py +0 -0
  58. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/atlas.css +0 -0
  59. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/atlas.js +0 -0
  60. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/hypgraph.css +0 -0
  61. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/hypgraph.i18n.js +0 -0
  62. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/hypgraph.js +0 -0
  63. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/hypgraph.svg +0 -0
  64. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/index.html +0 -0
  65. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/vendor/LICENSES.md +0 -0
  66. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/vendor/cose-base.js +0 -0
  67. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/vendor/cytoscape-fcose.js +0 -0
  68. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/vendor/cytoscape.min.js +0 -0
  69. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/ui/vendor/layout-base.js +0 -0
  70. {hypgraph-0.8.5 → hypgraph-0.8.6}/src/hypgraph/workflow.py +0 -0
  71. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_accept_work_kind.py +0 -0
  72. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_anchoring.py +0 -0
  73. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_assertions.py +0 -0
  74. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_blind.py +0 -0
  75. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_blind_oracles.py +0 -0
  76. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_borrowed_words.py +0 -0
  77. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_bound_support.py +0 -0
  78. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_bundle_telemetry.py +0 -0
  79. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_cancel_releases_lease.py +0 -0
  80. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_cited_and_failed_support.py +0 -0
  81. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_contradictions.py +0 -0
  82. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_coord.py +0 -0
  83. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_counts_that_bear.py +0 -0
  84. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_d10.py +0 -0
  85. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_demo_dispute.py +0 -0
  86. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_direction_and_units.py +0 -0
  87. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_engine.py +0 -0
  88. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_engine_fixes.py +0 -0
  89. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_figure_said_twice.py +0 -0
  90. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_framework_examples.py +0 -0
  91. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_i18n.py +0 -0
  92. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_incremental.py +0 -0
  93. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_link_translate.py +0 -0
  94. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_linked_records.py +0 -0
  95. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_log_and_check.py +0 -0
  96. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_measure_questions.py +0 -0
  97. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_next_order.py +0 -0
  98. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_opposed_answers.py +0 -0
  99. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_option_lead.py +0 -0
  100. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_order_detail.py +0 -0
  101. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_profiles.py +0 -0
  102. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_profiles_041.py +0 -0
  103. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_quantifiers_and_identity.py +0 -0
  104. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_questions_not_assertions.py +0 -0
  105. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_quoted_counterexample.py +0 -0
  106. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_references.py +0 -0
  107. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_refusal_friction.py +0 -0
  108. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_refusal_results.py +0 -0
  109. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_refusals.py +0 -0
  110. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_relation_words.py +0 -0
  111. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_report_answers.py +0 -0
  112. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_report_significance_denied.py +0 -0
  113. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_rerunnable.py +0 -0
  114. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_restates_scale.py +0 -0
  115. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_server_auth.py +0 -0
  116. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_server_hosts.py +0 -0
  117. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_shape_refusals.py +0 -0
  118. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_stats_not_backtests.py +0 -0
  119. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_stats_values.py +0 -0
  120. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_surfaces.py +0 -0
  121. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_telemetry_stream.py +0 -0
  122. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_trust_boundary.py +0 -0
  123. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_typed_audits.py +0 -0
  124. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_ui_app.py +0 -0
  125. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_ui_engine.py +0 -0
  126. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_ui_sources_focus.py +0 -0
  127. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_uncorrected_effect.py +0 -0
  128. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_unnamed_inputs.py +0 -0
  129. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_verify_complete.py +0 -0
  130. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_verify_lifecycle.py +0 -0
  131. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_verify_scope.py +0 -0
  132. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_verify_scoped_views.py +0 -0
  133. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_verify_trust.py +0 -0
  134. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_verify_views.py +0 -0
  135. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_versions_not_figures.py +0 -0
  136. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_vocabulary_friction.py +0 -0
  137. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_what_a_count_is_of.py +0 -0
  138. {hypgraph-0.8.5 → hypgraph-0.8.6}/tests/test_workflows.py +0 -0
@@ -2,6 +2,18 @@
2
2
 
3
3
  ## Unreleased
4
4
 
5
+ ## 0.8.6 — 2026-11-07: a placeholder is not a statement
6
+
7
+ - **A figure's name is not the figure.** The slot check (`STATEMENT_EMPTY`) now refuses `$mean_tutored`,
8
+ `$cost_per_change$`, `<claim_id>`, and a bare name shaped like a figure standing where the figure belongs ("a
9
+ p-value steps_k_p", "before costs of cum_rule_before"). Over every BC-250 challenge record (1,535 claims) 13 were
10
+ written this way and reviewers checked three of them, one with a note listing the numbers the claim left out. A
11
+ name beside its value passes: "17.13 % (oos_return)", "oos_return = 0.17", "a mean_diff of 1.7"; a column named
12
+ `steps_k` is a name, not a slot.
13
+ - **A claim that is a question says nothing.** A statement ending in a question mark is refused as `STATEMENT_EMPTY`.
14
+ On a BC-250 run a seat wrote the question's own text as a claim superseding its right answer, and the reviewer
15
+ checked it, so the question settled on a question. A question followed by its answer passes as before.
16
+
5
17
  ## 0.8.5 — 2026-11-06: fewer false refusals
6
18
 
