Changes for page Requirements

Summary

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

Details

Page properties

Parent

...	...	@@ -1,1 +1,1 @@
1		-Test.FactHarbor.Specification.WebHome
	1	+Test.FactHarbor pre13 V0\.9\.70.Specification.WebHome

Content

...	...	@@ -1,4 +1,7 @@
1		-= Requirements = **This page defines Roles, Content States, Rules, and System Requirements for FactHarbor.** **Core Philosophy:** Invest in system improvement, not manual data correction. When AI makes errors, improve the algorithm and re-process automatically. == Navigation == * **[[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]]** - What users need from FactHarbor (drives these requirements)
	1	+= Requirements =
	2	+
	3	+ **This page defines Roles, Content States, Rules, and System Requirements for FactHarbor.** **Core Philosophy:** Invest in system improvement, not manual data correction. When AI makes errors, improve the algorithm and re-process automatically. == Navigation == * **[[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]]** - What users need from FactHarbor (drives these requirements)
	4	+
2	2	* **This page** - How we fulfill those needs through system design (% class="box infomessage" %)
3	3	(((
4	4	**How to read this page:** 1. **User Needs drive Requirements**: See [[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]] for what users need
...	...	@@ -5,7 +5,7 @@
5	5	2. **Requirements define implementation**: This page shows how we fulfill those needs
6	6	3. **Functional Requirements (FR)**: Specific features and capabilities
7	7	4. **Non-Functional Requirements (NFR)**: Quality attributes (performance, security, etc.) Each requirement references which User Needs it fulfills.
8		-))) == 1. Roles == **Fulfills**: UN-12 (Submit claims), UN-13 (Cite verdicts), UN-14 (API access) FactHarbor uses three simple roles plus a reputation system. === 1.1 Reader === **Who**: Anyone (no login required) **Can**:
	11	+)))== 1. Roles == **Fulfills**: UN-12 (Submit claims), UN-13 (Cite verdicts), UN-14 (API access) FactHarbor uses three simple roles plus a reputation system. === 1.1 Reader === **Who**: Anyone (no login required) **Can**:
9	9	* Browse and search claims
10	10	* View scenarios, evidence, verdicts, and confidence scores
11	11	* Flag issues or errors
...	...	@@ -78,10 +78,12 @@
78	78	* Flag uncertainty clearly
79	79	* Identify contradictions in evidence
80	80	* Learn from human corrections **When AKEL Makes Errors**:
	84	+
81	81	1. Capture the error pattern (what, why, how common)
82	82	2. Improve the system (better prompt, model, validation)
83	83	3. Re-process affected claims automatically
84	84	4. Measure improvement (did quality increase?) **Human Role**: Train AKEL through corrections, not replace AKEL === 3.3 Contributors Should === * Improve clarity and structure
	89	+
85	85	* Add missing sources
86	86	* Flag errors for system improvement
87	87	* Suggest better ways to present information
...	...	@@ -122,6 +122,7 @@
122	122	* **Score 60-80**: Publish with prominent warnings
123	123	* **Score 40-60**: Publish with standard warnings
124	124	* **Score < 40**: Publish normally **Continuous monitoring**: Risk score recalculated as new information emerges **User Needs served**: UN-10 (Detect manipulation tactics), UN-16 (Review status) == 6. System Improvement Process == **Core principle**: Fix the system, not just the data. === 6.1 Error Capture === **When users flag errors or make corrections**:
	130	+
125	125	1. What was wrong? (categorize)
126	126	2. What should it have been?
