Hugging Face's logo

Spaces:
Mirageinv
/
Article_classifier
Running

App Files Community
Mirageinv commited on
Commit
0bfbe31
·
1 Parent(s): fb5a03f

Added task

Browse files
Files changed (5) hide show
  1. app.py +63 -0
  2. checkpoints/epoch_8.pt +3 -0
  3. checkpoints/labels_info.json +1 -0
  4. requirements.txt +3 -0
  5. transformer_hug_face.ipynb +423 -0
app.py ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import json
2
+ import streamlit as st
3
+ import torch
4
+ import torch.nn.functional as F
5
+ from transformers import AutoTokenizer, DistilBertForSequenceClassification
6
+
7
+ CHECKPOINT_PATH = "checkpoints/epoch_8.pt"
8
+ LABELS_PATH = "checkpoints/labels_info.json"
9
+
10
+ with open(LABELS_PATH, 'r') as f:
11
+ LABELS = json.load(f)
12
+
13
+ print(len(LABELS))
14
+ BASE_MODEL = "distilbert-base-cased"
15
+
16
+ @st.cache_resource
17
+ def load_model():
18
+ tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
19
+ # The same model
20
+ model = DistilBertForSequenceClassification.from_pretrained(BASE_MODEL, num_labels=len(LABELS))
21
+ state_dict = torch.load(CHECKPOINT_PATH, map_location=torch.device('cpu'))
22
+ model.load_state_dict(state_dict)
23
+ model.eval()
24
+
25
+ return tokenizer, model
26
+
27
+ tokenizer, model = load_model()
28
+
29
+ st.title("Классификация научных статей по тематике")
30
+ st.write("Введите название и аннотацию статьи для предсказания её тематики по таксономии arxiv.org")
31
+
32
+ title = st.text_input("Название статьи:")
33
+ abstract = st.text_area("Аннотация (abstract):")
34
+
35
+ if st.button("Классифицировать"):
36
+ if not title and not abstract:
37
+ st.warning("Введите хотя бы название статьи.")
38
+ else:
39
+ text = title if not abstract else f"{title} {abstract}"
40
+
41
+ inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=256)
42
+
43
+ with torch.no_grad():
44
+ outputs = model(**inputs)
45
+ probs = F.softmax(outputs.logits, dim=1).squeeze()
46
+
47
+ label_probs = [(label, prob.item()) for label, prob in zip(list(LABELS.values()), probs)]
48
+
49
+ # Sorting for getting 95% afterwards
50
+ label_probs.sort(key=lambda x: x[1], reverse=True)
51
+
52
+ cumulative = 0.0
53
+ top_labels = []
54
+ for label, prob in label_probs:
55
+ cumulative += prob
56
+ top_labels.append((label, prob))
57
+ if cumulative >= 0.95:
58
+ break
59
+
60
+ # Вывод
61
+ st.subheader("Наиболее вероятные тематики (суммарно ≥95%):")
62
+ for label, prob in top_labels:
63
+ st.write(f"**{label}** — {prob * 100:.2f}%")
checkpoints/epoch_8.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44188202ad76c8dbcb1d336d120d9de85b1a0b3ae08bb8b691b2d9704216a395
3
+ size 270220194
checkpoints/labels_info.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": "(Primary) 62H30, 65Kxx (Secondary)", "1": "00", "2": "00-01, 99-00", "3": "00A72", "4": "01-02 (Primary) 68T15, 03B35 (Secondary)", "5": "03", "6": "03-03, 01A45", "7": "03A05, 03B42, 03B48", "8": "03Axx, 03Bxx, 03B15, 68T15", "9": "03B-02, 68U02", "10": "03B15", "11": "03B35, 68T15, 68T27", "12": "03B42", "13": "03B47", "14": "03B47 (Primary) 68Q32, 68T50, 03B65 (Secondary)", "15": "03B52, 03B50, 03B80", "16": "03B52, 03C05, 03G10", "17": "03B52, 03E72, 97M10, 97M99", "18": "03B52, 68P20, 06A15", "19": "03B52, 78M50, 68T27, 68T05, 68T20", "20": "03B52, 92B20, 68T05", "21": "03B60, 03B15, 68T27, 68T30, 68T15", "22": "03B65", "23": "03B65, 03B15, 03B40, 68T50, 68N18", "24": "03B65, 03G10, 68M11, 68P05, 68Q55, 68T30, 68U35", "25": "03B65, 91F20", "26": "03B70 (Primary) 68T27 (Secondary)", "27": "03Cxx", "28": "03E72", "29": "03E72, 03B52, 94D05, 26E60", "30": "03E72, 16D25", "31": "03E72, 97A99", "32": "03E72, 97C30", "33": "03E99, 06F30, 03C90", "34": "03F20", "35": "03Fxx", "36": "03G10 68P05 68T01", "37": "03G10 68T27", "38": "03G25, 03B50", "39": "05-04", "40": "05B35", "41": "05C50, 05C70, 15A18, 58C40, 65F15, 65N25, 62H30, 91C20", "42": "05C50, 15A18, 62H30, 90C59", "43": "05C51, 90B, 97M, 68R, 68T", "44": "05C69, 68R10", "45": "05C85", "46": "05C85, 68R10, 90B15, 90C35", "47": "05C90, 68R10, 97K30", "48": "05D40, 60C05", "49": "06Axx, 03G25, 03B60, 08B20, 68U35", "50": "06B99, 62H30", "51": "06E30, 68Q17, 68R01, 68T01, 68T27", "52": "1.2.0", "53": "1.2.6", "54": "1.2.7", "55": "11Kxx", "56": "11N36, 11Y16, 68G05, 62H30", "57": "11Z05", "58": "13Pxx, 14Qxx (Primary), 15A69, 15A72, 68T45 (Secondary)", "59": "14H50, 14Q05, 68T45", "60": "14J26", "61": "14J30 (Primary)", "62": "14J40, 14J70, 14M15, 62M10", "63": "14J60 (Primary) 14F05, 14J26 (Secondary)", "64": "14N, 14Q, 68", "65": "14T05, 52B05", "66": "15A04", "67": "15A18 58B10", "68": "15A23, 15A42, 15A45, 15B10", "69": "15A29, 65F22, 65K10, 68U10, 90C25, 90C46", "70": "15A29, 65H10, 90C26", "71": "15A66, 42A38", "72": "15A69", "73": "15A80 (Primary), 20M99, 65F99, 65K10, 68N19, 65G30, 68W10, 68N30\n (Secondary), 68Q65, 49M99, 12K10", "74": "15A83", "75": "15A83, 15A23, 40C05, 65F30", "76": "16B50, 18A10, 68T50", "77": "18D10", "78": "18D20, 06B23", "79": "18Dxx, 18Axx", "80": "1D30", "81": "20B40", "82": "20E05, 20F05, 68T05 (Primary) 57M05,57M20", "83": "20F28, 68Q17, 68T05", "84": "22A05, 22A30, 57M50, 57N65, 57R19", "85": "26A33", "86": "26B30, 49Q20, 65J20", "87": "28A78, 28A80", "88": "28A80, 68U10, 94A08", "89": "28E10", "90": "34F05, 60G99", "91": "35A15, 65D19, 35J05", "92": "35D40, 49L25, 65N06, 06A07, 35F21, 68Q87", "93": "35K57", "94": "35P30, 62H35, 65M70, 94A08", "95": "35Q68", "96": "35R30, 62G05, 62G35", "97": "35R30, 74D99, 92C55", "98": "37A25, 94A17", "99": "37B15, 68Q80", "100": "37D45, 90C27, 68Q10, 68Q17, 34G20", "101": "37M10, 46E22, 68U10, 65D19, 62H30, 68T10", "102": "37N99", "103": "41A15, 65D07", "104": "41A25, 41A10, 82C32, 41A46, 68T05, 94A34", "105": "41A30, 41A63, 65D15, 68T05, 92B20", "106": "41A30, 65D15, 92B20", "107": "41A35, 46E30, 47A58, 47B38, 94A12", "108": "41A46 (Primary); 94A08 (Secondary)", "109": "41A60, 62G07, 42B10", "110": "41A99, 