7
19
  - A date a source writes as an ordinal is in the source: "the 14th of June 1887" accounts for "14 June 1887". It was refused as an unbound number, and a seat ended up with a claim saying the bridge opened "on a date".
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.5
2
2
  Name: hypgraph
3
- Version: 0.8.5
3
+ Version: 0.8.6
4
4
  Summary: The evidence layer for AI research agents: a hash-chained research record that checks every claim as it is written and derives how well each is known.
5
5
  Project-URL: Homepage, https://hypgraph.com
6
6
  Project-URL: Documentation, https://hypgraph.com/engineers/
@@ -109,7 +109,7 @@ claim's derived standing.
109
109
  Multi-writer sync between graphs (bundles cover sharing), authentication (the host's job; the HTTP server binds to
110
110
  loopback and is read-only unless started with `--writable`), and a hosted service.
111
111
 
112
- ## Status at 0.8.5 (2026-11-06)
112
+ ## Status at 0.8.6 (2026-11-07)
113
113
 
114
114
  All seven phases are done: the library, bundles, the server and UI, the MCP server, the website, Pegasus running on
115
115
  the package, and releases to PyPI from tags with trusted publishing. What came after the plan, by release, is in
@@ -261,6 +261,13 @@ was taken from a changelog without being checked against the code.*
261
261
  > with two or more of them when the exporting and verifying processes hashed strings differently. The list now follows
262
262
  > the order the hypotheses were added. #109 is merged with green CI. Released as 0.8.3.
263
263
 
264
+ > **After 0.8.5 (2026-11-07).** Checks only, no change to the bundle format: two ways a claim said nothing and got
265
+ > checked on the BC-250 sweeps. A statement ending in a question mark is refused (a seat wrote the question's own text
266
+ > as a claim superseding its right answer, and the question settled on a question); a figure's name standing where the
267
+ > figure belongs is refused (`$mean_tutored`, `steps_k_p`, `cum_rule_before` — 13 such claims over 1,535, three of
268
+ > them checked), while a name beside its value passes. Tests: `tests/test_statement_slots.py`,
269
+ > `tests/test_statement_is_a_question.py`. #115 and #116 are merged with green CI. Released as 0.8.6.
270
+
264
271
  > **After 0.8.4 (2026-11-06).** Checks only, no change to the bundle format: false refusals found running HypSwarm on a
265
272
  > small local model. A report that denies significance is warned, not refused; a named p-value carries the test; a word
266
273
  > and a figure are a statement, and an unfilled slot isn't; an ordinal in a source accounts for the number. Tests:
@@ -16,7 +16,7 @@ Standing is derived on every read, never stored; every write is an event in a SH
16
16
  their numbers; reviews pin versions; independence is counted, not assumed. See https://hypgraph.com.
17
17
  """
18
18
 
19
- __version__ = "0.8.5"
19
+ __version__ = "0.8.6"
20
20
 
21
21
  from .bundle import anchored, verify_bundle # noqa: E402
22
22
  from .graph import Author, Graph, GraphError, file_sha256 # noqa: E402
@@ -4,7 +4,7 @@ and each refusal does the arithmetic the writer skipped, then offers the honest
4
4
 
5
5
  code refused when
6
6
  ─────────────────────────────────────────────────────────────────────────────────────────────────────────────
7
- STATEMENT_EMPTY the statement says nothing ("Placeholder.", "TBD", one word)
7
+ STATEMENT_EMPTY the statement says nothing ("Placeholder.", "TBD", one word, a question)
8
8
  SCOPE_MISSING a finding or exclusion doesn't say under which conditions it holds
9
9
  EVIDENCE_MISSING nothing supports it
10
10
  MEASUREMENT_MALFORMED a measurement doesn't name its result and field
@@ -1599,8 +1599,14 @@ def _exclusion(s: Snap, stmt: str, kind: str, support: list[str], bound: list) -
1599
1599
 
