Wiki source code of POC Requirements (POC1 & POC2)

Last modified by Robert Schaub on 2025/12/23 17:40

version	line-number	content
1.1	1	= POC Requirements =
	2
	3	Status: ✅ Approved for Development
	4	Version: 3.0 (Aligned with Main Requirements)
	5	Goal: Prove that AI can extract claims and determine verdicts automatically without human intervention
	6
	7	{{info}}
	8	Core Philosophy: POC validates the [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]] through simplified implementation. All POC features map to formal FR/NFR requirements.
	9	{{/info}}
	10
	11
	12	== 1. POC Overview ==
	13
	14	=== 1.1 What POC Tests ===
	15
	16	Core Question:
1.2	17
1.1	18	> Can AI automatically extract factual claims from articles and evaluate them with reasonable verdicts?
	19
	20	What we're proving:
1.2	21
1.1	22	* AI can identify factual claims from text
	23	* AI can evaluate those claims with structured evidence
	24	* Quality gates can filter unreliable outputs
	25	* The core workflow is technically feasible
	26
	27	What we're NOT proving:
1.2	28
1.1	29	* Production-ready reliability (that's POC2)
	30	* User-facing features (that's Beta 0)
	31	* Full IFCN compliance (that's V1.0)
	32
	33	=== 1.2 Requirements Mapping ===
	34
	35	POC1 implements a subset of the full system requirements defined in [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]].
	36
	37	Scope Summary:
1.2	38
1.1	39	* In Scope: 8 requirements (7 FRs + 1 NFR)
	40	* Partial: 3 NFRs (simplified versions)
	41	* Out of Scope: 19 requirements (deferred to later phases)
	42
	43	== 2. POC1 Scope ==
	44
	45	{{success}}
1.2	46	Authoritative Source for Phase Mapping: [[Requirements Roadmap Matrix>>Test.FactHarbor V0\.9\.88.Roadmap.Requirements-Roadmap-Matrix.WebHome]]
1.1	47
	48	The Roadmap Matrix is the single source of truth for which requirements are implemented in which phases. This page provides POC1-specific implementation details only.
	49	{{/success}}
	50
	51	POC1 implements these formal requirements:
	52
	53	\|= Formal Req \|= Implementation in POC1 \|= Notes
	54	\| FR4 \| Analysis Summary \| Basic format; quality metadata deferred to POC2
	55	\| FR7 \| Automated Verdicts \| Full implementation with quality gates (NFR11)
	56	\| NFR11 \| Quality Assurance Framework \| 4 quality gates implemented
	57
	58	POC1 also implements these workflow components (detailed as FR1-FR6 in implementation sections below)
	59
1.2	60	{{info}}Note: FR11 (Audit Trail) and FR13 (In-Article Claim Highlighting) are deferred to Beta 0 for production readiness and user experience enhancement.{{/info}}:
	61
1.1	62	* Claim extraction (FR1)
	63	* Claim context (FR2)
	64	* Multiple scenarios (FR3)
	65	* Evidence collection (FR5)
	66	* Source quality assessment (FR6)