65D15", "111": "42A16", "112": "42C40, 68U10, 65D15", "113": "43A32", "114": "46E22, 62G10", "115": "46N10, 68U10, 94A08, 47A52", "116": "47G20", "117": "47N10, 35A15, 49N45, 65M20, 65J22, 68U10, 94A12, 65D18", "118": "47N30", "119": "47N30, 65K10", "120": "49D10, 60J70, 91F20", "121": "49J15", "122": "49J40, 53A05, 68U99, 68T10", "123": "49J40, 94A08, 68U10, 35K55", "124": "49J45, 65Y05, 90C59, 93D99", "125": "49J55, 49J45, 60D05, 68R10, 62G20", "126": "49J55, 49J45, 62G20, 35J20, 65N12", "127": "49K20, 65Y05, 65M32, 65K10, 76D55, 68U10, 35M10", "128": "49L20, 90C39, 82C32", "129": "49M15, 65C60, 65K05, 90C06", "130": "49M15, 65K05, 90C06, 90C25, 90C51", "131": "49M25, 65D10, 62G99, 65D18, 65K10, 49Q20", "132": "49M30; 80M50", "133": "49M99", "134": "49M99 (primary), 90C90, 90C25, 49N45 (secondary)", "135": "49N45, 68T45, 68U10", "136": "49Q10, 62H35", "137": "51A05", "138": "51K05, 68P01", "139": "51N10", "140": "53A20, 53A45, 42C15, 28C15", "141": "53A55, 14L24, 14H50, 68T45", "142": "55-XX,", "143": "55P10, 55Q05", "144": "57-04", "145": "57M60 (Primary), 37E99, 57N35 (Secondary)", "146": "60-04", "147": "60-04, 60-08, 60J10 60J20", "148": "6006", "149": "60B20", "150": "60C05, 60F15", "151": "60D05", "152": "60E10, 62Gxx, 62Exx, 62H12, 42Bxx, 46E22", "153": "60E15, 60G17 (Primary), 60G40, 60G42, 60G44 (Secondary)", "154": "60F15, 62M5", "155": "60G15", "156": "60G15 (Primary) 58E30, 62-09", "157": "60G15 (Primary), 58E30", "158": "60G15 (Primary), 62-09, 58E30", "159": "60G15 62M30 62G08 12H05 68W30 13P10 13P20 13J30 13P25 60B11 35Q61", "160": "60G15, 58E30", "161": "60G15, 62H12, 62M99", "162": "60G15, 62K05, 65D18", "163": "60G15, 68M11, 97R40", "164": "60G25", "165": "60G35, 15A66", "166": "60G40, 60J10, 68W20, 68W40", "167": "60G55, 60G15, 62F15, 62M30, 62H11", "168": "60J10 (Primary) 92D15 (Secondary)", "169": "60J20, 61E40, 65C50", "170": "60J20, 65C60, 62M05, 60G35, 94A12, 94A05, 90C39", "171": "60J22, 65C40", "172": "60J28, 62P10, 68T05, 62G86, 90B22", "173": "60J60, 62-04, 62E17, 60E15, 65C60 (Primary) 62-07, 65C05, 68T05\n (Secondary)", "174": "60J70", "175": "60K35", "176": "60K35, 60K35 (Primary), 60K35 (Secondary)", "177": "60K99, 68T05, 68R05", "178": "62", "179": "62, 62F, 62H30, 62h", "180": "62-01", "181": "62-04", "182": "62-07", "183": "62-07, 00A66", "184": "62-07, 60G10, 62M10", "185": "62-07, 62-09, 68T50, 03B52, 03E72", "186": "62-07, 62H25, 62H30", "187": "62-07, 62H30, 97N80, 65C10", "188": "62-07, 62H99", "189": "62-07, 62Jxx", "190": "62-07, 92C50", "191": "62-07, 93B50", "192": "62-09, 62H15, 62C05", "193": "62-XX", "194": "62-XX, 62Fxx, 62F15, 62H30", "195": "62-XX, 62H30, 62H12, 62-07, 62Fxx", "196": "62A01", "197": "62A86", "198": "62A86, 62H30, 62G30", "199": "62B10, 94A15, 94A17, 68W10, 68W15, 68W20", "200": "62C05 (Primary) 62G05, 62G08 (Secondary)", "201": "62C05, 62P25", "202": "62C10", "203": "62C10, 62C10, 46N30", "204": "62C10, 62F15, 94A12, 62H30", "205": "62C86 (Decision theory and fuzziness)", "206": "62D05", "207": "62E10, 14M07, 14M25, 51M20", "208": "62F07 (Primary) 62C12, 62J05 (Secondary)", "209": "62F07, 05C40, 49N45,", "210": "62F07, 06A07, 90C27", "211": "62F10, 62F15", "212": "62F10, 62F15, 68W40", "213": "62F10, 68W40", "214": "62F12, 62H30, 90B15, 15A23", "215": "62F15", "216": "62F15 (Primary), 68T37 (Secondary)", "217": "62F15, 60J20", "218": "62F30, 62F30 (Primary) 62H12 (Secondary)", "219": "62F35, 65K10", "220": "62F35, 65K10, 49M15", "221": "62F40, 62G90, 62M10, 62M20, 62M45, 62M15, 68T05, 68T10", "222": "62F99 (Primary); 82-08 (Secondary)", "223": "62FXX, 65KXX", "224": "62G05", "225": "62G05, 62F15", "226": "62G05, 62G20, 62G32 (Primary), 62C20, 62E10, 62N99 (Secondary)", "227": "62G07", "228": "62G07, 62H30", "229": "62G08", "230": "62G08, 46E22, 47B32", "231": "62G08, 62F12 (Primary), 62J07 (Secondary)", "232": "62G08, 62G07, 62H05, 68T10", "233": "62G08, 62G09, 62G20, 62G86", "234": "62G08, 62G15", "235": "62G08, 62G20, 62G35", "236": "62G08, 62G20, 62M10", "237": "62G09", "238": "62G10", "239": "62G15", "240": "62G20", "241": "62G20, 62G05, 62A01", "242": "62G20, 68Q32, 86W32", "243": "62G35 (Primary), 62K05, 60G15 (Secondary)", "244": "62G35, 62H30", "245": "62G99, 46E22, 62G08", "246": "62G99; 94A99", "247": "62H05, 60E05, 68T30", "248": "62H12", "249": "62H12, 47N30, 65C60", "250": "62H12, 62H30, 62B10", "251": "62H12, 62J99, 15A83", "252": "62H12, 94A15, 15A69", "253": "62H17 (Primary), 62M40", "254": "62H17, 62M40", "255": "62H20, 62M20, 62B10, 60G25, 68T05, 90B15, 05C82", "256": "62H25", "257": "62H25, 62.07", "258": "62H25, 62H30", "259": "62H25, 68T10", "260": "62H30", "261": "62H30 (Primary) 62F05, 62J12 (Secondary)", "262": "62H30 (Primary) 68T10 (Secondary)", "263": "62H30 and 90C22", "264": "62H30, 60G55", "265": "62H30, 62F10", "266": "62H30, 62G05, 68T10", "267": "62H30, 62G07", "268": "62H30, 62G20", "269": "62H30, 62G20, 49J55, 91C20, 68R10, 60D05", "270": "62H30, 62M45, 91C20", "271": "62H30, 62P10, 62L12", "272": "62H30, 65F15, 65F20, 65F22", "273": "62H30, 68H05", "274": "62H30, 68P01", "275": "62H30, 68P01, 6207", "276": "62H30, 68T05, 62B10 (Primary)", "277": "62H30, 68T05, 65K10", "278": "62H30, 68T10", "279": "62H30, 91C20", "280": "62H30, 91C20, 62-07, 68T10", "281": "62H30, 91C20, 68P15, 68T05", "282": "62H30, 91C20, 94A08", "283": "62H35", "284": "62H35, 62M40, 65K10, 68U10", "285": "62H35, 65K05, 68U10, 62M40", "286": "62H35, 65N22, 65N55, 74G65, 74G75", "287": "62H35, 65T60, 58J65, 37L05", "288": "62H35, 68U10, 62F15, 68Q32", "289": "62J, 90C25, 49M29, 90C11, 15A83", "290": "62J02", "291": "62J02, 62G08, 68T05", "292": "62J05, 62G05, 62F15", "293": "62J05, 62H12", "294": "62J05, 62J07, 41A25, 49M15, 68Q32", "295": "62J05, 62J07, 90C25", "296": "62J05, 90C25, 90C06", "297": "62J07", "298": "62J07 (Primary) 69J99 (Secondary)", "299": "62J07 (primary)", "300": "62J07, 62F07", "301": "62J07, 62P10", "302": "62J10 (Primary), 62-09, 