127	127	3. Why did the system fail? (root cause)
...	...	@@ -132,6 +132,7 @@
132	132	4. **Deploy**: Roll out if quality improves
133	133	5. **Re-process**: Automatically update affected claims
134	134	6. **Monitor**: Track quality metrics === 6.3 Quality Metrics Dashboard === **Track continuously**:
	141	+
135	135	* Error rate by category
136	136	* Source quality distribution
137	137	* Confidence score trends
...	...	@@ -199,28 +199,43 @@
199	199	* Exportable as standalone summary report
200	200	* Shareable via permanent URL ==== FR13 — In-Article Claim Highlighting ==== **Fulfills**: UN-17 (In-article claim highlighting) **Purpose**: Enable readers to quickly assess claim credibility while reading by visually highlighting factual claims with color-coded indicators ==== Visual Example: Article with Highlighted Claims ==== (% class="box" %)
201	201	(((
202		-**Article: "New Study Shows Benefits of Mediterranean Diet"** A recent study published in the Journal of Nutrition has revealed new findings about the Mediterranean diet. (% class="box successmessage" style="margin:10px 0;" %)
	209	+**Article: "New Study Shows Benefits of Mediterranean Diet"** A recent study published in the Journal of Nutrition has revealed new findings about the Mediterranean diet.
	210	+
	211	+(% class="box successmessage" style="margin:10px 0;" %)
203	203	(((
204	204	🟢 **Researchers found that Mediterranean diet followers had a 25% lower risk of heart disease compared to control groups** (% style="font-size:0.9em; color:#666;" %)
205	205	↑ WELL SUPPORTED • 87% confidence
206	206	[[Click for evidence details →]]
207		-(%%)
208		-))) The study, which followed 10,000 participants over five years, showed significant improvements in cardiovascular health markers. (% class="box warningmessage" style="margin:10px 0;" %)
	216	+
	217	+
	218	+)))
	219	+
	220	+The study, which followed 10,000 participants over five years, showed significant improvements in cardiovascular health markers.
	221	+
	222	+(% class="box warningmessage" style="margin:10px 0;" %)
209	209	(((
210	210	🟡 **Some experts believe this diet can completely prevent heart attacks** (% style="font-size:0.9em; color:#666;" %)
211	211	↑ UNCERTAIN • 45% confidence
212	212	Overstated - evidence shows risk reduction, not prevention
213	213	[[Click for details →]]
214		-(%%)
215		-))) Dr. Maria Rodriguez, lead researcher, recommends incorporating more olive oil, fish, and vegetables into daily meals. (% class="box errormessage" style="margin:10px 0;" %)
	228	+
	229	+
	230	+)))
	231	+
	232	+Dr. Maria Rodriguez, lead researcher, recommends incorporating more olive oil, fish, and vegetables into daily meals.
	233	+
	234	+(% class="box errormessage" style="margin:10px 0;" %)
216	216	(((
217	217	🔴 **The study proves that saturated fats cause heart disease** (% style="font-size:0.9em; color:#666;" %)
218	218	↑ REFUTED • 15% confidence
219	219	Claim not supported by study design; correlation ≠ causation
220	220	[[Click for counter-evidence →]]
221		-(%%)
222		-))) Participants also reported feeling more energetic and experiencing better sleep quality, though these were secondary measures.
223		-))) **Legend:**
	240	+
	241	+
	242	+)))
	243	+
	244	+Participants also reported feeling more energetic and experiencing better sleep quality, though these were secondary measures.