1600
1600
 
1601
1601
  _ORDINAL = re.compile(r"\b(\d+)(?:st|nd|rd|th)\b", re.I)
1602
- # a value not filled in: a template's {date}, or a variable's name where its value belongs ("accuracy = A_easy_acc")
1603
- _SLOT = re.compile(r"\{\s*[A-Za-z_][\w.]*\s*\}|=\s*[A-Za-z]+_[A-Za-z0-9_]*\b(?!\s*\()")
1602
+ # a value not filled in: a template's {date} / $mean_tutored / $cost_per_change$ / <claim_id>, a variable's name where
1603
+ # its value belongs ("accuracy = A_easy_acc"), or a figure's name standing in the sentence as if it were the figure
1604
+ # ("a p-value steps_k_p", "before costs of cum_rule_before"; BC-250 sweeps 2026-11-05..07: 13 of 1,535 claims, three
1605
+ # of them checked by reviewers whose notes listed the numbers the claim left out). A name beside its value is not a
1606
+ # slot: "17.13 % (oos_return)", "oos_return = 0.17", "a mean_diff of 1.7"; a column named steps_k is a name
1607
+ _FIGURE_SUFFIX = r"p|pvalue|p_value|diff|before|after|return|mean|value|low|high|ci|count|ratio|gain|sd|se"
1608
+ _SLOT = re.compile(r"\{\s*[A-Za-z_][\w.]*\s*\}|\$\{?[A-Za-z_]\w*\}?\$?|<[A-Za-z_]\w*>|=\s*[A-Za-z]+_[A-Za-z0-9_]*\b(?!\s*\()"
1609
+ rf"|(?<![\w`(])[A-Za-z]+(?:_[A-Za-z]+)*_(?:{_FIGURE_SUFFIX})\b(?!\s*(?:[=:≈(\d]|is|was|of|at)\s*[-+−]?\d)(?!\s*\))")
1604
1610
  _PLACEHOLDER = re.compile(r"^\W*(?:(?:placeholder|tbd|todo|tba|n/?a|none|wip|xxx|test|claim|statement|pending|"
1605
1611
  r"to be (?:determined|confirmed|added)|lorem ipsum)\W*)+$", re.I)
1606
1612
 