62H25", "303": "62J99", "304": "62J99, 81P50, 62H12", "305": "62K05", "306": "62L05", "307": "62L10", "308": "62L20", "309": "62L20, 62L12, 90C99", "310": "62M09, 62P99, 68T50, 91F20, 03B65, 91E40, 60J20", "311": "62M10, 91F20", "312": "62M15, 90B22, 60G55", "313": "62M20 (Primary) 91B84, 62G99 (Secondary)", "314": "62M45", "315": "62M45, 62M10, 68T05", "316": "62M45, 68Q32", "317": "62M45, 68T50", "318": "62M45, 82C32, 92B20", "319": "62N02, 62G05", "320": "62N05, 90B25", "321": "62P10", "322": "62P10, 62F15", "323": "62P30, 68T05", "324": "62P35", "325": "63P99, 91D30", "326": "65-XX", "327": "65B99, 52A99, 60G99, 62L20", "328": "65B99, 90C59", "329": "65C20, 65C40, 65C05, 62P30", "330": "65C40, 62M05", "331": "65C60", "332": "65C60, 65K05, 65Y20, 90C06, 90C20, 90C25", "333": "65C60, 90C25, 68T05", "334": "65C99", "335": "65C99, 65M99, 60H30, 65-05", "336": "65D05, 68T99, 65F50", "337": "65D10 (primary), 51K05 (secondary)", "338": "65D18, 58D10, 49Q10", "339": "65D18, 65J22, 68U10, 68Q32", "340": "65D18, 65M80", "341": "65D18, 68W05", "342": "65D19", "343": "65D19, 65T60, 11K70, 62H30", "344": "65F10, 68U10, 62H35", "345": "65F22", "346": "65F22, 65F50, 94A08", "347": "65F22, 65K10", "348": "65F30", "349": "65F35", "350": "65F99", "351": "65J20, 94A08, 49N45, 49N30", "352": "65K02", "353": "65K05, 65K10, 90C25, 90C31", "354": "65K05, 68W25", "355": "65K05, 90-08, 90C06, 90C25, 90C90", "356": "65K05, 90C15, 90C90", "357": "65K05, 90C30, 90C90, 93B30", "358": "65K10", "359": "65K10, 65K05", "360": "65K10, 65Y05, 68W10, 68W20", "361": "65K10, 68U10", "362": "65K10, 68W40, 68Q32", "363": "65K10, 90C06, 62F35, 47N30", "364": "65K10, 90C25", "365": "65K10, 90C26, 49M37 (Primary)", "366": "65Kxx, 65Nxx", "367": "65Kxx, 65Yxx", "368": "65L05, 65L10, 58D17", "369": "65M22 (Primary) 68N15, 68N18, 65K10 (Secondary)", "370": "65M75, 60H35, 65C30", "371": "65N06", "372": "65N06, 65N22, 68U10", "373": "65N99, 90C25, 97N50", "374": "65Nxx", "375": "65T60", "376": "68", "377": "68 Computer Science", "378": "68, 81, 92", "379": "68, 92", "380": "68-01", "381": "68-02", "382": "68-04", "383": "68-06", "384": "68-42, 68-20, 68-35", "385": "68-45", "386": "68-XX", "387": "68.U99", "388": "68745", "389": "68M12, 68M14, 62M45, 68T05", "390": "68N01, 68T50", "391": "68N17", "392": "68N99", "393": "68P10, 68P20, 68Q87", "394": "68P15 (Primary), 68T27 (Secondary)", "395": "68P20", "396": "68P20, 06B99, 68T30", "397": "68P20, 68T30, 03B52", "398": "68P20, 68Txx", "399": "68P25, 94A60", "400": "68P30, 58C05, 94A12, 94A08, 68T05, 90C26, 90C48, 90C55", "401": "68P30, 94A45", "402": "68Q01", "403": "68Q01, 68Q32 68Txx", "404": "68Q05", "405": "68Q05, 68Q10, 68Q17", "406": "68Q05, 68Q45, 68Q70, 68Q85, 68T37, 03E72, 15B15", "407": "68Q05, 68Q45, 68Q70, 68Q85, 68T37, 03E72, 15B15,", "408": "68Q10", "409": "68Q12", "410": "68Q15", "411": "68Q17", "412": "68Q17, 68Q10, 68W30", "413": "68Q25, 68Q32, 68T05, 68W25, 68W40", "414": "68Q25, 68W25, 68Q32, 68T05", "415": "68Q32", "416": "68Q32 (Primary) 68T05, 37A99 (Secondary)", "417": "68Q32 (Primary) 68T05, 62M20, 60G25, 62J07, 62G08, 62F15 (Secondary)", "418": "68Q32, 68Q05, 68T05, 68Q10, 62P10, 97M60, 92D15, 91A80", "419": "68Q32, 68Q45, 68T15", "420": "68Q32, 68T05, 62J05, 90C25", "421": "68Q32, 68T05, 91A60, 91A20", "422": "68Q32, 68T05, 97C30, 46N30", "423": "68Q32, 68T27", "424": "68Q32: Computational learning theory", "425": "68Q42", "426": "68Q45", "427": "68Q55", "428": "68Q55, 14M15", "429": "68Q60, 03B70, 68T27", "430": "68Q85", "431": "68Q87", "432": "68R", "433": "68R05", "434": "68R10", "435": "68R99", "436": "68T-06, 94C-06", "437": "68T00", "438": "68T01", "439": "68T01, 62H35", "440": "68T01, 68Q05", "441": "68T01, 68T05, 68T10, 68T50, 68U15", "442": "68T01, 68T05, 68T35, 68T50", "443": "68T01, 68T05, 68T42", "444": "68T01, 68T05, 68U10, 62M45, 78M32, 92C50, 92C55, 94A08", "445": "68T01, 68T05, 68U10, 62M45, 78M32, 92C55, 94A08", "446": "68T01, 68T10, 68T30", "447": "68T01, 68T10, 68T45, 62H25", "448": "68T01, 68T27, 68T20, 68T30", "449": "68T04", "450": "68T05", "451": "68T05 (Primary) 65F99, 15B99 (Secondary)", "452": "68T05 (Primary), 93E35, 90C40, 93E20, 49L20 (Secondary)", "453": "68T05 (Primary), 93E35, 93E20, 90C40, 49L20 (Secondary)", "454": "68T05 Learning and adaptive systems", "455": "68T05,", "456": "68T05, 05C80, 62G99", "457": "68T05, 49D, 49M", "458": "68T05, 49L20, 93C15, 34H05", "459": "68T05, 58J35", "460": "68T05, 62G08,", "461": "68T05, 62G15", "462": "68T05, 62H30, 62C10", "463": "68T05, 65K10, 42-02", "464": "68T05, 65L06", "465": "68T05, 68Q32", "466": "68T05, 68Q32, 62B10", "467": "68T05, 68T10", "468": "68T05, 68T10, 68Q32", "469": "68T05, 68T10, 68Q32,", "470": "68T05, 68T10, 68T45, 68U10, 68W25, 68W99", "471": "68T05, 68T10, 68T45, 92B20", "472": "68T05, 68T30", "473": "68T05, 68T30, 68T40, 62J02, 65D15", "474": "68T05, 68T37, 60G25, 62M20", "475": "68T05, 68T40", "476": "68T05, 68T40, 62G08, 37H10", "477": "68T05, 68T45", "478": "68T05, 68T50", "479": "68T05, 81P68, 92B20, 82C32", "480": "68T05, 90C40", "481": "68T05, 91A26, 91A22, 93E35, 60J05, 91A80", "482": "68T05, 91C20", "483": "68T05, 92C50", "484": "68T05, 94A15", "485": "68T05, 94A20, 41A35", "486": "68T06", "487": "68T10", "488": "68T10 (Primary) 62H30 (Secondary)", "489": "68T10 (Primary), 62Fxx (Secondary), 62H12, 97K80, 68T05", "490": "68T10 (Primary), 68T40 (Secondary)", "491": "68T10, 62H30", "492": "68T10, 62H30, 62H35", "493": "68T10, 62H30, 68Q32, 68T05, 68Q32, 91E40", "494": "68T10, 62H30, 91C20", "495": "68T10, 62H99, 65Y20, 68T05", "496": "68T10, 68T05", "497": "68T10, 68T10", "498": "68T10, 68T15", "499": "68T10, 68T45", "500": "68T10, 90C05, 94A17, 62B10, 68U35", "501": "68T15", "502": "68T15, 68T27, 68T35", "503": "68T15, 68T30", "504": "68T15, 68T40, 68T37", "505": "68T20", "506": "68T20 (Primary), 68T05 (Secondary)", "507": "68T20, 06A99, 90B50, 90C29, 90C59, 93-02, 93A13, 93B50, 93B51", "508": "68T20, 