	245	+)))**Legend:**
224	224	* 🟢 = Well-supported claim (confidence ≥75%)
225	225	* 🟡 = Uncertain claim (confidence 40-74%)
226	226	* 🔴 = Refuted/unsupported claim (confidence <40%)
...	...	@@ -229,28 +229,43 @@
229	229	**FactHarbor Analysis** **Claim:**
230	230	"Researchers found that Mediterranean diet followers had a 25% lower risk of heart disease" **Verdict:** WELL SUPPORTED
231	231	**Confidence:** 87% **Evidence Summary:**
	254	+
232	232	* Meta-analysis of 12 RCTs confirms 23-28% risk reduction
233	233	* Consistent findings across multiple populations
234	234	* Published in peer-reviewed journal (high credibility) **Uncertainty Factors:**
235	235	* Exact percentage varies by study (20-30% range) [[View Full Analysis →]]
236		-))) **Color-Coding System**:
	259	+)))**Color-Coding System**:
237	237	* **Green**: Well-supported claims (confidence ≥75%, strong evidence)
238	238	* **Yellow/Orange**: Uncertain claims (confidence 40-74%, conflicting or limited evidence)
239	239	* **Red**: Refuted or unsupported claims (confidence <40%, contradicted by evidence)
240		-* **Gray/Neutral**: Non-factual content (opinions, questions, procedural text) ==== Interactive Highlighting Example (Detailed View) ==== (% style="width:100%; border-collapse:collapse;" %)
	263	+* **Gray/Neutral**: Non-factual content (opinions, questions, procedural text) ==== Interactive Highlighting Example (Detailed View) ====
	264	+
241	241	|=**Article Text**|=**Status**|=**Analysis**
242		-|(((A recent study published in the Journal of Nutrition has revealed new findings about the Mediterranean diet.)))|(% style="text-align:center;" %)Plain text|(% style="font-style:italic; color:#888;" %)Context - no highlighting
243		-|(((//Researchers found that Mediterranean diet followers had a 25% lower risk of heart disease compared to control groups//)))|(% style="background-color:#D4EDDA; text-align:center; padding:8px;" %)🟢 **WELL SUPPORTED**|(((
	266	+|(((
	267	+A recent study published in the Journal of Nutrition has revealed new findings about the Mediterranean diet.
	268	+)))|(% style="text-align:center;" %)Plain text|(% style="font-style:italic; color:#888;" %)Context - no highlighting
	269	+|(((
	270	+//Researchers found that Mediterranean diet followers had a 25% lower risk of heart disease compared to control groups//
	271	+)))|(% style="background-color:#D4EDDA; text-align:center; padding:8px;" %)🟢 **WELL SUPPORTED**|(((
244	244	**87% confidence** Meta-analysis of 12 RCTs confirms 23-28% risk reduction [[View Full Analysis]]
245	245	)))
246		-|(((The study, which followed 10,000 participants over five years, showed significant improvements in cardiovascular health markers.)))|(% style="text-align:center;" %)Plain text|(% style="font-style:italic; color:#888;" %)Methodology - no highlighting
247		-|(((//Some experts believe this diet can completely prevent heart attacks//)))|(% style="background-color:#FFF3CD; text-align:center; padding:8px;" %)🟡 **UNCERTAIN**|(((
	274	+|(((
	275	+The study, which followed 10,000 participants over five years, showed significant improvements in cardiovascular health markers.
	276	+)))|(% style="text-align:center;" %)Plain text|(% style="font-style:italic; color:#888;" %)Methodology - no highlighting
	277	+|(((
	278	+//Some experts believe this diet can completely prevent heart attacks//
	279	+)))|(% style="background-color:#FFF3CD; text-align:center; padding:8px;" %)🟡 **UNCERTAIN**|(((
248	248	**45% confidence** Overstated - evidence shows risk reduction, not prevention [[View Details]]
249	249	)))
250		-|(((Dr. Rodriguez recommends incorporating more olive oil, fish, and vegetables into daily meals.)))|(% style="text-align:center;" %)Plain text|(% style="font-style:italic; color:#888;" %)Recommendation - no highlighting
251		-|(((//The study proves that saturated fats cause heart disease//)))|(% style="background-color:#F8D7DA; text-align:center; padding:8px;" %)🔴 **REFUTED**|(((
	282	+|(((
	283	+Dr. Rodriguez recommends incorporating more olive oil, fish, and vegetables into daily meals.