	67	* Time evolution tracking (FR8) - deferred to POC2
	68	* Audit trail (FR11) - deferred to Beta 0
	69	* In-article highlighting (FR13) - deferred to Beta 0
	70
	71	Partial implementations:
1.2	72
1.1	73	* NFR1 (Explainability) - Basic only
	74	* NFR2 (Performance) - Functional but not optimized
	75	* NFR3 (Transparency) - Basic only
	76
	77	Detailed POC1 implementation specifications continue below...
	78
	79
	80
	81	== 3. POC Simplifications ==
	82
	83	=== 3.1 FR1: Claim Extraction (Full Implementation) ===
	84
	85	Main Requirement: AI extracts factual claims from input text
	86
	87	POC Implementation:
1.2	88
1.1	89	* ✅ AKEL extracts claims using LLM
	90	* ✅ Each claim includes original text reference
	91	* ✅ Claims are identified as factual/non-factual
	92	* ❌ No advanced claim parsing (added in POC2)
	93
	94	Acceptance Criteria:
1.2	95
1.1	96	* Extracts 3-5 claims from typical article
	97	* Identifies factual vs non-factual claims
	98	* Quality Gate 1 validates extraction
	99
	100	=== 3.2 FR3: Multiple Scenarios (Full Implementation) ===
	101
	102	Main Requirement: Generate multiple interpretation scenarios for ambiguous claims
	103
	104	POC Implementation:
1.2	105
1.1	106	* ✅ AKEL generates 2-3 scenarios per claim
	107	* ✅ Scenarios capture different interpretations
	108	* ✅ Each scenario is evaluated separately
	109	* ✅ Verdict considers all scenarios
	110
	111	Acceptance Criteria:
1.2	112
1.1	113	* Generates 2+ scenarios for ambiguous claims
	114	* Scenarios are meaningfully different
	115	* All scenarios are evaluated
	116
	117	=== 3.3 FR4: Analysis Summary (Basic Implementation) ===
	118
	119	Main Requirement: Provide user-friendly summary of analysis
	120
	121	POC Implementation:
1.2	122
1.1	123	* ✅ Simple text summary generated
	124	* ❌ No rich formatting (added in Beta 0)
	125	* ❌ No visual elements (added in Beta 0)
	126	* ❌ No interactive features (added in Beta 0)
	127
	128	POC Format:
	129	```
	130	Claim: [extracted claim]
	131	Scenarios: [list of scenarios]
	132	Evidence: [supporting/opposing evidence]
	133	Verdict: [probability with uncertainty]
	134	```
	135
	136
	137	=== 3.4 FR5-FR6: Evidence Collection & Evaluation (Full Implementation) ===
	138
	139	Main Requirements:
1.2	140
1.1	141	* FR5: Collect supporting and opposing evidence
	142	* FR6: Evaluate evidence source reliability
	143
	144	POC Implementation:
1.2	145
1.1	146	* ✅ AKEL searches for evidence (web/knowledge base)
	147	* ✅ Mandatory contradiction search (finds opposing evidence)
	148	* ✅ Source reliability scoring
	149	* ❌ No evidence deduplication (added in POC2)
	150	* ❌ No advanced source verification (added in POC2)
	151
	152	Acceptance Criteria:
1.2	153
1.1	154	* Finds 2+ supporting evidence items
	155	* Finds 1+ opposing evidence (if exists)
	156	* Sources scored for reliability
	157
	158	=== 3.5 FR7: Automated Verdicts (Full Implementation) ===
	159
	160	Main Requirement: AI computes verdicts with uncertainty quantification
	161
	162	POC Implementation:
1.2	163
1.1	164	* ✅ Probabilistic verdicts (0-100% confidence)
	165	* ✅ Uncertainty explicitly stated
	166	* ✅ Reasoning chain provided
	167	* ✅ Quality Gate 4 validates verdict confidence
	168
	169	POC Output:
	170	```
	171	Verdict: 70% likely true
	172	Uncertainty: ±15% (moderate confidence)
	173	Reasoning: Based on 3 high-quality sources...
	174	Confidence Level: MEDIUM
	175	```
	176
	177	Acceptance Criteria:
1.2	178
1.1	179	* Verdicts include probability (0-100%)
	180	* Uncertainty explicitly quantified
	181	* Reasoning chain explains verdict
	182
	183	=== 3.6 NFR11: Quality Assurance Framework (LITE VERSION) ===
	184
	185	Main Requirement: Complete quality assurance with 7 quality gates
	186
	187	POC Implementation: 2 gates only
	188
	189	Quality Gate 1: Claim Validation
1.2	190
1.1	191	* ✅ Validates claim is factual and verifiable
	192	* ✅ Blocks non-factual claims (opinion/prediction/ambiguous)