68M10, 90B18, 90B50, 90C30, 90C27", "509": "68T20, 68M10, 90B50, 90B40, 90C27, 90C29, 90C59, 93B51", "510": "68T20, 68T42", "511": "68T20, 68W40", "512": "68T20, 90B18, 90B50, 90C27", "513": "68T20, 90C05", "514": "68T20, 93A13, 90B50", "515": "68T20, 93A13, 93B51, 90B50", "516": "68T27", "517": "68T27, 03B35, 03B10", "518": "68T27, 68N17", "519": "68T27, 68T15", "520": "68T27, 68T30", "521": "68T27, 97E30, 03A10, 68T30", "522": "68T30", "523": "68T30 (Primary), 68T01 (Secondary)", "524": "68T30 (Primary), 68T20 (Secondary)", "525": "68T30, 68T27", "526": "68T30, 68T50, 97G40", "527": "68T35", "528": "68T35, 68T30", "529": "68T37", "530": "68T37, 62C12", "531": "68T37, 62C86, 90C29, 90C70", "532": "68T37, 68T05", "533": "68T37, 68T05, 62P35", "534": "68T37, 68T10", "535": "68T37, 68T42", "536": "68T37, 82C32", "537": "68T37, 93C65", "538": "68T40", "539": "68T40, 68T45, 68T01", "540": "68T42", "541": "68T42 (Primary), 68T40 (Secondary)", "542": "68T42, 68T27, 68T37, 67T45", "543": "68T45", "544": "68T45, 68T10 (Primary)", "545": "68T45, 68T40", "546": "68T45, 68U05 (Primary), 68T10, 68T01 (Secondary)", "547": "68T45, 68U10", "548": "68T50", "549": "68T50 (Primary), 68T10 (Secondary)", "550": "68T50 (primary) 03B65, 18C50 (secondary)", "551": "68T50, 03B10", "552": "68T50, 03H65", "553": "68T50, 15A23", "554": "68T50, 68Q45", "555": "68T50, 68T05", "556": "68T50, 68T10, 68T37", "557": "68T50, 91F20", "558": "68T50, 91F20, 97C30", "559": "68T50, 92B20", "560": "68T50, 97C50", "561": "68T99", "562": "68T99, 65N55, 65F99, 65N75, 62C99, 42C40, 60G42, 68Q25", "563": "68T99, 78M50, 68T05", "564": "68Txx", "565": "68Txx, 68T05, 68T10, 68T30, 05C85", "566": "68U01", "567": "68U02", "568": "68U10", "569": "68U10, 05C85", "570": "68U10, 49J20, 35Q93, 65K10, 65F08, 76D55", "571": "68U10, 49J20, 35Q93, 65K10, 76D55, 90C20", "572": "68U10, 49J20, 35Q93, 65M32, 76D55, 65K10", "573": "68U10, 53C22, 74B20, 49M20", "574": "68U10, 62F15", "575": "68U10, 65K10", "576": "68U10, 65K10, 65M06", "577": "68U10, 68M11", "578": "68U10, 68R05", "579": "68U10, 68T10", "580": "68U10, 68T10, 62H35", "581": "68U10, 68U05", "582": "68U10, 68U05, 65D18", "583": "68U10, 68W10, 65M15", "584": "68U10, 90C90, 65T60", "585": "68U10, 94A08", "586": "68U10, 94A08, 62H35, 05C50, 47A52, 68R10", "587": "68U15, 68M20", "588": "68U15, 68T50", "589": "68U20", "590": "68U35", "591": "68Uxx", "592": "68Uxx, 37A50", "593": "68Uxx, 49N15, 62Jxx, 68Q32, 62-04", "594": "68Uxx, 62J15, 68Q32, 62-04,", "595": "68W01, 68W40, 68W25, 49K30", "596": "68W10, 90C25", "597": "68W15", "598": "68W20, 68W01, 68T01, 68T20, 68T50", "599": "68W20, 68W25, 68U05, 62H30", "600": "68W27, 62L05", "601": "68W30, 14N99, 68T45", "602": "68W30, 65D25, 68T05", "603": "68W30, 68T05, O3C10", "604": "68W40, 68Q25", "605": "68W48, 60J20, 93E15", "606": "69U99, 94A99", "607": "6Q655", "608": "70F04", "609": "78", "610": "78M32", "611": "78M50", "612": "78Mxx", "613": "80M50", "614": "80M50, 90C15, 90C26, 90C30, 68T05", "615": "80M50, 90C27", "616": "82C32 (Primary), 68T45 (Secondary)", "617": "82C32, 60C05, 68Q32", "618": "85-08, 68U10", "619": "85A35 (Primary), 68W10, 62P35", "620": "86-04", "621": "8U05, 65D18", "622": "90-02, 90-08, 90B99, 37D05", "623": "90-08", "624": "90-08, 90-04, 90C05, 90C08", "625": "90-08, 90C25, 65P99, 65K10, 93E10, 93E12", "626": "90-XX", "627": "90B08 (Primary) 90B06, 90B50 (Secondary)", "628": "90B35", "629": "90B50", "630": "90B50, 90B51, 90C27, 90C59", "631": "90B50, 91B08", "632": "90C05, 90C59", "633": "90C06", "634": "90C06, 81P50, 65K10, 62F35, 47N30", "635": "90C06, 90C25, 68T05", "636": "90C06, 90C25, 90C26, 90C59", "637": "90C06, 90C25, 90C26, 90C59, 93B30, 93B15, 93B40", "638": "90C10", "639": "90C11, 68Q32", "640": "90C15, 68T05, 65K10", "641": "90C15, 90C25, 68W20", "642": "90C20", "643": "90C22, 90C47, 62J07", "644": "90C22, 92C55", "645": "90C25", "646": "90C25, 49M29, 94A08", "647": "90C25, 68W15", "648": "90C25, 68W15, 68W10", "649": "90C26", "650": "90C26, 62K25, 62F35", "651": "90C26, 65D15", "652": "90C26, 90C30, 90C59", "653": "90C26, 90C30, 90C59, 90C06", "654": "90C26, 90C56", "655": "90C26, 90C90", "656": "90C27", "657": "90C27, 68P10", "658": "90C27, 68R05, 91B69", "659": "90C27, 68T10, 68T20", "660": "90C27, 90C29", "661": "90C29", "662": "90C29 ? 90C70 ? 90C90", "663": "90C40", "664": "90C40 (Primary) 90C39, 93E35, 60J10 (Secondary)", "665": "90C40, 62L20, 68W40", "666": "90C52, 90C90, 68T05", "667": "90C52, 90C90, 90C06, 68T05", "668": "90C53, 65F10,", "669": "90C55, 90C15, 62H30", "670": "90C56", "671": "90C59", "672": "90C59, 93D99", "673": "90C90", "674": "90C90, 68Q32, 62H30, 90C05, 52B12", "675": "90C90, 90C46, 68Q32", "676": "90Cxx", "677": "90D20 (Primary) 90D80, 49N55, 93C41, 93B52, 51D05, 68U07 (Secondary)", "678": "91A05, 91A10", "679": "91A05, 91A43 (Primary), 91A46 (Secondary)", "680": "91A06, 03B42", "681": "91A12, 68Q15", "682": "91A20 (Primary) 68W27, 68Q32 (Secondary)", "683": "91A20 (Primary), 68T05 (Secondary), 68W27 (Secondary), 91A05\n (Secondary), 91A26 (Secondary)", "684": "91A20 (Primary), 91A05, 91A15 (Secondary)", "685": "91A22", "686": "91B06, 90B50", "687": "91B14", "688": "91B14, 68W15, 90B30 (Primary) 68T20, 91B10, 91B12 (Secondary)", "689": "91B14, 91B06, 03B42", "690": "91B26 (Primary) 90B06, 90B40 (Secondary)", "691": "91B69", "692": "91B80, 68T05, 92B20, 81P68", "693": "91C20", "694": "91C20, 62-07, 03-XX", "695": "91C99", "696": "91D30, 68T05, 68T10", "697": "91E10", "698": "91E10, 97C30, 68T50", "699": "91E40, 68T05, 68T20, 68T30", "700": "91E40, 68T05, 92C42", "701": "91E45", "702": "91F10", "703": "91F20", "704": "91F20(primary) 03B65, 68T50(secondary)", "705": "91F20, 03B65, 68T50", "706": "91F20, 13P10", "707": "91F20, 14M12, 92B10, 13P25", "708": "91F20, 62P25", "709": "91F20, 68P30", "710": "91F20, 68T20, 68T50, 92D15", "711": "91F20, 70F99", "712": "91F20, 82B20", "713": "91F20, 94A99, 60GNN", "714": "91G99, 