	284	+)))|(% style="text-align:center;" %)Plain text|(% style="font-style:italic; color:#888;" %)Recommendation - no highlighting
	285	+|(((
	286	+//The study proves that saturated fats cause heart disease//
	287	+)))|(% style="background-color:#F8D7DA; text-align:center; padding:8px;" %)🔴 **REFUTED**|(((
252	252	**15% confidence** Claim not supported by study; correlation ≠ causation [[View Counter-Evidence]]
253		-))) **Design Notes:**
	289	+)))**Design Notes:**
	290	+
254	254	* Highlighted claims use italics to distinguish from plain text
255	255	* Color backgrounds match XWiki message box colors (success/warning/error)
256	256	* Status column shows verdict prominently
...	...	@@ -277,11 +277,13 @@
277	277	* Highlighting data stored as annotations with byte offsets
278	278	* Client-side rendering of highlights based on verdict data
279	279	* Mobile responsive (tap instead of hover) === 8.5 Workflow & Moderation === ==== FR9 — Publication Workflow ==== **Fulfills**: UN-1 (Fast access to verified content), UN-16 (Clear review status) **Simple flow**:
	317	+
280	280	1. Claim submitted
281	281	2. AKEL processes (automated)
282	282	3. If confidence > threshold: Publish (labeled as AI-generated)
283	283	4. If confidence < threshold: Flag for improvement
284	284	5. If risk score > threshold: Flag for moderator **No multi-stage approval process** ==== FR10 — Moderation ==== **Focus on abuse, not routine quality**:
	323	+
285	285	* Automated abuse detection
286	286	* Moderators handle flags
287	287	* Quick response to harmful content
...	...	@@ -304,29 +304,37 @@
304	304	* Automated testing
305	305	* Continuous integration
306	306	* Comprehensive documentation === NFR11: AKEL Quality Assurance Framework === **Fulfills:** AI safety, IFCN methodology transparency **Specification:** Multi-layer AI quality gates to detect hallucinations, low-confidence results, and logical inconsistencies. ==== Quality Gate 1: Claim Extraction Validation ==== **Purpose:** Ensure extracted claims are factual assertions (not opinions/predictions) **Checks:**
	346	+
307	307	1. **Factual Statement Test:** Is this verifiable? (Yes/No)
308	308	2. **Opinion Detection:** Contains hedging language? ("I think", "probably", "best")
309	309	3. **Future Prediction Test:** Makes claims about future events?
310	310	4. **Specificity Score:** Contains specific entities, numbers, dates? **Thresholds:**
	351	+
311	311	* Factual: Must be "Yes"
312	312	* Opinion markers: <2 hedging phrases
313	313	* Specificity: ≥3 specific elements **Action if Failed:** Flag as "Non-verifiable", do NOT generate verdict ==== Quality Gate 2: Evidence Relevance Validation ==== **Purpose:** Ensure AI-linked evidence actually relates to claim **Checks:**
	355	+
314	314	1. **Semantic Similarity Score:** Evidence vs. claim (embeddings)
315	315	2. **Entity Overlap:** Shared people/places/things?
316	316	3. **Topic Relevance:** Discusses claim subject? **Thresholds:**
	359	+
317	317	* Similarity: ≥0.6 (cosine similarity)
318	318	* Entity overlap: ≥1 shared entity
319	319	* Topic relevance: ≥0.5 **Action if Failed:** Discard irrelevant evidence ==== Quality Gate 3: Scenario Coherence Check ==== **Purpose:** Validate scenario assumptions are logical and complete **Checks:**
	363	+
320	320	1. **Completeness:** All required fields populated
321	321	2. **Internal Consistency:** Assumptions don't contradict
322	322	3. **Distinguishability:** Scenarios meaningfully different **Thresholds:**
	367	+
323	323	* Required fields: 100%
324	324	* Contradiction score: <0.3
325	325	* Scenario similarity: <0.8 **Action if Failed:** Merge duplicates, reduce confidence -20% ==== Quality Gate 4: Verdict Confidence Assessment ==== **Purpose:** Only publish high-confidence verdicts **Checks:**
	371	+
326	326	1. **Evidence Count:** Minimum 2 sources
327	327	2. **Source Quality:** Average reliability ≥0.6
328	328	3. **Evidence Agreement:** Supporting vs. contradicting ≥0.6
329	329	4. **Uncertainty Factors:** Hedging in reasoning **Confidence Tiers:**
	376	+
330	330	* **HIGH (80-100%):** ≥3 sources, ≥0.7 quality, ≥80% agreement
331	331	* **MEDIUM (50-79%):** ≥2 sources, ≥0.6 quality, ≥60% agreement
332	332	* **LOW (0-49%):** <2 sources OR low quality/agreement