	193	* ✅ Provides clear rejection reason
	194
	195	Quality Gate 4: Verdict Confidence Assessment
1.2	196
1.1	197	* ✅ Validates ≥2 sources found
	198	* ✅ Validates quality score ≥0.6
	199	* ✅ Blocks low-confidence verdicts
	200	* ✅ Provides clear rejection reason
	201
	202	Out of Scope (POC2+):
1.2	203
1.1	204	* ❌ Gate 2: Evidence Relevance
	205	* ❌ Gate 3: Scenario Coherence
	206	* ❌ Gate 5: Source Diversity
	207	* ❌ Gate 6: Reasoning Validity
	208	* ❌ Gate 7: Output Completeness
	209
	210	Rationale: Prove gate concept works. Add remaining gates in POC2 after validating approach.
	211
	212
	213	=== 3.7 NFR1-3: Performance, Scalability, Reliability (Basic) ===
	214
	215	Main Requirements:
1.2	216
1.1	217	* NFR1: Response time < 30 seconds
	218	* NFR2: Handle 1000+ concurrent users
	219	* NFR3: 99.9% uptime
	220
	221	POC Implementation:
1.2	222
1.1	223	* ⚠️ Response time monitored (not optimized)
	224	* ⚠️ Single-threaded processing (no concurrency)
	225	* ⚠️ Basic error handling (no advanced retry logic)
	226
	227	Rationale: POC proves functionality. Performance optimization happens in POC2.
	228
	229	POC Acceptance:
1.2	230
1.1	231	* Analysis completes (no timeout requirement)
	232	* Errors don't crash system
	233	* Basic logging in place
	234
	235	== 4. What's NOT in POC Scope ==
	236
	237	=== 4.1 User-Facing Features (Beta 0+) ===
	238
	239	{{warning}}
	240	Deferred to Beta 0:
	241	{{/warning}}
	242
	243	Out of Scope:
1.2	244
1.1	245	* ❌ User accounts and authentication (FR8)
	246	* ❌ User corrections system (FR9, FR45-46)
	247	* ❌ Public publishing interface (FR10)
	248	* ❌ Social sharing (FR11)
	249	* ❌ Email notifications (FR12)
	250	* ❌ API access (FR13)
	251
	252	Rationale: POC validates AI capabilities. User features added in Beta 0.
	253
	254
	255	=== 4.2 Advanced Features (V1.0+) ===
	256
	257	Out of Scope:
1.2	258
1.1	259	* ❌ IFCN compliance (FR47)
	260	* ❌ ClaimReview schema (FR48)
	261	* ❌ Archive.org integration (FR49)
	262	* ❌ OSINT toolkit (FR50)
	263	* ❌ Video verification (FR51)
	264	* ❌ Deepfake detection (FR52)
	265	* ❌ Cross-org sharing (FR53)
	266
	267	Rationale: Advanced features require proven platform. Added post-V1.0.
	268
	269
	270	=== 4.3 Production Requirements (POC2, Beta 0) ===
	271
	272	Out of Scope:
1.2	273
1.1	274	* ❌ Security controls (NFR4, NFR12)
	275	* ❌ Code maintainability (NFR5)
	276	* ❌ System monitoring (NFR13)
	277	* ❌ Evidence deduplication
	278	* ❌ Advanced source verification
	279	* ❌ Full 7-gate quality framework
	280
	281	Rationale: POC proves concept. Production hardening happens in POC2 and Beta 0.
	282
	283
	284	== 5. POC Output Specification ==
	285
	286	=== 5.1 Required Output Elements ===
	287
	288	For each analyzed claim, POC must produce:
	289
1.2	290	*
	291	**
	292	**1. Claim
1.1	293	* Original text
	294	* Classification (factual/non-factual/ambiguous)
	295	* If non-factual: Clear reason why
	296
	297	2. Scenarios (if factual)
1.2	298
1.1	299	* 2-3 interpretation scenarios
	300	* Each scenario clearly described
	301
	302	3. Evidence (if factual)
1.2	303
1.1	304	* Supporting evidence (2+ items)
	305	* Opposing evidence (if exists)
	306	* Source URLs and reliability scores
	307
	308	4. Verdict (if factual)
1.2	309
1.1	310	* Probability (0-100%)
	311	* Uncertainty quantification
	312	* Confidence level (LOW/MEDIUM/HIGH)
	313	* Reasoning chain
	314
	315	5. Quality Status
1.2	316
1.1	317	* Which gates passed/failed
	318	* If failed: Clear explanation why
	319
	320	=== 5.2 Example POC Output ===
	321
	322	{{code language="json"}}
	323	{
	324	"claim": {
	325	"text": "Switzerland has the highest life expectancy in Europe",
	326	"type": "factual",
	327	"gate1_status": "PASS"
	328	},
	329	"scenarios": [
	330	"Switzerland's overall life expectancy is highest",
	331	"Switzerland ranks highest for specific age groups"
	332	],
	333	"evidence": {
	334	"supporting": [
	335	{
	336	"source": "WHO Report 2023",
	337	"reliability": 0.95,
	338	"excerpt": "Switzerland: 83.4 years average..."
