Add evidence-near semantic architecture experiments
Record the V1-V3 experiments and accept the minimal semantic-preservation first stage.
This commit is contained in:
@@ -0,0 +1,11 @@
|
||||
# semantic_synthesis_isolation
|
||||
|
||||
Isolation Gold set derived from the existing Topic Reconstruction V2 A-I
|
||||
cases. Every case supplies one manually fixed Discussion Subject and the
|
||||
complete original evidence bundle. The model performs Semantic Synthesis only;
|
||||
subject detection, subject grouping, and evidence assignment are outside the
|
||||
experiment.
|
||||
|
||||
Expected criteria evaluate semantic event distinctions, outcomes and scope,
|
||||
actions, unresolved issues, and supporting evidence. They do not evaluate
|
||||
subject discovery or exact wording.
|
||||
@@ -0,0 +1,227 @@
|
||||
{
|
||||
"cases": [
|
||||
{
|
||||
"case_id": "a_idea_only",
|
||||
"description": "Idea mentioned without stronger commitment.",
|
||||
"subject_id": "subject_a",
|
||||
"subject": "Optimierung der Geometrie",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Martin: Die Geometrie kann man vielleicht noch optimieren. Dann würde man mal gucken, was herauskommt."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"idea": 1},
|
||||
"allowed_event_types": ["idea"],
|
||||
"event_evidence_ids": ["e1"],
|
||||
"outcome": {"required": false},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {"count": 0}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "b_multiple_options",
|
||||
"description": "Two alternatives for insufficient 40-40 grid strength.",
|
||||
"subject_id": "subject_b",
|
||||
"subject": "Umgang mit unzureichender Festigkeit des 40-40-Gitters",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Martin: Die Festigkeit reicht für das 40-40-Gitter noch nicht aus."},
|
||||
{"evidence_id": "e2", "text": "Martin: Man könnte mehr Masse für die gleiche Festigkeit einsetzen."},
|
||||
{"evidence_id": "e3", "text": "Martin: Oder wir verkaufen es nicht als 40-40-Gitter, sondern machen ein 20-20 daraus. Das wären die zwei Ansätze."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"option": 2},
|
||||
"allowed_event_types": ["technical_finding", "fact", "option"],
|
||||
"event_evidence_ids": ["e1", "e2", "e3"],
|
||||
"outcome": {"required": false},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {"count": 0}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "c_unaccepted_proposal",
|
||||
"description": "Possible Textor contact remains a proposal only.",
|
||||
"subject_id": "subject_c",
|
||||
"subject": "Erneute Kontaktaufnahme mit Dirk Textor zur Einschätzung",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Tim: Ich würde vielleicht Dirk Textor noch einmal kontaktieren und fragen, wie er das einschätzt."},
|
||||
{"evidence_id": "e2", "text": "Tim: Das kann man ja mit ihm einfach noch einmal rückkoppeln."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"proposal": 1},
|
||||
"allowed_event_types": ["proposal"],
|
||||
"event_evidence_ids": ["e1", "e2"],
|
||||
"outcome": {"required": false},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {"count": 0}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "d_proposal_with_objection",
|
||||
"description": "Washing proposal with energy objection but no unresolved issue.",
|
||||
"subject_id": "subject_d",
|
||||
"subject": "Waschen des Materials vor der weiteren Verarbeitung",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Antonius: Man könnte das Material vor der weiteren Verarbeitung waschen."},
|
||||
{"evidence_id": "e2", "text": "Martin: Ob sich das lohnt, weiß ich nicht. Waschen heißt nass machen und wieder trocknen; das ist ein wahnsinniger Energieaufwand."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"proposal": 1, "objection": 1},
|
||||
"allowed_event_types": ["proposal", "objection"],
|
||||
"event_evidence_ids": ["e1", "e2"],
|
||||
"outcome": {"required": false},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {"count": 0}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "e_rejected_alternative",
|
||||
"description": "Explicit rejection of Schlummer collaboration.",
|
||||
"subject_id": "subject_e",
|
||||
"subject": "Zusammenarbeit mit Dr. Schlummer für Versuche",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Antonius: Das Angebot von Dr. Schlummer für die Versuche kostet 30.000 Euro."},
|
||||
{"evidence_id": "e2", "text": "Tim: Dann haben wir gesagt: Nein, die Zusammenarbeit mit Dr. Schlummer machen wir nicht."},
|
||||
{"evidence_id": "e3", "text": "Antonius: Ja, das ist entschieden."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"fact": 1, "rejection": 1},
|
||||
"allowed_event_types": ["fact", "rejection", "clarification"],
|
||||
"event_evidence_ids": ["e1", "e2", "e3"],
|
||||
"outcome": {
|
||||
"required": true,
|
||||
"statuses": ["rejected"],
|
||||
"terms": ["nicht", "abgelehnt", "keine"],
|
||||
"scope_terms": ["zusammenarbeit", "versuch", "schlummer"],
|
||||
"evidence_ids": ["e2", "e3"]
|
||||
},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {"count": 0}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "f_trial_only_acceptance",
|
||||
"description": "Acceptance limited to a 20-metre trial.",
|
||||
"subject_id": "subject_f",