60J22", "715": "92-08", "716": "9208", "717": "92B05", "718": "92B20", "719": "92B20, 34C23, 34K18", "720": "92B20, 65C10, 37B15, 62P10", "721": "92B20, 68T05, 68T37", "722": "92B20, 81P68, 82C32", "723": "92B20, 90B22, 90B20, 37M10", "724": "92B20, 92B25, 70E60, 68T05, 68U20", "725": "92B99", "726": "92C-06, 94C-06", "727": "92C55, 68T45, 68T10, 62M45", "728": "92C55, 92C37, 92C17, 35A15, 68U10, 33C55", "729": "92D15, 91E40, 68T20, 68T30", "730": "92DXX, 68TXX, 03Dxx", "731": "92E10, 46M20, 94A08, 68U10, 44A12, 55R35", "732": "92F99", "733": "93C05", "734": "93C85, 70Q05, 68T40, 90C39, 90C35, 68R10", "735": "93Cxx", "736": "93E10", "737": "93E20, 90C40", "738": "93E20, 91D30", "739": "93E35", "740": "93E35, 15B48", "741": "94", "742": "94A08", "743": "94A08 65T60", "744": "94A08, 65Nxx, 65Kxx", "745": "94A08, 68U10", "746": "94A08, 68U10, 47N10", "747": "94A08, 68U10, 47N10, 49N45, 65J22", "748": "94A08, 94A12", "749": "94A12", "750": "94A12 (Primary), 62P12", "751": "94A12, 92C55, 62M10", "752": "94A15, 68T05, 62B10", "753": "94A17", "754": "94A17, 60G10, 94A29, 68Q30, 68T50", "755": "94A17, 62B15", "756": "94A17, 68U10, 94A08", "757": "94A29, 60G10, 94A17", "758": "94AXX", "759": "94Axx", "760": "94C-06", "761": "94Cxx", "762": "94D05", "763": "97P20", "764": "97Pxx, 68Mxx,", "765": "97R30", "766": "97R40", "767": "97R40, 62H35, 68U15, 68T50,", "768": "97R40, 68T01, 65K10, 62M45", "769": "97R40, 68T10, 62H30", "770": "97Rxx", "771": "A.1", "772": "A.1, I.2, I.5, J.3", "773": "A.1; E.2; H.2.1; H.3.3; H.3.7; I.2.7", "774": "A.1; F.4.1; I.2.11", "775": "A.1; H.1.1; H.4.2; I.1.2; I.2.8; I.5.2; J.6", "776": "A.1; I.4.9; I.5.4", "777": "A.1;E.2;F.4.1;I.2.0;I.2.6;I.2.8;I.2.9;I.2.11;I.3.5;I.6.0;J.6", "778": "A.1;I.4,I.3.3,I.2.10;I.3.7;B.4.2", "779": "A.m", "780": "A0", "781": "A0;F1.1;J5", "782": "Artificial intelligence and nonmonotonic reasoning and belief\n revision", "783": "B.0; C.0; K.4.0; I.0", "784": "B.1.1", "785": "B.1.2; B.2.3; F.1.1; I.2.8", "786": "B.1.3", "787": "B.1.4", "788": "B.1.4; H.3.1", "789": "B.2.0; C.1.3", "790": "B.2.1", "791": "B.2.2", "792": "B.2.4; G.1.2", "793": "B.2.4; I.4.6; I.4.8", "794": "B.3.1; B.2.0; B.6.0; I.2.0; I.6.m; C.1.m", "795": "B.3.1; B.4.3; B.5.1; B.6.1; C.1.3; C.1.m; I.2.3", "796": "B.6.0", "797": "B.6.1; C.1.3; I.2.0", "798": "B.6.1; G.3", "799": "B.7.1; I.2.6", "800": "B.7.1; I.2.9; I.2.8; I.6.0", "801": "B.8.1", "802": "C.0; D.2.1; D.3.1; F.4.1", "803": "C.1.3", "804": "C.1.3; B.3.1", "805": "C.1.3; C.2.0; E.3.x; F.1.1", "806": "C.1.3; C.3", "807": "C.1.3; D.1.3; I.2.6; I.2.7; H.3.4", "808": "C.1.3; E.3.x; F.1.1", "809": "C.1.3; F.1.1.; I.2.0; I.2.6; I.2.10; I.4.3.; I.4.10; I.5.1", "810": "C.1.3; F.1.1; I.2.6", "811": "C.1.3; F.1.1; I.2.6; I.5.1", "812": "C.1.3; F.1.3", "813": "C.1.3; H.5.1", "814": "C.1.3; I.2.10", "815": "C.1.3; I.2.6", "816": "C.1.3; I.2.6; I.5", "817": "C.1.3; I.5.1", "818": "C.1.3; I.5.1; I.2.6; G.1.2", "819": "C.1.3; I.5.1; I.7.2; I.2.7", "820": "C.1.4; C.2.1; C.2.4; C.2.4; F.1.1; I.2.6; H.3.5", "821": "C.1.4; C.3; B.7.2; F.2.2", "822": "C.1.4; G.1.6; I.2.8", "823": "C.2.0", "824": "C.2.0; H.4.3", "825": "C.2.0; K.4.4; I.2.6", "826": "C.2.1; C.2.2; C.2.4; C.2.6; F.1.1; I.2.6; I.2.8; I.2.9", "827": "C.2.1; C.2.2; F.1.1; I.2.6; I.2.8", "828": "C.2.1; D.2.2; G.2.3; I.2.8; J.6", "829": "C.2.1; I.2.6; I.2.7", "830": "C.2.2, C.2.4, D.2.4, I.2.4, F.3.1, F.3.1", "831": "C.2.2; I.2.6", "832": "C.2.2; I.2.6; I.2.0", "833": "C.2.3", "834": "C.2.3; F.4.1; G.2.2; I.2.3; I.2.6", "835": "C.2.3; I.2.6", "836": "C.2.4", "837": "C.2.4; D.2.11; H.1.0", "838": "C.2.4; F.4.1; G.2.1; G.3; H.2.4; H.2.7; H.3.5; H.5.3; J.3; K.4.1;\n K.6.5", "839": "C.2.4; I.5; I.2.6; D.2.10; D.2.11; D.2.5; D.2.2; I.2.7", "840": "C.3", "841": "C.3; C.4; F.1.1; I.2.6; I.2.9; I.6.5; J.2, J.7", "842": "C.3; C.5.4; I.5.5", "843": "C.3; H.5.5", "844": "C.4", "845": "Comptuational science", "846": "Computer Science", "847": "D. 2.5", "848": "D.#.2; I.2.2; I.2.3", "849": "D.1.0", "850": "D.1.16; I.2.8", "851": "D.1.2; I.2.2", "852": "D.1.3", "853": "D.1.3; D.2.12; D.3.1; H.3.5", "854": "D.1.3; D.3.1; D.3.2; D.3.3; F.3.2", "855": "D.1.3; I.2.10; I.4.8; I.5.4; I.3.3", "856": "D.1.6", "857": "D.1.6.; F.3.2.; F.4.1; I.2.3.; I.2.4", "858": "D.1.6.; F.3.2.; I.2.3.; I.2.4", "859": "D.1.6; D.1.2; I.2.2; F.4.1; I.2.3", "860": "D.1.6; D.1.7", "861": "D.1.6; D.3", "862": "D.1.6; D.3.1", "863": "D.1.6; D.3.1; F.3.2; G.3", "864": "D.1.6; D.3.1; F.4.1; I.2.3", "865": "D.1.6; D.3.2", "866": "D.1.6; D.3.2; F.4.1; I.2.3; I.2.4", "867": "D.1.6; D.3.2; I.2.4; F.4.1", "868": "D.1.6; F.1.3", "869": "D.1.6; F.2; F.3; F.4; I.2; F.1.3", "870": "D.1.6; F.3.1; F.4.1", "871": "D.1.6; F.4.1; I.2.3", "872": "D.1.6; I.2.10; I.2.8", "873": "D.1.6; I.2.3", "874": "D.1.6; I.2.3; I.2.4", "875": "D.1.6; I.2.4", "876": "D.1.6; I.2.4; I.2.6; I.2.9", "877": "D.1.6; I.2.8; I.2.4; J.5", "878": "D.1.6;F.2.2;F.4.2;I.2.8;I.6.5", "879": "D.1.6;I.2.2;I.2.3;F.4.1", "880": "D.1.6;I.2.4", "881": "D.1.7; H.2.8; I.4.6", "882": "D.1; F.1", "883": "D.2.0; I.2.7", "884": "D.2.11; D.2.10; D.3.3; I.2.8", "885": "D.2.13", "886": "D.2.1; D.2.2; D.2.10", "887": "D.2.2", "888": "D.2.2; G.1.10; G.2.2; H.1.1; H.1.2; H.3.1; H.3.3; H.3.5; H.5.2;\n H.5.3; H.5.4; I.2.1; I.2.4; I.2.7; I.3.6; K.4", "889": "D.2.2; G.1.6", "890": "D.2.2; G.2.3; I.2.8; J.6", "891": "D.2.2; H.1.2; I.1.3", "892": "D.2.2; I.2.10", "893": "D.2.2; I.2.8", "894": "D.2.4", "895": "D.2.4 model checking; F.4.1 modal logic; J.3 medical information\n systems", "896": "D.2.4, I.2.7", "897": "D.2.4; D.2.5", "898": "D.2.4; D.2.5; I.2.2; F.3.1", "899": "D.2.4; I.2.2", "900": "D.2.4; I.2.6", "901": "D.2.4;D.2.2;F.4.1;I.2.4;F.3.1", "902": "D.2.4;F.3.1;F.4.1;I.2.4;D.2.1", "903": "D.2.5", "904": "D.2.5; D.2.4; D.3.2", "905": "D.2.5; I.2.3", "906": "D.2.6; G.1.2; G.1.3; G.3; I.2.10; I.5; H.2.8", "907": "D.2.6; I.2.7; J.5; K.3.2", "908": "D.2.8", "909": "D.3", "910": "D.3.0", "911": "D.3.1, F.3.0", "912": "D.3.1; F.4.1; I.2.3", "913": "D.3.2", "914": "D.3.2; D.3.3", "915": "D.3.2; D.3.3; D.1.6", "916": "D.3.2; D.3.3; F.4.1", "917": "D.3.2; D.3.3; F2.2", "918": "D.3.2; D.3.3; G.2.2", "919": "D.3.2; D3.3", "920": "D.3.2; F.4.1", "921": "D.3.2; H.2.4", "922": "D.3.2;D.3.3", "923": "D.3.3", "924": "D.3.3; F.3.2; G.1.0", "925": "D.3.3; F.4.1", "926": "D.3.3; I.1.2; I.2.2", "927": "D.3.3; K.6.5; D.4.6", "928": "D.3.3;D.2.2;G.1.0;H.5.1", "929": "D.3.3;G.1.6", "930": "D.3.3;I.1.2;I.1.3", "931": "D.3.3;I.2.2;I.2.3", "932": "D.3.4; D.1.6", "933": "D.4.6", "934": "D.4.8; G.3; C.2.3", "935": "D.4.8; H.1.2; H.2.8; I.2.7", "936": "E.0", "937": "E.1; E.3; H.2.8; H.3.3", "938": "E.1; F.2.2; G.2.1; G.2.2; G.2.3; G.3; G.4; J.3", "939": "E.2; H.2.1; H.3.3; H.3.4; H.3.7; I.2.7", "940": "E.2; H.2.5; I.2.7", "941": "E.4", "942": "E.4,F.2,H.3,I.2,I.5,I.7", "943": "E.4; F.2; I.2", "944": "E.4; G.3; H.3.3", "945": "E.4; G.3; I.2.7", "946": "E.4; H.1.1; G.1.0", "947": "E.4; I.2.6", "948": "E.4; I.2.6; I.5", "949": "E.4;I.2.6;G.3", "950": "E.5; E.4; E.2; H.1.1; F.1.1; F.1.3", "951": "E4, H.3.3, H.5.5, I.2.6, I.2.10, I.5.3, J.3,J.5", "952": "F.0", "953": "F.1", "954": "F.1.0; I.2.0", "955": "F.1.1", "956": "F.1.1, I.2.6", "957": "F.1.1; D.3.1; F.4.3", "958": "F.1.1; F.1.2; F.2.0; F.4.1; I.1.2; I.2.0", "959": "F.1.1; F.3.3; I.2.0; I.2.2", "960": "F.1.1; F.4.0; H.1.1; I.2.0; J.3", "961": "F.1.1; F.4.3; I.2.1; J.5", "962": "F.1.1; G.1.6; J.1; J.4", "963": "F.1.1; H.1.1", "964": "F.1.1; I.2.0", "965": "F.1.1; I.2.2; I.2.3; I.2.4", "966": "F.1.1; I.2.3", "967": "F.1.1; I.2.6", "968": "F.1.1; I.2.6; I.5.1", "969": "F.1.1; I.2.7", "970": "F.1.1; J.3", "971": "F.1.1; J.3; I.2.m", "972": "F.1.1; K.3.2; I.2.6", "973": "F.1.1;F.2.2;G.3;I.2.1;J.4", "974": "F.1.1;K.3.2;I.1.10", "975": "F.1.2; C.2.4", "976": "F.1.2; F.4.3; J.7", "977": "F.1.2; G.2.1; G.2.2", "978": "F.1.2; G.3", "979": "F.1.2; I.2.8; G.3; I.6.8", "980": "F.1.3", "981": "F.1.3; F.2.2; F.2.3; I.4.3; I.5.1; I.5.4; I.5.5", "982": "F.1.3; F.4.1; I.2.4", "983": "F.1.3; I.2.8", "984": "F.1.3;I.2.4;D.1.6", "985": "F.1; E.2; D.1; I.4", "986": "F.2", "987": "F.2, E.4, I.2", "988": "F.2.0", "989": "F.2.0; G.1.6; I.2.6", "990": "F.2.0; I.2.0", "991": "F.2.1", "992": "F.2.1; F.2.2; I.2.6", "993": "F.2.1; G.1.2; G.1.3; G.1.6", "994": "F.2.1; G.1.3; G.1.6; G.3; J.3", "995": "F.2.1; G.1.6; G.2.0; I.1.2", "996": "F.2.1; G.1.6; I.1.2", "997": "F.2.1; I.2.8", "998": "F.2.1; J.2", "999": "F.2.2", "1000": "F.2.2; F.1.2", "1001": "F.2.2; F.4.1; I.2.10; I.5.2", "1002": "F.2.2; G.1.6; G.4; I.1.2", "1003": "F.2.2; G.1.6; I.2.6; I.5.1", "1004": "F.2.2; G.2.1; G.4; G.1.6", "1005": "F.2.2; G.2.1; I.2.4; I.4.0; I.5.1", "1006": "F.2.2; G.2.1; I.2.8", "1007": "F.2.2; G.2.2", "1008": "F.2.2; G.2; G.3", "1009": "F.2.2; G.3", "1010": "F.2.2; G.3; I.1.2; I.2.6; I.2.8", "1011": "F.2.2; H.2.4; I.2.8; G.2.2", "1012": "F.2.2; I.2", "1013": "F.2.2; I.2.1", "1014": "F.2.2; I.2.4", "1015": "F.2.2; I.2.6", "1016": "F.2.2; I.2.7", "1017": "F.2.2; I.2.8", "1018": "F.2.2; I.2.8; D.1.3", "1019": "F.2.2; I.2; H.2", "1020": "F.2.2; I.5.1", "1021": "F.2.2; I.5.3", "1022": "F.2.2; I.5.3; H.5.3; H.5.m", "1023": "F.2.2; I.5; J.3", "1024": "F.2.2; J.3", "1025": "F.2.2;H.2.8;F.1.2", "1026": "F.2.3", "1027": "F.2.3; F.1.0", "1028": "F.2.3; I.2.3", "1029": "F.2.m; I.2.8", "1030": "F.2; F.2.2; I.2; I.2.6", "1031": "F.2; J.4", "1032": "F.3.0", "1033": "F.3.1", "1034": "F.3.1;F.3.2;I.2.5;I.2.4", "1035": "F.3.2; D.3.1; I.2.5; G.3", "1036": "F.3.2; D.3.2", "1037": "F.3.2; G.3; I.2.5", "1038": "F.3.3; F.4.2; D.3.3", "1039": "F.3; H.2; I.2; D.2", "1040": "F.4.0; F.4.1", "1041": "F.4.0; G.3", "1042": "F.4.1", "1043": "F.4.1 I.2.7", "1044": "F.4.1, D.3.2", "1045": "F.4.1, F.3.1, I.2.4, C.2.2, C.2.4", "1046": "F.4.1, I.2.3, I.2.4", "1047": "F.4.1, I.2.4", "1048": "F.4.1; D.1.5; D.3.3", "1049": "F.4.1; D.1.6", "1050": "F.4.1; D.3.3", "1051": "F.4.1; F.1.3", "1052": "F.4.1; F.2.2", "1053": "F.4.1; F.3.1; I.2.4", "1054": "F.4.1; G.1.6", "1055": "F.4.1; G.2.2", "1056": "F.4.1; G.2.2; I.2.6", "1057": "F.4.1; I.2", "1058": "F.4.1; I.2.3", "1059": "F.4.1; I.2.3; I.2.4", "1060": "F.4.1; I.2.3; I.2.4; G.3", "1061": "F.4.1; I.2.3; I.2.7", "1062": "F.4.1; I.2.4", "1063": "F.4.1; I.2.4; I.2.1", "1064": "F.4.1; I.2.6", "1065": "F.4.1; I.2.6; I.2.7", "1066": "F.4.1; I.2.7", "1067": "F.4.1; I.2.8", "1068": "F.4.1; K.3.2", "1069": "F.4.1;D.1.6;I.2.4", "1070": "F.4.1;F4.3;", "1071": "F.4.1;I.2.0", "1072": "F.4.1;I.2.3", "1073": "F.4.1;I.2.3; I.2.4; F.2.2", "1074": "F.4.1;I.2.3;D.1.0", "1075": "F.4.1;I.2.3;D.1.6", "1076": "F.4.1;I.2.3;I.2.4", "1077": "F.4.1;I.2.4;D.I.6", "1078": "F.4.1;I.2.4;I.2.3", "1079": "F.4.2", "1080": "F.4.2; F.1.1", "1081": "F.4.2; F.4.3", "1082": "F.4.2; G.2.2; I.2.8; F.1.3", "1083": "F.4.2; I.2.7", "1084": "F.4.3", "1085": "F.4.3; F.1.1", "1086": "F.4.3; F.1.1; F.1.3", "1087": "F.4.3; I.2.7", "1088": "F.4.3; I.2.7; F.4.2", "1089": "F.4; I.2.3; I.2.4", "1090": "F.5.3; K.3; K.4", "1091": "F1.1;I2.6;I5,1", "1092": "G.1.0; G.1.6", "1093": "G.1.0; G.1.6; I.2.8", "1094": "G.1.0; G.4", "1095": "G.1.1", "1096": "G.1.10; G.2.3; H.2.8", "1097": "G.1.1; G.1.2; G.1.6; G.1.10; G.3; I.2.6", "1098": "G.1.2", "1099": "G.1.2; I.4.m", "1100": "G.1.2; I.5", "1101": "G.1.3; F.4.1; F.4.2; I.2.7", "1102": "G.1.3; G.1.6", "1103": "G.1.3; G.1.6; G.1.8; I.4.0; I.4.5", "1104": "G.1.3; G.3; I.2.6; I.5.1", "1105": "G.1.3; H.3.1; H.3.3", "1106": "G.1.4", "1107": "G.1.4; I.2.6", "1108": "G.1.6", "1109": "G.1.6, F.4.1", "1110": "G.1.6; C.1.4", "1111": "G.1.6; C.2.1", "1112": "G.1.6; F.1.1; I.2.6; G.1.3", "1113": "G.1.6; G.1.8", "1114": "G.1.6; G.2.1; G.2.3; H.3.3; I.2.8; I.5.3", "1115": "G.1.6; G.2.1; I.2.8", "1116": "G.1.6; G.3; I.1.2; F.2.2; G.2.2", "1117": "G.1.6; G.3; I.2.6", "1118": "G.1.6; G.3; I.2.6; I.2.8", "1119": "G.1.6; G.3; I.2.8", "1120": "G.1.6; H.4.2", "1121": "G.1.6; I.2.10; I.2.0; I.2.6", "1122": "G.1.6; I.2.3; I.2.8; I.6.3; I.6.1; I.6.3", "1123": "G.1.6; I.2.6", "1124": "G.1.6; I.2.6; I.2.8", "1125": "G.1.6; I.2.8", "1126": "G.1.6; I.2.8; I.2.6; J.2", "1127": "G.1.6; I.4.10", "1128": "G.1.6; I.4.4", "1129": "G.1.6; I.4.5", "1130": "G.1.6; I.4.6", "1131": "G.1.6; I.4.8", "1132": "G.1.6; I.4.9", "1133": "G.1.6; I.4; I.5", "1134": "G.1.6; I.5.1; J.3", "1135": "G.1.6; I.5.3", "1136": "G.1.6; I.5.3; I.5.1", "1137": "G.1.6; I.5.4", "1138": "G.1.6; J.5", "1139": "G.1.6; K.3.2", "1140": "G.1.6;I.2.8", "1141": "G.1; E.1", "1142": "G.2.0", "1143": "G.2.1", "1144": "G.2.1; G.2.2", "1145": "G.2.2", "1146": "G.2.2; F.2.2; I.4.0", "1147": "G.2.2; I.2.3; I.4.8", "1148": "G.2.2; I.5.5; E.2", "1149": "G.2.3; I.2.8; F.2.2", "1150": "G.2; G.3", "1151": "G.2; I.2.6; G.3; G.1.6", "1152": "G.2;G.1.6;I.2;I.2.6", "1153": "G.3", "1154": "G.3, I.2.7, I.5.1, I.5.4", "1155": "G.3, I.5.2", "1156": "G.3.3", "1157": "G.3.7", "1158": "G.3.8; E.1.3", "1159": "G.3; G.1.2; I.2", "1160": "G.3; G.1.2; I.2.6", "1161": "G.3; G.1.2; I.2.6; I.5.4", "1162": "G.3; G.1.6", "1163": "G.3; G.4; I.2.6", "1164": "G.3; H.1.1; I.2.11; I.5.m; J.3", "1165": "G.3; H.2.8", "1166": "G.3; H.2.8; H.3.3", "1167": "G.3; H.2.8; I.2.1", "1168": "G.3; H.3.3", "1169": "G.3; H.3.3; H.4; I.2", "1170": "G.3; H.3.3; I.5.3", "1171": "G.3; H.3.5; I.5.4", "1172": "G.3; I.2", "1173": "G.3; I.2.10; I.4; I.5.4", "1174": "G.3; I.2.10; I.5; I.4.10; I.5.1", "1175": "G.3; I.2.11; I.5.1; J.3", "1176": "G.3; I.2.1; I.5.1; I.5.2; I.5.4; J.3", "1177": "G.3; I.2.3", "1178": "G.3; I.2.6", "1179": "G.3; I.2.6; D.3.3", "1180": "G.3; I.2.6; F.2", "1181": "G.3; I.2.6; I.2.7", "1182": "G.3; I.2.6; I.2.7; I.5", "1183": "G.3; I.2.6; I.5.1", "1184": "G.3; I.2.6; J.2", "1185": "G.3; I.2.7", "1186": "G.3; I.2.7; J.5", "1187": "G.3; I.2.8", "1188": "G.3; I.2.8; I.2.9", "1189": "G.3; I.4.6", "1190": "G.3; I.5.0; I.5.1", "1191": "G.3; I.5.1; H.3.3", "1192": "G.3; I.5.3", "1193": "G.3; I.5.4", "1194": "G.3; I.6.4; J.2; J.3", "1195": "G.3; J.3", "1196": "G.3;F.2.2", "1197": "G.3;I.2.4;I.2.6;I.2.10;I.4.1;I.4.4;I.4.5;I.4.10", "1198": "G.4; I.2.10; I.4.7; I.4.8; I.4.9; I.5.3", "1199": "G.4; I.2.5; I.2.6; I.5.2", "1200": "G1.6;I.2.8", "1201": "H 3.3, H 5.2", "1202": "H.1.1; E.4", "1203": "H.1.1; I.2.0; I.2.2", "1204": "H.1.2", "1205": "H.1.2; H.3.1", "1206": "H.1.2; H.3.1; I.2.7", "1207": "H.1.2; H.5.1; H.5.4; I.2.10", "1208": "H.1.2; H.5.2", "1209": "H.1.2; I.2", "1210": "H.1.2; I.2.1; I.2.7", "1211": "H.1.2; I.2.6; H.3.3", "1212": "H.1.2; I.2.6; I.2.1; J.7; J.4; K.4.1; K.4.3; K.5.2; I.2.7; K.4.2", "1213": "H.1.2; I.2.9; I.2.10; I.2.7; H.5.2; H.5.1; I.2.6; I.4.8; I.4.7;\n I.4.6", "1214": "H.1.2; I.4.6; C.3", "1215": "H.2, I.2.4", "1216": "H.2.0", "1217": "H.2.1", "1218": "H.2.1; H.2.4", "1219": "H.2.3", "1220": "H.2.3; F.4.1; I.2.3", "1221": "H.2.3; I.2.7; I.7.1", "1222": "H.2.4", "1223": "H.2.4; H.5.3; H.5.5; I.2.7", "1224": "H.2.4; I.2.3", "1225": "H.2.8", "1226": "H.2.8 Database Management, Database Applications-Data Mining", "1227": "H.2.8, H.3.1, I.2.7, I.5.5", "1228": "H.2.8; C.2.5; K.6.5", "1229": "H.2.8; F.1.2", "1230": "H.2.8; G.1.3; I.2.6; H.3.3", "1231": "H.2.8; G.2.2", "1232": "H.2.8; H.2.4", "1233": "H.2.8; H.3.1; I.2.6", "1234": "H.2.8; H.3.1; J.3", "1235": "H.2.8; H.3.3", "1236": "H.2.8; H.3.3; I.2.6", "1237": "H.2.8; H.3.3; I.2; I.5.3", "1238": "H.2.8; H.3.3; I.5.3; I.4.9", "1239": "H.2.8; H.3.5", "1240": "H.2.8; H.3.5; H.4.3; I.2.7; I.5.4; J.4; K.4.1", "1241": "H.2.8; H.4.2", "1242": "H.2.8; I.1.1; I.2.10; I.5.2", "1243": "H.2.8; I.2.3; F.4.1", "1244": "H.2.8; I.2.6", "1245": "H.2.8; I.2.6; I.5.1", "1246": "H.2.8; I.2.7", "1247": "H.2.8; I.5.1", "1248": "H.2.8; I.5.1; I.5.2", "1249": "H.2.8; I.5.3", "1250": "H.2.8; I.5.3; J.3", "1251": "H.2.8; J.3", "1252": "H.2.8; J.4", "1253": "H.2.m;I.2.m", "1254": "H.2; I.2.6; I.5.4", "1255": "H.3", "1256": "H.3, H.3.3, I.2.7", "1257": "H.3.0; H.3.3; D.3.0; D.3.1; D.3.m", "1258": "H.3.0; I.2.4", "1259": "H.3.1", "1260": "H.3.1, H.3.3", "1261": "H.3.1, I.2.6, I.2.7", "1262": "H.3.1; H.3.3", "1263": "H.3.1; H.3.3; G.1.6; H.2.4", "1264": "H.3.1; H.3.3; H.3.6; I.2.7; I.5.4; J.4", "1265": "H.3.1; H.3.3; I.2.6; I.2.7", "1266": "H.3.1; H.3.3; I.2.6; I.2.7; J.5", "1267": "H.3.1; H.3.3; I.2.7", "1268": "H.3.1; H.3.3; I.2.7; I.5", "1269": "H.3.1; H.3.3; I.2.7; I.5.4", "1270": "H.3.1; H.3.3; I.2.7; I.7; I.5; I.2.3", "1271": "H.3.1; H.3.3; I.2.7; J.4", "1272": "H.3.1; H.3.4; H.3.7; H.5.2; I.2.7", "1273": "H.3.1; H.3.6", "1274": "H.3.1; H.3.6; I.2.6", "1275": "H.3.1; I.2.3; I.2.7", "1276": "H.3.1; I.2.6; I.2.7", "1277": "H.3.1; I.2.6; I.2.7; E.1; G.1.3", "1278": "H.3.1; I.2.7", "1279": "H.3.1; I.2.7; I.2.4", "1280": "H.3.1; I.7.3", "1281": "H.3.1;H.3.3;H.3.4;H.5.2;I.2.7", "1282": "H.3.1;H.3.3;I.2.3", "1283": "H.3.1;H.3.3;I.4.8;I.5.3", "1284": "H.3.1;H.3.3;I.5.3;I.7.3", "1285": "H.3.1;I.2.7;I.5.4", "1286": "H.3.1;I.7.2;H.5.1", "1287": "H.3.2", "1288": "H.3.2; I.5.1; I.2.6; E.5; I.7; C.2; F.1; D.4.3", "1289": "H.3.3", "1290": "H.3.3; D.1.3; G.2.2", "1291": "H.3.3; E.2", "1292": "H.3.3; G.1.3; G.2.2", "1293": "H.3.3; G.2; I.2", "1294": "H.3.3; H.2.8; G.3", "1295": "H.3.3; H.3.4; I.2.7", "1296": "H.3.3; H.3.5; I.6.0", "1297": "H.3.3; H.3.m", "1298": "H.3.3; H.5.1; I.2.6; I.2.7", "1299": "H.3.3; I.2.1", "1300": "H.3.3; I.2.11; I.5.2; I.5.3", "1301": "H.3.3; I.2.11;I.5", "1302": "H.3.3; I.2.6", "1303": "H.3.3; I.2.6; D.2.8", "1304": "H.3.3; I.2.6; I.2.7", "1305": "H.3.3; I.2.6; I.2.7; I.5.3; I.5.4", "1306": "H.3.3; I.2.6; I.2.7; I.5.4", "1307": "H.3.3; I.2.6; I.5; I.5.3; I.5.4", "1308": "H.3.3; I.2.7", "1309": "H.3.3; I.2.7; I.2.6", "1310": "H.3.3; I.2.7; J.4", "1311": "H.3.3; I.4.9", "1312": "H.3.3; I.5.1", "1313": "H.3.3; I.5.3", "1314": "H.3.3;H.3.5", "1315": "H.3.4", "1316": "H.3.4; G.3; G.4", "1317": "H.3.4; I.5.1; I.2.6; I.2.7", "1318": "H.3.5", "1319": "H.3.5; H.4.2; H.5.4; I.2.6; K.8", "1320": "H.3.5; I.2", "1321": "H.3.5; I.2.6", "1322": "H.3.5; I.2.7; H.3.5", "1323": "H.3.7", "1324": "H.3.7; I.2.4", "1325": "H.3.m", "1326": "H.3; I.2.7; K.4.1", "1327": "H.4", "1328": "H.4