	339	}
	340	],
	341	"opposing": [
	342	{
	343	"source": "Eurostat 2024",
	344	"reliability": 0.90,
	345	"excerpt": "Spain leads at 83.5 years..."
	346	}
	347	]
	348	},
	349	"verdict": {
	350	"probability": 0.65,
	351	"uncertainty": 0.15,
	352	"confidence": "MEDIUM",
	353	"reasoning": "WHO and Eurostat show similar but conflicting data...",
	354	"gate4_status": "PASS"
	355	}
	356	}
	357	{{/code}}
	358
	359
	360	== 6. Success Criteria ==
	361
	362	{{success}}
	363	POC Success Definition: POC validates that AI can extract claims, find balanced evidence, and compute reasonable verdicts with quality gates improving output quality.
	364	{{/success}}
	365
	366	=== 6.1 Functional Success ===
	367
	368	POC is successful if:
	369
	370	✅ FR1-FR7 Requirements Met:
1.2	371
1.1	372	1. Extracts 3-5 factual claims from test articles
	373	2. Generates 2-3 scenarios per ambiguous claim
	374	3. Finds supporting AND opposing evidence
	375	4. Computes probabilistic verdicts with uncertainty
	376	5. Provides clear reasoning chains
	377
	378	✅ Quality Gates Work:
1.2	379
1.1	380	1. Gate 1 blocks non-factual claims (100% block rate)
	381	2. Gate 4 blocks low-quality verdicts (blocks if <2 sources or quality <0.6)
	382	3. Clear rejection reasons provided
	383
	384	✅ NFR11 Met:
1.2	385
1.1	386	1. Quality gates reduce hallucination rate
	387	2. Blocked outputs have clear explanations
	388	3. Quality metrics are logged
	389
	390	=== 6.2 Quality Thresholds ===
	391
	392	Minimum Acceptable:
1.2	393
1.1	394	* ≥70% of test claims correctly classified (factual/non-factual)
	395	* ≥60% of verdicts are reasonable (human evaluation)
	396	* Gate 1 blocks 100% of non-factual claims
	397	* Gate 4 blocks verdicts with <2 sources
	398
	399	Target:
1.2	400
1.1	401	* ≥80% claims correctly classified
	402	* ≥75% verdicts are reasonable
	403	* <10% false positives (blocking good claims)
	404
	405	=== 6.3 POC Decision Gate ===
	406
	407	After POC1, we decide:
	408
	409	✅ PROCEED to POC2 if:
1.2	410
1.1	411	* Success criteria met
	412	* Quality gates demonstrably improve output
	413	* Core workflow is technically sound
	414	* Clear path to production quality
	415
	416	⚠️ ITERATE POC1 if:
1.2	417
1.1	418	* Success criteria partially met
	419	* Gates work but need tuning
	420	* Core issues identified but fixable
	421
	422	❌ PIVOT APPROACH if:
1.2	423
1.1	424	* Success criteria not met
	425	* Fundamental AI limitations discovered
	426	* Quality gates insufficient
	427	* Alternative approach needed
	428
	429	== 7. Test Cases ==
	430
	431	=== 7.1 Happy Path ===
	432
	433	Test 1: Simple Factual Claim
1.2	434
1.1	435	* Input: "Paris is the capital of France"
1.2	436	* Expected: Factual, 1 scenario, verdict 95% true
1.1	437
	438	Test 2: Ambiguous Claim
1.2	439
1.1	440	* Input: "Switzerland has the highest income in Europe"
	441	* Expected: Factual, 2-3 scenarios, verdict with uncertainty
	442
	443	Test 3: Statistical Claim
1.2	444
1.1	445	* Input: "10% of people have condition X"
	446	* Expected: Factual, evidence with numbers, probabilistic verdict
	447
	448	=== 7.2 Edge Cases ===
	449
	450	Test 4: Opinion
1.2	451
1.1	452	* Input: "Paris is the best city"
	453	* Expected: Non-factual (opinion), blocked by Gate 1
	454
	455	Test 5: Prediction
1.2	456
1.1	457	* Input: "Bitcoin will reach $100,000 next year"
	458	* Expected: Non-factual (prediction), blocked by Gate 1
	459
	460	Test 6: Insufficient Evidence
1.2	461
1.1	462	* Input: Obscure factual claim with no sources
	463	* Expected: Blocked by Gate 4 (<2 sources)
	464
	465	=== 7.3 Quality Gate Tests ===
	466
	467	Test 7: Gate 1 Effectiveness
1.2	468
1.1	469	* Input: Mix of 10 factual + 10 non-factual claims