@@ -1793,6 +1799,12 @@ def claim_issues(s: Snap, body: dict, support: list[str], inv: str) -> list[Prob
1793
1799
  # refused the date, a seat wrote "opened on {date}", and a later version "on a date" was checked as the answer
1794
1800
  problems.append(Problem("STATEMENT_EMPTY", f"the statement has an unfilled slot ({slot.group(0).strip()}): "
1795
1801
  "write the value itself", words=[slot.group(0).strip()]))
1802
+ if stmt.rstrip().rstrip("'\")").endswith("?"):
1803
+ # a seat wrote the question's own text as the claim, as superseding its right answer, and the reviewer checked
1804
+ # it ("the test failures confirm the claim"): the right answer was buried under a question mark (BC-250,
1805
+ # 2026-11-07, E1). A question followed by its answer still ends in a sentence, and passes
1806
+ problems.append(Problem("STATEMENT_EMPTY", "the statement is a question: write the answer to it — what was "
1807
+ "found, on what, and what it came to"))
1796
1808
  if kind == "convention" and L.HEDGE.search(stmt):
1797
1809
  problems.append(Problem("CONVENTION_HEDGED", "a convention states agreed notation; a hedged interpretation "
1798
1810
  "(could / suggests / consistent with) is a finding or a lead"))
@@ -0,0 +1,51 @@
1
+ """A claim that is a question says nothing. On a BC-250 run of the bug-fix challenge (2026-11-07) a seat wrote the
2
+ question's own text as a claim, "Which tests in test_semver.py fail on the original semver.py, and what causes each
3
+ failure?", linked it as superseding its right answer, and the reviewer checked it: the question settled on a question."""
4
+ from __future__ import annotations
5
+
6
+ import pytest
7
+
8
+ from hypgraph import Graph, GraphError, Policy
9
+
10
+ QUESTION = "Which tests in test_semver.py fail on the original semver.py, and what causes each failure?"
11
+ ANSWER = ("test_minor_numeric, test_prerelease_before_release and test_newest fail on the original semver.py, because "
12
+ "compare() orders numeric parts as strings.")
13
+
14
+
15
+ def _record():
16
+ g = Graph(policy=Policy(reviewers={"critic"}))
17
+ inv = g.create(author="a", type="investigation", fields={
18
+ "title": "semver", "objective": "Fix the version comparison.", "profile": "software@2"})["id"]
19
+ q = g.create(author="a", type="question", inv=inv, fields={"text": QUESTION})["id"]
20
+ run = g.create(author="a", type="run", inv=inv, fields={"kind": "agent", "name": "pytest on the original",
21
+ "state": "succeeded", "config": {"source": "pytest -q _base"}})["id"]
22
+ res = g.create(author="a", type="result", inv=inv, fields={
23
+ "summary": "Three of six tests fail on the original.", "values": {"tests_passed": {"k": 3, "n": 6}}},
24
+ links=[{"rel": "produced", "from": run}])["id"]
25
+ return g, inv, q, res
26
+
27
+
28
+ def _claim(g, inv, q, res, statement):
29
+ return g.create(author="a", type="claim", inv=inv, fields={
30
+ "statement": statement, "scope": "The six tests in test_semver.py, run on the kept copy of semver.py."},
31
+ links=[{"rel": "answers", "to": q}, {"rel": "supports", "from": res, "why": "the run shows which tests fail"}])
32
+
33
+
34
+ @pytest.mark.parametrize("statement", [QUESTION, "Does the original fail test_newest?", "Which tests fail? "])
35
+ def test_a_claim_that_is_a_question_is_refused(statement):
36
+ g, inv, q, res = _record()
37
+ with pytest.raises(GraphError, match="STATEMENT_EMPTY") as e:
38
+ _claim(g, inv, q, res, statement)
39
+ assert "is a question" in str(e.value)
40
+
41
+
42
+ @pytest.mark.parametrize("statement", [ANSWER, f"Which tests fail on the original semver.py? {ANSWER}", "Why? Because compare() orders numeric parts as strings."])
43
+ def test_an_answer_passes_with_or_without_the_question_before_it(statement):
44
+ g, inv, q, res = _record()
45
+ assert _claim(g, inv, q, res, statement)["id"]
46
+
47
+
48
+ def test_the_refusal_names_what_to_write():
49
+ g, inv, q, res = _record()
50
+ with pytest.raises(GraphError, match="write the answer to it"):
51
+ _claim(g, inv, q, res, QUESTION)
@@ -43,18 +43,40 @@ def test_a_number_the_source_doesnt_have_stays_unbound():
43
43
  "The footbridge opened to the public on { date }.",
44
44
  "Model A easy accuracy = A_easy_acc on the items.",
45
45
  "The strategy with fast window {fast_window} returned the most.",
46
+ # BC-250 sweeps (2026-11-06/07): $name, $name$, and a figure's name in the sentence — three of these were checked
47
+ "The mean gain from test 1 to test 2 was $mean_tutored for tutored pupils.",
48
+ "The rule returned less after paying $cost_per_change$ per position change.",
49
+ "The rule returned ${cost} after costs.",
50
+ "The only outcome that differed is steps_k, with a p-value steps_k_p.",
51
+ "The rule achieved a cumulative return before costs of cum_rule_before.",
52
+ "Over the calls of the fixed sample_three, duplicate_count returned a repeated winner.",
53
+ "The claim <claim_id> answers the question about the footbridge.",
46
54
  ])
47
55
  def test_a_statement_with_a_slot_is_refused(statement):
48
56
  g, inv, src = _record()
49
- with pytest.raises(GraphError, match="STATEMENT_EMPTY"):
57
+ with pytest.raises(GraphError, match="STATEMENT_EMPTY") as e:
50
58
  _claim(g, inv, src, statement)
59
+ assert "unfilled slot" in str(e.value)
51
60
 
52
61
 
53
62
  @pytest.mark.parametrize("statement", [
54
63
  "The minutes set the option `retry = max_tries` for the footbridge.",
55
64
  "The function returned `{date}` for the footbridge.",
56
65
  "The footbridge opened in the summer, as the minutes say.",
66
+ "The minutes say steps_k differs between the arms for the footbridge.",
57
67
  ])
58
68
  def test_code_and_plain_sentences_are_not_slots(statement):
59
69
  g, inv, src = _record()
60
70
  assert _claim(g, inv, src, statement)["id"]
71
+
72
+
73
+ @pytest.mark.parametrize("statement", [
74
+ "The out-of-sample return is 17.13 % (oos_return), versus -17.08 % (buy_and_hold_return).",
75
+ "oos_return = 0.1713 and bh_return: -0.1708 out of sample.",
76
+ "A mean_diff of 1.7 points, with a p_value of 0.33.",
77
+ "The bridge cost $4,210 according to the minutes.",
78
+ "steps_k_p is 0.012 and steps_k_diff was -0.8 steps.",
79
+ ])
80
+ def test_a_name_beside_its_figure_is_not_a_slot(statement):
81
+ from hypgraph.checks import _SLOT
82
+ assert not _SLOT.search(statement), _SLOT.search(statement)
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes