Changes for page POC1: Core Workflow with Quality Gates

Summary

• Page properties (2 modified, 0 added, 0 removed)

Details

Page properties

Parent

...	...	@@ -1,1 +1,1 @@
1		-Test.FactHarbor pre10 V0\.9\.70.Roadmap.WebHome
	1	+Test.FactHarbor.Roadmap.WebHome

Content

...	...	@@ -12,12 +12,12 @@
12	12	**Key Innovation:** Quality validation BEFORE publication, not after
13	13
14	14	**What We're Proving:**
15		-
16	16	* AKEL can reliably extract factual claims from articles
17	17	* AKEL can generate credible verdicts with proper evidence
18	18	* Quality gates prevent hallucinations and low-confidence outputs
19	19	* Fully automated approach is viable
20	20
	20	+
21	21	== 2. Scope ==
22	22
23	23	=== In Scope ===
...	...	@@ -40,6 +40,7 @@
40	40	* A/B testing
41	41	* Gates 2 & 3 (Evidence relevance, Scenario coherence)
42	42
	43	+
43	43	== 3. Requirements ==
44	44
45	45	=== 3.1 NFR11: Quality Assurance Framework (POC1 Lite Version) ===
...	...	@@ -56,7 +56,6 @@
56	56	**Purpose:** Ensure extracted claims are factual assertions, not opinions or predictions
57	57
58	58	**Validation Checks:**
59		-
60	60	1. **Factual Statement Test:** Can this be verified with evidence?
61	61	2. **Opinion Detection:** Contains hedging language? ("I think", "probably", "best", "worst")
62	62	3. **Specificity Score:** Contains concrete details? (names, numbers, dates, locations)
...	...	@@ -63,13 +63,14 @@
63	63	4. **Future Prediction Test:** Makes claims about future events?
64	64
65	65	**Pass Criteria:**
66		-{{code}}- isFactual: true
	66	+{{code}}
	67	+- isFactual: true
67	67	- opinionScore: ≤ 0.3
68	68	- specificityScore: ≥ 0.3
69		-- claimType: FACTUAL{{/code}}
	70	+- claimType: FACTUAL
	71	+{{/code}}
70	70
71	71	**Action if Failed:**
72		-
73	73	* Flag as "Non-verifiable: Opinion/Prediction/Ambiguous"
74	74	* Do NOT generate scenarios or verdicts
75	75	* Display explanation to user
...	...	@@ -82,7 +82,6 @@
82	82	**Purpose:** Only publish verdicts with sufficient evidence and confidence
83	83
84	84	**Validation Checks:**
85		-
86	86	1. **Evidence Count:** Minimum 2 independent sources
87	87	2. **Source Quality:** Average reliability ≥ 0.6 (on 0-1 scale)
88	88	3. **Evidence Agreement:** % supporting vs. contradicting ≥ 0.6
...	...	@@ -89,7 +89,8 @@
89	89	4. **Uncertainty Factors:** Count of hedging statements in reasoning
90	90
91	91	**Confidence Tiers:**
92		-{{code}}HIGH (80-100%):
	92	+{{code}}
	93	+HIGH (80-100%):
93	93	- ≥3 sources
94	94	- ≥0.7 average quality
95	95	- ≥80% agreement
...	...	@@ -103,10 +103,10 @@
103	103	- ≥2 sources BUT low quality/agreement
104	104
105	105	INSUFFICIENT:
106		- - <2 sources → DO NOT PUBLISH{{/code}}
	107	+ - <2 sources → DO NOT PUBLISH
	108	+{{/code}}
107	107
108	108	**POC1 Publication Rule:**
109		-
110	110	* Minimum **MEDIUM** confidence required
111	111	* Blocked verdicts show "Insufficient Evidence" message
112	112
...	...	@@ -139,7 +139,6 @@
139	139	{{/code}}
140	140
141	141	**Updated Verdict States:**
142		-
143	143	* PUBLISHED - Passed all gates
144	144	* INSUFFICIENT_EVIDENCE - Failed Gate 4
145	145	* NON_FACTUAL_CLAIM - Failed Gate 1
...	...	@@ -146,6 +146,7 @@
146	146	* PROCESSING - In progress
147	147	* ERROR - System failure
148	148
	149	+
149	149	=== 3.3 Modified FR4: Analysis Summary (Enhanced) ===
150	150
151	151	**Enhancement for POC1:**
...	...	@@ -176,7 +176,6 @@
176	176	POC1 is considered **SUCCESSFUL** if:
177	177
178	178	**✅ Functional:**
179		-
180	180	* Processes diverse test articles without crashes
181	181	* Generates verdicts for all factual claims
182	182	* Blocks all non-factual claims (0% pass through)
...	...	@@ -183,7 +183,6 @@
183	183	* Blocks all insufficient-evidence verdicts (0% with <2 sources)
184	184
185	185	**✅ Quality:**
186		-
187	187	* Hallucination rate <10% (manual verification)
188	188	* 0 verdicts with <2 sources published
189	189	* 0 opinion statements published as facts
...	...	@@ -190,18 +190,17 @@
190	190	* Average quality score ≥7.0/10
191	191
192	192	**✅ Performance:**
193		-
194	194	* Processing time reasonable for POC demonstration
195	195	* Quality gates execute efficiently
196	196	* UI displays results clearly
197	197
198	198	**✅ Learnings:**
199		-
200	200	* Identified prompt engineering improvements
201	201	* Documented AKEL strengths/weaknesses
202	202	* Validated threshold values
203	203	* Clear path to POC2 defined
204	204
	202	+
205	205	== 5. Decision Gates ==
206	206
207	207	**POC1 → POC2 Decision:**
...	...	@@ -232,7 +232,6 @@
232	232	{{/code}}
233	233
234	234	**POC1 Acceptable Simplifications:**
235		-
236	236	* Single AKEL call (not multi-component pipeline)
237	237	* No scenarios (implicit in verdicts)
238	238	* Basic evidence linking
...	...	@@ -239,16 +239,18 @@
239	239	* 2 gates instead of 4
240	240	* No review queue
241	241
242		-**See:** [[Architecture>>Test.FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] for details
	239	+**See:** [[Architecture>>Test.FactHarbor.Specification.Architecture.WebHome]] for details
243	243
244	244
245	245	== Related Pages ==
246	246
247		-* [[Roadmap Overview>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.WebHome]] - All phases
248		-* [[POC2 Requirements>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.POC2.WebHome]] - Next phase
249		-* [[Requirements>>Test.FactHarbor pre10 V0\.9\.70.Specification.Requirements.WebHome]] - Full system requirements
250		-* [[Architecture>>Test.FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] - System architecture
	244	+* [[Roadmap Overview>>Test.FactHarbor.Roadmap.WebHome]] - All phases
	245	+* [[POC2 Requirements>>Test.FactHarbor.Roadmap.POC2.WebHome]] - Next phase
	246	+* [[Requirements>>Test.FactHarbor.Specification.Requirements.WebHome]] - Full system requirements
	247	+* [[Architecture>>Test.FactHarbor.Specification.Architecture.WebHome]] - System architecture
251	251	* [[NFR11 Full Specification>>Test.FactHarbor.Specification.Requirements.WebHome#NFR11]] - Complete quality framework
252	252
	250	+
253	253	**Document Status:** ✅ POC1 Specification Complete - Ready for Implementation
254	254	**Version:** V0.9.70
	253	+