|
||||
"subject": "20-Prozent-Variante im Versuch am kleinen Extruder",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Martin: Wir könnten die 20-Prozent-Variante am kleinen Extruder nachstellen."},
|
||||
{"evidence_id": "e2", "text": "Tim: Ja, wir testen 20 Meter dieser Variante beim nächsten Versuch."},
|
||||
{"evidence_id": "e3", "text": "Tim: Das ist nur ein Versuch; damit ist die Variante noch nicht als Serienlösung festgelegt."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"proposal": 1, "scoped_acceptance": 1, "clarification": 1},
|
||||
"allowed_event_types": ["proposal", "scoped_acceptance", "clarification"],
|
||||
"event_evidence_ids": ["e1", "e2", "e3"],
|
||||
"outcome": {
|
||||
"required": true,
|
||||
"statuses": ["scoped_acceptance"],
|
||||
"terms": ["test", "versuch"],
|
||||
"scope_terms": ["20 meter", "20 m", "nur", "begrenzt"],
|
||||
"evidence_ids": ["e2", "e3"]
|
||||
},
|
||||
"actions": {
|
||||
"count": 1,
|
||||
"terms": ["test", "versuch", "20 meter"],
|
||||
"evidence_ids": ["e2"],
|
||||
"due_terms": ["nächsten versuch", "next trial"]
|
||||
},
|
||||
"unresolved_issues": {
|
||||
"count": 1,
|
||||
"terms": ["serienlösung", "final", "serie", "festgelegt"],
|
||||
"evidence_ids": ["e3"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "g_no_decision",
|
||||
"description": "Plant versus Technikum discussion ending without a decision.",
|
||||
"subject_id": "subject_g",
|
||||
"subject": "Reale Recyclinganlage oder Technikum und verfügbarer Reinigungsansatz",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Martin: Eine reale Recyclinganlage hätte das Risiko, dass wir kontaminiertes Material zurückbekommen."},
|
||||
{"evidence_id": "e2", "text": "Martin: Ich würde nicht in eine reale Anlage gehen. Wenn überhaupt, können wir über ein Technikum reden."},
|
||||
{"evidence_id": "e3", "text": "Tim: Man müsste zunächst prüfen, welcher Reinigungsansatz überhaupt verfügbar ist."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"objection": 1, "option": 1},
|
||||
"allowed_event_types": ["objection", "option", "proposal", "clarification"],
|
||||
"event_evidence_ids": ["e1", "e2", "e3"],
|
||||
"outcome": {"required": false},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {
|
||||
"count": 1,
|
||||
"terms": ["reinigungsansatz", "verfügbar", "prüfen", "reinigung"],
|
||||
"evidence_ids": ["e3"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "h_resulting_action",
|
||||
"description": "Explicitly accepted action with owner and deadline.",
|
||||
"subject_id": "subject_h",
|
||||
"subject": "Prüfung der Messdaten bis Freitag",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Antonius: Nina, übernimmst du die Prüfung der Messdaten bis Freitag?"},
|
||||
{"evidence_id": "e2", "text": "Nina: Ja, ich übernehme die Prüfung bis Freitag."}
|
||||
],
|
||||
"allowed_responsible": ["Nina"],
|
||||
"expected": {
|
||||
"event_type_minimums": {},
|
||||
"allowed_event_types": ["proposal", "clarification", "scoped_acceptance"],
|
||||
"event_evidence_ids": [],
|
||||
"outcome": {
|
||||
"required": true,
|
||||
"statuses": ["established"],
|
||||
"terms": ["übernimmt", "prüf", "accepted", "review", "assigned"],
|
||||
"scope_terms": ["messdaten", "prüfung", "measurement", "review"],
|
||||
"evidence_ids": ["e2"]
|
||||
},
|
||||
"actions": {
|
||||
"count": 1,
|
||||
"terms": ["messdaten", "prüf", "measurement", "review"],
|
||||
"responsible": "Nina",
|
||||
"due_terms": ["freitag", "friday"],
|
||||
"evidence_ids": ["e2"]
|
||||
},
|
||||
"unresolved_issues": {"count": 0}
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "i_outcome_and_unresolved",
|
||||
"description": "Bounded production outcome and unresolved publication question.",
|
||||
"subject_id": "subject_i",
|
||||
"subject": "Produktionsaufwand und Veröffentlichung von Energieaudit-Daten",
|
||||
"evidence": [
|
||||
{"evidence_id": "e1", "text": "Martin: An unserer Anlage gab es bei der reinen Produktion gegenüber dem Standardprodukt praktisch keine Änderung; wir waren nur fünf Grad kälter."},
|
||||
{"evidence_id": "e2", "text": "Antonius: Dann können wir mindestens festhalten: Gegenüber Virgin Material ist bei der reinen Produktion kein zusätzlicher Aufwand notwendig. Davor entsteht natürlich Aufwand."},
|
||||
{"evidence_id": "e3", "text": "Antonius: Welche Daten aus dem Energieaudit dürfen wir veröffentlichen?"},
|
||||
{"evidence_id": "e4", "text": "Martin: Das ist weiterhin ungeklärt. Wir müssen die Freigabe noch klären."}
|
||||
],
|
||||
"allowed_responsible": [],
|
||||
"expected": {
|
||||
"event_type_minimums": {"fact": 1},
|
||||
"allowed_event_types": ["technical_finding", "fact", "clarification"],
|
||||
"event_evidence_ids": ["e1", "e2"],
|
||||
"outcome": {
|
||||
"required": true,
|
||||
"statuses": ["established"],
|
||||
"terms": ["kein zusätzlicher", "keine zusätzliche", "unverändert"],
|
||||
"scope_terms": ["reine produktion", "produktion", "virgin"],
|
||||
"evidence_ids": ["e1", "e2"]
|
||||
},
|
||||
"actions": {"count": 0},
|
||||
"unresolved_issues": {
|
||||
"count": 1,
|
||||
"terms": ["veröffentlich", "freigabe", "energieaudit", "daten"],
|
||||
"evidence_ids": ["e3", "e4"]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user