File size: 17,916 Bytes
2e90048
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
import gradio as gr
import spaces
import torch
import requests
import feedparser
import trafilatura
import plotly.express as px
import pandas as pd
import html
import re

from urllib.parse import urlparse, quote_plus
from transformers import (
    AutoTokenizer,
    AutoModelForSequenceClassification
)

# =====================================================
# 1. CONFIGURATION
# =====================================================

APP_NAME = "TruthLens AI"

MODEL_NAME = "cross-encoder/nli-deberta-v3-small"

HEADERS = {
    "User-Agent": "TruthLensAI/1.0 Educational Project"
}

LABELS = [
    "Contradicts",
    "Supports",
    "Unclear"
]

# =====================================================
# 2. LOAD HUGGING FACE MODEL
# =====================================================

# Load on CPU first.
# GPU is used only inside the ZeroGPU function below.

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

model = AutoModelForSequenceClassification.from_pretrained(
    MODEL_NAME
)

model.eval()

# =====================================================
# 3. EXTRACT NEWS ARTICLE
# =====================================================

def extract_article(url):

    parsed = urlparse(url)

    if parsed.scheme not in ["http", "https"]:
        raise ValueError("Enter a valid HTTP or HTTPS URL.")

    if not parsed.hostname:
        raise ValueError("Invalid website address.")

    if parsed.hostname.lower() in [
        "localhost",
        "127.0.0.1",
        "::1"
    ]:
        raise ValueError("This website address is not allowed.")

    response = requests.get(
        url,
        headers=HEADERS,
        timeout=20,
        stream=True
    )

    response.raise_for_status()

    if int(response.headers.get("Content-Length", 0)) > 4_000_000:
        raise ValueError("Article page is too large.")

    content = response.raw.read(4_000_000)

    response.close()

    text = trafilatura.extract(content)

    metadata = trafilatura.extract_metadata(content)

    if not text:
        raise ValueError(
            "Could not extract article. "
            "The website may block automatic access."
        )

    title = (
        metadata.title
        if metadata and metadata.title
        else text[:150]
    )

    return title, text[:10000]


# =====================================================
# 4. SEARCH GOOGLE NEWS RSS
# =====================================================

def search_news(claim):

    rss_url = (
        "https://news.google.com/rss/search?q="
        + quote_plus(claim)
        + "&hl=en-IN&gl=IN&ceid=IN:en"
    )

    response = requests.get(
        rss_url,
        headers=HEADERS,
        timeout=20
    )

    response.raise_for_status()

    feed = feedparser.parse(response.content)

    sources = []
    seen = set()

    for entry in feed.entries[:30]:

        source_info = entry.get("source", {})

        publisher = source_info.get(
            "title", "Unknown publisher"
        )

        publisher_url = source_info.get("href", "")

        link = entry.get("link", "")

        domain = (
            urlparse(publisher_url).netloc
            if publisher_url
            else urlparse(link).netloc
        )

        domain = domain.lower().replace("www.", "")

        if not domain or domain in seen:
            continue

        if urlparse(link).scheme not in ["http", "https"]:
            continue

        seen.add(domain)

        summary = re.sub(
            r"<[^>]*>", " ",
            entry.get("summary", "")
        )

        summary = html.unescape(summary)

        title = entry.get("title", "")

        evidence = title + ". " + summary

        sources.append({
            "publisher": publisher,
            "domain": domain,
            "title": title,
            "link": link,
            "evidence": evidence[:1800]
        })

        if len(sources) >= 8:
            break

    return sources


# =====================================================
# 5. AI FACT CHECKING USING HUGGING FACE
# =====================================================

@spaces.GPU(duration=120)
def analyse_evidence(claim, sources):

    results = []

    # Move the model to GPU only during this function.
    model.to("cuda")

    try:

        for source in sources:

            evidence = source["evidence"]

            # Premise = evidence
            # Hypothesis = news claim

            inputs = tokenizer(
                evidence,
                claim,
                return_tensors="pt",
                truncation=True,
                max_length=384
            )

            inputs = {
                key: value.to("cuda")
                for key, value in inputs.items()
            }

            with torch.inference_mode():

                output = model(**inputs)

                probabilities = torch.softmax(
                    output.logits,
                    dim=-1
                )[0]

            scores = probabilities.cpu().tolist()

            # Model label order:
            # 0 = contradiction
            # 1 = entailment
            # 2 = neutral

            contradiction = scores[0]
            support = scores[1]
            unclear = scores[2]

            if support >= 0.45 and support > contradiction:

                verdict = "Supports"
                confidence = support

            elif (
                contradiction >= 0.45
                and contradiction > support
            ):

                verdict = "Contradicts"
                confidence = contradiction

            else:

                verdict = "Unclear"
                confidence = unclear

            results.append({
                **source,
                "verdict": verdict,
                "confidence": round(confidence * 100, 1)
            })

    finally:

        # Return model to CPU after analysis.
        model.to("cpu")

        if torch.cuda.is_available():
            torch.cuda.empty_cache()

    return results


# =====================================================
# 6. CALCULATE FINAL VERDICT
# =====================================================

def calculate_verdict(results):

    counts = {
        "Supporting": 0,
        "Contradicting": 0,
        "Unclear": 0
    }

    for item in results:

        if item["verdict"] == "Supports":
            counts["Supporting"] += 1

        elif item["verdict"] == "Contradicts":
            counts["Contradicting"] += 1

        else:
            counts["Unclear"] += 1

    total = len(results)

    if total == 0:

        return "NON-VERIFIABLE", {
            "Supporting": 0,
            "Contradicting": 0,
            "Unclear": 100
        }

    percentages = {
        key: round(value / total * 100, 1)
        for key, value in counts.items()
    }

    if total < 3:

        verdict = "NON-VERIFIABLE"

    elif percentages["Supporting"] >= 60:

        verdict = "LIKELY TRUE"

    elif percentages["Contradicting"] >= 60:

        verdict = "LIKELY FALSE"

    else:

        verdict = "NON-VERIFIABLE"

    return verdict, percentages


# =====================================================
# 7. CREATE PERCENTAGE GRAPH
# =====================================================

def create_graph(percentages):

    df = pd.DataFrame({
        "Category": list(percentages.keys()),
        "Percentage": list(percentages.values())
    })

    fig = px.bar(
        df,
        x="Category",
        y="Percentage",
        color="Category",
        text="Percentage",
        range_y=[0, 110],
        color_discrete_map={
            "Supporting": "#22C55E",
            "Contradicting": "#EF4444",
            "Unclear": "#F59E0B"
        },
        title="Evidence Distribution"
    )

    fig.update_traces(
        texttemplate="%{text}%",
        textposition="outside"
    )

    fig.update_layout(
        template="plotly_dark",
        paper_bgcolor="#111827",
        plot_bgcolor="#111827",
        font_color="white",
        showlegend=False,
        yaxis_title="Percentage of sources",
        xaxis_title=""
    )

    return fig


# =====================================================
# 8. DISPLAY SOURCE CARDS
# =====================================================

def create_source_cards(results):

    if not results:
        return "<h3>No matching sources found.</h3>"

    cards = ""

    for item in results:

        if item["verdict"] == "Supports":
            color = "#22C55E"

        elif item["verdict"] == "Contradicts":
            color = "#EF4444"

        else:
            color = "#F59E0B"

        publisher = html.escape(item["publisher"])
        title = html.escape(item["title"])
        domain = html.escape(item["domain"])
        link = html.escape(item["link"], quote=True)

        cards += f"""
        <div style="
            background:#1F2937;
            border:1px solid #374151;
            border-left:5px solid {color};
            border-radius:14px;
            padding:18px;
            margin-bottom:14px;
        ">

            <div style="
                display:flex;
                justify-content:space-between;
                flex-wrap:wrap;
                gap:10px;
            ">

                <b style="color:white;font-size:16px">
                    {publisher}
                </b>

                <b style="color:{color}">
                    {item['verdict'].upper()}
                </b>

            </div>

            <p style="color:#D1D5DB">
                {title}
            </p>

            <small style="color:#9CA3AF">
                {domain} |
                Model confidence: {item['confidence']}%
            </small>

            <br><br>

            <a href="{link}"
               target="_blank"
               rel="noopener noreferrer"
               style="color:#60A5FA">
                Read original report β†’
            </a>

        </div>
        """

    return cards


# =====================================================
# 9. MAIN NEWS ANALYSIS
# =====================================================

def run_analysis(url, custom_claim, progress=gr.Progress()):

    try:

        if not url or not url.strip():

            raise ValueError(
                "Please enter a news article URL."
            )

        progress(0.1, desc="Extracting news article...")

        title, article = extract_article(url)

        claim = (
            custom_claim.strip()
            if custom_claim and custom_claim.strip()
            else title
        )

        progress(0.3, desc="Searching news sources...")

        sources = search_news(claim)

        if not sources:

            percentages = {
                "Supporting": 0,
                "Contradicting": 0,
                "Unclear": 100
            }

            return (
                f"## πŸ“° {title}\n\n{article[:1500]}",
                "<h2 style='color:#F59E0B'>NON-VERIFIABLE</h2>"
                "<p>No matching independent reports were found.</p>",
                create_graph(percentages),
                "<p>No sources found.</p>",
                "Insufficient evidence to verify this news."
            )

        progress(
            0.5,
            desc="AI is comparing evidence from publishers..."
        )

        results = analyse_evidence(
            claim,
            sources
        )

        progress(0.85, desc="Generating final report...")

        verdict, percentages = calculate_verdict(results)

        graph = create_graph(percentages)

        source_cards = create_source_cards(results)

        if verdict == "LIKELY TRUE":

            color = "#22C55E"
            explanation = "Most collected sources support the claim."

        elif verdict == "LIKELY FALSE":

            color = "#EF4444"
            explanation = "Most collected sources contradict the claim."

        else:

            color = "#F59E0B"
            explanation = "Available evidence is insufficient or mixed."

        report = f"""
        <div style="
            background:#111827;
            border:1px solid #374151;
            padding:24px;
            border-radius:16px;
        ">