...	...	@@ -337,11 +337,13 @@
337	337	* ✅ All gates operational
338	338	* ✅ Hallucination rate <5%
339	339	* ✅ Quality metrics public === NFR12: Security Controls === **Fulfills:** Production readiness, legal compliance **Requirements:**
	387	+
340	340	1. **Input Validation:** SQL injection, XSS, CSRF prevention
341	341	2. **Rate Limiting:** 5 analyses per minute per IP
342	342	3. **Authentication:** Secure sessions, API key rotation
343	343	4. **Data Protection:** HTTPS, encryption, backups
344	344	5. **Security Audit:** Penetration testing, GDPR compliance **Milestone:** Beta 0 (essential), V1.0 (complete) **BLOCKER** === NFR13: Quality Metrics Transparency === **Fulfills:** IFCN transparency, user trust **Public Metrics:**
	393	+
345	345	* Quality gates performance
346	346	* Evidence quality stats
347	347	* Hallucination rate
...	...	@@ -352,6 +352,7 @@
352	352	**Note:** Implementation phases (POC1, POC2, Beta 0, V1.0) are defined in [[POC Requirements>>FactHarbor.Specification.POC.Requirements]] and [[Implementation Roadmap>>FactHarbor.Implementation-Roadmap.WebHome]], not in this priority matrix.
353	353
354	354	**Priority Levels:**
	404	+
355	355	* **CRITICAL** - System doesn't work without it, or major safety/legal risk
356	356	* **HIGH** - Core functionality, essential for success
357	357	* **MEDIUM** - Important but not blocking
...	...	@@ -358,12 +358,13 @@
358	358	* **LOW** - Nice to have, can be deferred
359	359
360	360	**Urgency Levels:**
	411	+
361	361	* **HIGH** - Immediate need (critical for proof of concept)
362	362	* **MEDIUM** - Important but not immediate
363	363	* **LOW** - Future enhancement
364	364
365	365	|= ID |= Title |= Priority |= Urgency |= Reason (for HIGH priority/urgency)
366		-| **HIGH URGENCY** |||||
	417	+| **HIGH URGENCY** |||||\\
367	367	| **FR1** | Claim Intake | CRITICAL | HIGH | System entry point - cannot process claims without it
368	368	| **FR5** | Evidence Collection | CRITICAL | HIGH | Core fact-checking functionality - no evidence = no verdict
369	369	| **FR7** | Verdict Computation | CRITICAL | HIGH | The output users see - core value proposition
...	...	@@ -372,7 +372,7 @@
372	372	| **FR3** | Claim Classification | HIGH | HIGH | Identifies factual vs non-factual claims - essential quality gate
373	373	| **FR4** | Scenario Generation | HIGH | HIGH | Handles ambiguous claims - key methodology innovation
374	374	| **FR6** | Evidence Evaluation | HIGH | HIGH | Source quality directly impacts verdict credibility
375		-| **MEDIUM URGENCY** |||||
	426	+| **MEDIUM URGENCY** |||||\\
376	376	| **NFR12** | Security Controls | CRITICAL | MEDIUM | —
377	377	| **FR9** | Corrections | HIGH | MEDIUM | IFCN requirement - mandatory for credibility
378	378	| **FR44** | ClaimReview Schema | HIGH | MEDIUM | Search engine visibility - MUST for V1.0 discovery
...	...	@@ -390,7 +390,7 @@
390	390	| **NFR2** | Scalability | MEDIUM | MEDIUM | —
391	391	| **NFR4** | Security & Privacy | MEDIUM | MEDIUM | —
392	392	| **NFR5** | Maintainability | MEDIUM | MEDIUM | —
393		-| **LOW URGENCY** |||||
	444	+| **LOW URGENCY** |||||\\
394	394	| **FR11** | Social Sharing | LOW | LOW | —
395	395	| **FR12** | Notifications | LOW | LOW | —
396	396	| **FR49** | A/B Testing | LOW | LOW | —
...	...	@@ -402,10 +402,12 @@
402	402	**Total:** 32 requirements (24 Functional, 8 Non-Functional)
403	403
404	404	**Notes:**
	456	+
405	405	* Reason column: Only populated for HIGH priority or HIGH urgency items
406	406	* MEDIUM and LOW priority items use "—" (no specific reason needed)
407	407
408	408	**See also:**
	461	+
409	409	* [[POC Requirements>>FactHarbor.Specification.POC.Requirements]] - POC1 scope and simplifications
410	410	* [[Implementation Roadmap>>FactHarbor.Implementation-Roadmap.WebHome]] - Phase-by-phase implementation plan
411	411	* [[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]] - Foundation that drives these requirements
...	...	@@ -440,7 +440,10 @@
440	440
441	441	**Note:** Each User Need inherits priority from the requirements it drives. For example, UN-2 (Claim Extraction and Verification) drives FR1-7, which are CRITICAL/HIGH priority, therefore UN-2 is also critical to the project.