	470	* Expected: Gate 1 blocks all 10 non-factual (100% precision)
	471
	472	Test 8: Gate 4 Effectiveness
1.2	473
1.1	474	* Input: Claims with varying evidence availability
	475	* Expected: Gate 4 blocks low-confidence verdicts
	476
	477	== 8. Technical Architecture (POC) ==
	478
	479	=== 8.1 Simplified Architecture ===
	480
	481	POC Tech Stack:
1.2	482
1.1	483	* Frontend: Simple web interface (Next.js + TypeScript)
	484	* Backend: Single API endpoint
	485	* AI: Claude API (Sonnet 4.5)
	486	* Database: Local JSON files (no database)
	487	* Deployment: Single server
	488
	489	Architecture Diagram: See [[POC1 Specification>>FactHarbor.Specification.POC.Specification]]
	490
	491
	492	=== 8.2 AKEL Implementation ===
	493
	494	POC AKEL:
1.2	495
1.1	496	* Single-threaded processing
	497	* Synchronous API calls
	498	* No caching
	499	* Basic error handling
	500	* Console logging
	501
	502	Full AKEL (POC2+):
1.2	503
1.1	504	* Multi-threaded processing
	505	* Async API calls
	506	* Evidence caching
	507	* Advanced error handling with retry
	508	* Structured logging + monitoring
	509
	510	== 9. POC Philosophy ==
	511
	512	{{info}}
	513	Important: POC validates concept, not production readiness. Focus is on proving AI can do the job, with production quality coming in later phases.
	514	{{/info}}
	515
	516	=== 9.1 Core Principles ===
	517
1.2	518	*
	519	**
	520	**1. Prove Concept, Not Production
1.1	521	* POC validates AI can do the job
	522	* Production quality comes in POC2 and Beta 0
	523	* Focus on "does it work?" not "is it perfect?"
	524
	525	2. Implement Subset of Requirements
1.2	526
1.1	527	* POC covers FR1-7, NFR11 (lite)
	528	* All other requirements deferred
	529	* Clear mapping to [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]]
	530
	531	3. Quality Gates Validate Approach
1.2	532
1.1	533	* 2 gates prove the concept
	534	* Remaining 5 gates added in POC2
	535	* Gates must demonstrably improve quality
	536
	537	4. Iterate Based on Results
1.2	538
1.1	539	* POC results determine next steps
	540	* Decision gate after POC1
	541	* Flexibility to pivot if needed
	542
1.2	543	=== 9.2 Success ===
1.1	544
1.2	545	Clear Path Forward ===
1.1	546
	547	POC succeeds if we can confidently answer:
	548
	549	✅ Technical Feasibility:
1.2	550
1.1	551	* Can AI extract claims reliably?
	552	* Can AI find balanced evidence?
	553	* Can AI compute reasonable verdicts?
	554
	555	✅ Quality Approach:
1.2	556
1.1	557	* Do quality gates improve output?
	558	* Can we measure and track quality?
	559	* Is the gate approach scalable?
	560
	561	✅ Production Path:
1.2	562
1.1	563	* Is the core architecture sound?
	564	* What needs improvement for production?
	565	* Is POC2 the right next step?
	566
	567	== 10. Related Pages ==
	568
	569	* [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]] - Full system requirements (this POC implements a subset)
	570	* [[POC1 Specification (Detailed)>>FactHarbor.Specification.POC.Specification]] - Detailed POC1 technical specs
	571	* [[POC Summary>>FactHarbor.Specification.POC.Summary]] - High-level POC overview
	572	* [[Implementation Roadmap>>FactHarbor.Roadmap.WebHome]] - POC1, POC2, Beta 0, V1.0 phases
	573	* [[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]] - What users need (drives requirements)
	574
	575	Document Owner: Technical Team
	576	Review Frequency: After each POC iteration
	577	Version History:
1.2	578
1.1	579	* v1.0 - Initial POC requirements
	580	* v2.0 - Updated after specification cross-check
	581	* v3.0 - Aligned with Main Requirements (FR/NFR IDs added)

Wiki source code of POC Requirements (POC1 & POC2)

Applications

Navigation

Need help?