            <p style="color:#9CA3AF">
                FINAL VERDICT
            </p>

            <h1 style="
                color:{color};
                font-size:32px;
            ">
                {verdict}
            </h1>

            <p style="color:#D1D5DB">
                {explanation}
            </p>

            <hr style="border-color:#374151">

            <div style="
                display:flex;
                justify-content:space-around;
                flex-wrap:wrap;
                gap:18px;
            ">

                <div>
                    <h2 style="color:#22C55E">
                        {percentages['Supporting']}%
                    </h2>
                    <small>Supporting</small>
                </div>

                <div>
                    <h2 style="color:#EF4444">
                        {percentages['Contradicting']}%
                    </h2>
                    <small>Contradicting</small>
                </div>

                <div>
                    <h2 style="color:#F59E0B">
                        {percentages['Unclear']}%
                    </h2>
                    <small>Unclear</small>
                </div>

            </div>

        </div>
        """

        summary = f"""
### AI Analysis Report

**Claim analysed:** {claim}

**Sources collected:** {len(results)}

**AI model:** DeBERTa Natural Language Inference

**Evidence distribution:**

- Supporting: {percentages['Supporting']}%
- Contradicting: {percentages['Contradicting']}%
- Unclear: {percentages['Unclear']}%

### Important limitations

The percentages represent the distribution of source assessments,
NOT the probability that the news is true.

The system searches Google News RSS and does not cover
the entire internet.

Publishers may repeat the same original report, so their
coverage is not necessarily independent.

AI predictions can be incorrect. Always check the
original reports before accepting a verdict.
"""

        progress(1.0, desc="Verification complete!")

        return (
            f"## πŸ“° {title}\n\n{article[:1800]}",
            report,
            graph,
            source_cards,
            summary
        )

    except Exception as error:

        error_message = html.escape(str(error))

        return (
            "## Article Analysis",
            f"""
            <h2 style="color:#F59E0B">
                NON-VERIFIABLE
            </h2>
            <p>{error_message}</p>
            """,
            create_graph({
                "Supporting": 0,
                "Contradicting": 0,
                "Unclear": 100
            }),
            "<p>Source information unavailable.</p>",
            "Please check the URL and try again."
        )


# =====================================================
# 10. GRADIO DESIGN
# =====================================================

CUSTOM_CSS = """
.gradio-container {
    max-width: 1150px !important;
    margin: auto !important;
}

#analyze-button {
    background: linear-gradient(90deg,#2563EB,#7C3AED);
    color: white;
    border: none;
}

#main-header {
    text-align: center;
    padding: 25px 10px;
}

#main-header h1 {
    font-size: 42px;
    background: linear-gradient(90deg,#60A5FA,#A78BFA);
    -webkit-background-clip: text;
    color: transparent;
}

"""

with gr.Blocks(
    theme=gr.themes.Soft(
        primary_hue="blue",
        secondary_hue="purple",
        neutral_hue="slate"
    ),
    css=CUSTOM_CSS,
    title="TruthLens AI"
) as demo:

    # HEADER

    gr.HTML("""
    <div id="main-header">

        <div style="font-size:48px">
            πŸ”Ž
        </div>

        <h1>
            TRUTHLENS AI
        </h1>

        <p style="
            color:#94A3B8;
            font-size:17px;
        ">
            BEYOND HEADLINES. TOWARDS TRUTH.
        </p>

        <p style="color:#64748B">
            AI-powered multi-source news verification
        </p>

    </div>
    """)

    # INPUT AREA

    with gr.Group():

        gr.Markdown("## πŸ”— Verify a News Article")

        url_input = gr.Textbox(
            label="News Article URL",
            placeholder="Paste your news article link here..."
        )

        claim_input = gr.Textbox(
            label="Specific claim (optional)",
            placeholder="Enter a specific statement to verify, or leave blank to use the headline.",
            lines=2
        )

        analyze_button = gr.Button(
            "πŸ” ANALYSE NEWS",
            variant="primary",
            elem_id="analyze-button"
        )

    gr.Markdown("---")

    # ARTICLE

    article_output = gr.Markdown(
        label="Extracted News Article"
    )

    # DASHBOARD

    gr.Markdown("## πŸ“Š Verification Dashboard")

    verdict_output = gr.HTML()

    graph_output = gr.Plot(
        label="Evidence Percentage Graph"
    )

    # SOURCES

    gr.Markdown("## 🌐 News Sources")

    source_output = gr.HTML()

    # AI REPORT

    gr.Markdown("## 🧠 AI Analysis Report")

    summary_output = gr.Markdown()

    # FOOTER

    gr.HTML("""
    <div style="
        text-align:center;
        padding:25px;
        color:#64748B;
    ">

        <b>TRUTHLENS AI</b>

        <p>
            An educational artificial intelligence project.
        </p>

        <small>
            AI-assisted results are not guaranteed factual conclusions.
        </small>

    </div>
    """)

    # BUTTON ACTION

    analyze_button.click(
        fn=run_analysis,
        inputs=[
            url_input,
            claim_input
        ],
        outputs=[
            article_output,
            verdict_output,
            graph_output,
            source_output,
            summary_output
        ]
    )

demo.queue().launch()