442	442
443		-== 11. MVP Scope == **Phase 1 : Read-Only MVP** Build:
	496	+== 11. MVP Scope ==
	497	+
	498	+ **Phase 1 : Read-Only MVP** Build:
	499	+
444	444	* Automated claim analysis
445	445	* Confidence scoring
446	446	* Source evaluation
...	...	@@ -477,13 +477,13 @@
477	477	* [[NFR12 — Security Controls>>#NFR12]]
478	478	* [[NFR13 — Quality Metrics Transparency>>#NFR13]] **Other Requirements:**
479	479	* [[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]]
480		-*
	536	+* \\
481	481	* [[Gap Analysis>>FactHarbor.Specification.Requirements.GapAnalysis]] * **[[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]]** - What users need (drives these requirements)
482	482	* [[Architecture>>FactHarbor.Specification.Architecture.WebHome]] - How requirements are implemented
483	483	* [[Data Model>>FactHarbor.Specification.Data Model.WebHome]] - Data structures supporting requirements
484	484	* [[Workflows>>FactHarbor.Specification.Workflows.WebHome]] - User interaction workflows
485	485	* [[AKEL>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]] - AI system fulfilling automation requirements
486		-* [[Global Rules>>FactHarbor.Organisation.How-We-Work-Together.GlobalRules.WebHome]]
	542	+* [[Global Rules>>Archive.FactHarbor.Organisation.How-We-Work-Together.GlobalRules.WebHome]]
487	487	* [[Privacy Policy>>FactHarbor.Organisation.How-We-Work-Together.Privacy-Policy]] = V0.9.70 Additional Requirements = == Functional Requirements (Additional) == === FR44: ClaimReview Schema Implementation === Generate valid ClaimReview structured data for Google/Bing visibility. **Schema.org Mapping:**
488	488	* 80-100% likelihood → 5 (Highly Supported)
489	489	* 60-79% → 4 (Supported)
...	...	@@ -490,6 +490,7 @@
490	490	* 40-59% → 3 (Mixed)
491	491	* 20-39% → 2 (Questionable)
492	492	* 0-19% → 1 (Refuted) **Milestone:** V1.0 === FR45: User Corrections Notification System === Notify users when analyses are corrected. **Mechanisms:**
	549	+
493	493	1. In-page banner (30 days)
494	494	2. Public correction log
495	495	3. Email notifications (opt-in)
...	...	@@ -498,9 +498,11 @@
498	498	2. EXIF metadata analysis
499	499	3. Manipulation detection (basic)
500	500	4. Context verification **Milestone:** Beta 0 (basic), V1.0 (extended) === FR47: Archive.org Integration === Auto-save evidence sources to Wayback Machine. **Milestone:** Beta 0 === FR48: Safety Framework for Contributors === Protect contributors from harassment and legal threats. **Milestone:** V1.1 === FR49: A/B Testing Framework === Test AKEL approaches and UI designs systematically. **Milestone:** V1.0 === FR50-FR53: Future Enhancements (V2.0+) === * **FR50:** OSINT Toolkit Integration
	558	+
501	501	* **FR51:** Video Verification System
502	502	* **FR52:** Interactive Detection Training
503	503	* **FR53:** Cross-Organizational Sharing **Milestone:** V2.0+ (12-18 months post-launch)
	562	+
504	504	=== FR54: Evidence Deduplication ===
505	505
506	506	**Fulfills:** Accurate evidence counting, quality metrics
...	...	@@ -512,21 +512,24 @@
512	512	**Deduplication Logic:**
513	513
514	514	1. **URL Normalization:**
515		- * Remove tracking parameters (?utm_source=...)
516		- * Normalize http/https
517		- * Normalize www/non-www
518		- * Handle redirects
519	519
	575	+* Remove tracking parameters (?utm_source=...)
	576	+* Normalize http/https
	577	+* Normalize www/non-www
	578	+* Handle redirects
	579	+
520	520	2. **Content Similarity:**
521		- * If two sources have >90% text similarity → Same source
522		- * If one is subset of other → Same source
523		- * Use fuzzy matching for minor differences
524	524
	582	+* If two sources have >90% text similarity → Same source
	583	+* If one is subset of other → Same source
	584	+* Use fuzzy matching for minor differences
	585	+
525	525	3. **Cross-Domain Syndication:**
526		- * Detect wire service content (AP, Reuters)
527		- * Mark as single source if syndicated
528		- * Count original publication only
529	529
	588	+* Detect wire service content (AP, Reuters)
	589	+* Mark as single source if syndicated
	590	+* Count original publication only
	591	+
530	530	**Display:**
531	531
532	532	{{code}}
...	...	@@ -538,6 +538,7 @@
538	538	{{/code}}
539	539
540	540	**Acceptance Criteria:**
	603	+
541	541	* ✅ Duplicate URLs recognized
542	542	* ✅ Syndicated content detected
543	543	* ✅ Evidence count shows "unique" vs "total"
...	...	@@ -544,20 +544,18 @@
544	544
545	545	**Milestone:** POC2, Beta 0
546	546
547		-== Enhanced Existing Requirements == === FR7: Automated Verdicts (Enhanced with Quality Gates) === **POC1+ Enhancement:** After AKEL generates verdict, it passes through quality gates: {{code}}
548		-Workflow:
	610	+== Enhanced Existing Requirements ==
	611	+
	612	+ ~=== FR7: Automated Verdicts (Enhanced with Quality Gates) === **POC1+ Enhancement:** After AKEL generates verdict, it passes through quality gates: {{code}}Workflow:
549	549	1. Extract claims ↓
550	550	2. [GATE 1] Validate fact-checkable ↓
551	551	3. Generate scenarios ↓
552	552	4. Generate verdicts ↓
553	553	5. [GATE 4] Validate confidence ↓
554		-6. Display to user
555		-{{/code}} **Updated Verdict States:**
	618	+6. Display to user{{/code}} **Updated Verdict States:**
	619	+
556	556	* PUBLISHED
557	557	* INSUFFICIENT_EVIDENCE
558	558	* NON_FACTUAL_CLAIM
559	559	* PROCESSING
560		-* ERROR === FR4: Analysis Summary (Enhanced with Quality Metadata) === **POC1+ Enhancement:** Display quality indicators: {{code}}
561		-Analysis Summary: Verifiable Claims: 3/5 High Confidence Verdicts: 1 Medium Confidence: 2 Evidence Sources: 12 Avg Source Quality: 0.73 Quality Score: 8.5/10
562		-{{/code}}
563		-
	624	+* ERROR === FR4: Analysis Summary (Enhanced with Quality Metadata) === **POC1+ Enhancement:** Display quality indicators: {{code}}Analysis Summary: Verifiable Claims: 3/5 High Confidence Verdicts: 1 Medium Confidence: 2 Evidence Sources: 12 Avg Source Quality: 0.73 Quality Score: 8.5/10{{/code}}