.0;H.5.1;H.5.2;I.2.7", "1329": "H.4.2", "1330": "H.4.2; H.2.8", "1331": "H.4.2; H.5; I.2; D.2; I.4; I.5; B.2", "1332": "H.4.2; I.2.0; I.2.1; I.2.6; I.2.8", "1333": "H.4.2; I.2.3", "1334": "H.4.2; I.2.3; I.2.6; I.5.3; J.7", "1335": "H.4.2; J.4", "1336": "H.4.3; I.2.6; I.2.7; I.5.4; K.4.1", "1337": "H.4.3; J.4", "1338": "H.4; D.2.8", "1339": "H.4; G.3", "1340": "H.5.1", "1341": "H.5.1; H.5.5; I.2.4; I.2.5; I.2.7", "1342": "H.5.1; I.2.0", "1343": "H.5.1; I.2.11", "1344": "H.5.1; I.2.4", "1345": "H.5.1; I.4.8; I.5.1", "1346": "H.5.2", "1347": "H.5.2, I.2.7, I.2.11", "1348": "H.5.2; D.2.7", "1349": "H.5.2; F.4.2", "1350": "H.5.2; H.1.m", "1351": "H.5.2; H.5.3; I.2.7", "1352": "H.5.2; I.2.1; I.2.7", "1353": "H.5.2; I.2.4", "1354": "H.5.2; I.2.7", "1355": "H.5.2; I.2.9", "1356": "H.5.2; I.4.1", "1357": "H.5.2; I.4.7; I.5.5; G.1.3", "1358": "H.5.2; I.5.1.d; I.6.9.c; I.6.9.f; I.2.6.g", "1359": "H.5.2; I.5.4", "1360": "H.5.2; I.5.4; I.2.7", "1361": "H.5.2;H.3.1;H.3.4", "1362": "H.5.2;K.4.2;H.1.1;H.5.1;I.2.7", "1363": "H.5.3", "1364": "H.5.3, H.5.4", "1365": "H.5.3; H.5.4; I.7.2; F.4.m; H.3.5; D.2.1; D.2.7; I.2.4; K.6.3", "1366": "H.5.3; I.2.6; I.2.7", "1367": "H.5.3; I.2.7", "1368": "H.5.4, H.5.3", "1369": "H.5.4; H.2.4; H.3.4; H.5.1; C.2.4; K.3.1", "1370": "H.5.5", "1371": "H.5.5; I.2.6", "1372": "H.5.5; I.5; I.2.6; I.4.3; I.4; I.2", "1373": "H.5.m", "1374": "H.5.m; H.3.5", "1375": "H.m", "1376": "H3.1; I.2.7", "1377": "H3.1; I2.4; K3.1", "1378": "H3; I.2; H.1.2", "1379": "I 2.11", "1380": "I 4.1", "1381": "I,2,7", "1382": "I.0; I.2.7", "1383": "I.1.2; H.1.1", "1384": "I.1.2; I.2.2", "1385": "I.1.2; I.2.8", "1386": "I.1.4", "1387": "I.1; I.1.2", "1388": "I.2", "1389": "I.2 (I.2.3; I.2.4; I.2.m)", "1390": "I.2 (I.2.4)", "1391": "I.2,E.1,F.1", "1392": "I.2.0", "1393": "I.2.0, I.6.7", "1394": "I.2.0; C.1.3", "1395": "I.2.0; D.1.3; F.2.2", "1396": "I.2.0; F.1.1", "1397": "I.2.0; I.2.11", "1398": "I.2.0; I.2.1; H.5.2", "1399": "I.2.0; I.2.1; I.2.7", "1400": "I.2.0; I.2.2; I.2.6", "1401": "I.2.0; I.2.3; I.2.4; I.2.6; I.2.8; I.5.0; I.5.1; I.5.2; I.5.4; F.4.1", "1402": "I.2.0; I.2.3; I.2.6", "1403": "I.2.0; I.2.3; J.4", "1404": "I.2.0; I.2.4", "1405": "I.2.0; I.2.4; I.2.6; I.2.11", "1406": "I.2.0; I.2.6", "1407": "I.2.0; I.2.6; H.2.8", "1408": "I.2.0; I.2.6; I.2.10", "1409": "I.2.0; I.2.6; I.2.8", "1410": "I.2.0; I.2.6; I.2.8; I.2.9", "1411": "I.2.0; I.2.6; I.2.9; I.2.10", "1412": "I.2.0; I.2.8", "1413": "I.2.0; I.2.9; I.2.11; I.6.0; J.3", "1414": "I.2.0; I.5.1", "1415": "I.2.0; J.3; F.1.1", "1416": "I.2.0; K.4.1", "1417": "I.2.0;H.1.2", "1418": "I.2.1", "1419": "I.2.10", "1420": "I.2.10 Vision and Scene Understanding", "1421": "I.2.10, D.1.3, G.1.2", "1422": "I.2.10, I.4, I.5", "1423": "I.2.10, I.4.7, I.4.8", "1424": "I.2.10, I.4.8, I.5.4", "1425": "I.2.10, I.4.9, G.2.2", "1426": "I.2.10; H.1.2", "1427": "I.2.10; I.2.6", "1428": "I.2.10; I.2.9; I.4.8; I.5.2; I.4.0", "1429": "I.2.10; I.3.5; I.4.1; I.4.8", "1430": "I.2.10; I.3.7; I.4.8", "1431": "I.2.10; I.4", "1432": "I.2.10; I.4.3; D.1.3", "1433": "I.2.10; I.4.6; I.4.7; I.4.8; I.5.1; I.5.4; G.3", "1434": "I.2.10; I.4.6; I.4.7; I.4.8; I.5.4", "1435": "I.2.10; I.4.6; I.4.8", "1436": "I.2.10; I.4.6; I.4.8; I.4.9; I.2.9; I.5.4; I.5.5; J.2; J.3; D.2;\n D.1.7; D.4.7", "1437": "I.2.10; I.4.6; I.4.8; I.5.4", "1438": "I.2.10; I.4.7; I.5.1", "1439": "I.2.10; I.4.8", "1440": "I.2.10; I.4.8; I.5", "1441": "I.2.10; I.4.8; I.5.4", "1442": "I.2.10; I.4.8; I.5.4; I.6.5; J.2; G.1.3", "1443": "I.2.10; I.4.8; I.5.5", "1444": "I.2.10; I.4.9; H.3.1", "1445": "I.2.10; I.4.m", "1446": "I.2.10; I.4; I.5", "1447": "I.2.10; I.4; I.5; J.0; J.2; J.3", "1448": "I.2.10; I.5.1", "1449": "I.2.10; I.5.1; I.2.6", "1450": "I.2.10; I.5.2; H.1", "1451": "I.2.10; I.5.4", "1452": "I.2.10; I.6.8; J.4; G.3", "1453": "I.2.10;I.4.6;I.4.10", "1454": "I.2.11", "1455": "I.2.11 Distributed Artificial Intelligence", "1456": "I.2.11, I.2.8, K.4.4", "1457": "I.2.11; D.2.2", "1458": "I.2.11; D.3.3", "1459": "I.2.11; F.4.1; I.2.4; G.2.2", "1460": "I.2.11; G.1.6; I.2.8; G.2.3", "1461": "I.2.11; G.1.6; I.2.9", "1462": "I.2.11; G.2.1; G.2.2", "1463": "I.2.11; I.2.3; F.4.1; D.4.7; H.3.4", "1464": "I.2.11; I.2.6", "1465": "I.2.11; I.2.8", "1466": "I.2.11; I.2.9; I.3.3; I.4; I.4.10; I.4.6; I.4.9; I.5.4", "1467": "I.2.11; I.5.1; G.1.6", "1468": "I.2.11; I.6.3; I.6.5", "1469": "I.2.11; J.3", "1470": "I.2.11; J.4", "1471": "I.2.11; J.4; G.1.6", "1472": "I.2.11; J.4; H.3", "1473": "I.2.11;H.3.3", "1474": "I.2.11;I.2.6", "1475": "I.2.12; I.2.4.k", "1476": "I.2.12;I.2.3;D.2.12;H.2.4", "1477": "I.2.1; H.2.8", "1478": "I.2.1; I.2.10; I.2.2; I.2.6", "1479": "I.2.1; I.2.10; I.4.7; I.4.9; J.3", "1480": "I.2.1; I.2.2; I.2.7; J.4", "1481": "I.2.1; I.2.3; J.3", "1482": "I.2.1; I.2.4; I.2.6; H.5.5", "1483": "I.2.1; I.2.6", "1484": "I.2.1; I.2.6; H.2.8", "1485": "I.2.1; I.2.6; I.2.7", "1486": "I.2.1; I.2.6; I.2.8", "1487": "I.2.1; I.2.6; I.4.3; I.4.6; I.5.1; I.5.4", "1488": "I.2.1; I.2.7", "1489": "I.2.1; I.2.8; F.2", "1490": "I.2.1; I.5.1; I.5.2; J.3", "1491": "I.2.1; J.4; G.1.6", "1492": "I.2.1; J.5", "1493": "I.2.2", "1494": "I.2.2; F.1.1", "1495": "I.2.2; I.2.9", "1496": "I.2.2;I.2.6;I.2.8", "1497": "I.2.3", "1498": "I.2.3, I.2.4", "1499": "I.2.3; D.1.6", "1500": "I.2.3; D.1.6; F.4.1", "1501": "I.2.3; D.2.5", "1502": "I.2.3; F.3.1; F.4.1; I.2.2", "1503": "I.2.3; F.4.1", "1504": "I.2.3; F.4.1; I.2.4", "1505": "I.2.3; G.3", "1506": "I.2.3; H.2.4", "1507": "I.2.3; H.2.8; I.2.4; G.2.3; F.4.1", "1508": "I.2.3; I.2.4", "1509": "I.2.3; I.2.4; D.1.6", "1510": "I.2.3; I.2.4; D.3.1; D.1.6", "1511": "I.2.3; I.2.4; F.1.3; F.4.1; F.4.3", "1512": "I.2.3; I.2.4; F.4.1", "1513": "I.2.3; I.2.4; I.2.0; F.4.1", "1514": "I.2.3; I.2.4; I.2.11", "1515": "I.2.3; I.2.4; I.2.8", "1516": "I.2.3; I.2.4; I.2.8; F.4.1", "1517": "I.2.3; I.2.6", "1518": "I.2.3; I.2.6; I.4.8; I.5.3", "1519": "I.2.3; I.2.6; I.5.1", "1520": "I.2.3; I.2.6; I.5.3", "1521": "I.2.3; I.2.7", "1522": "I.2.3; I.2.8; F.4.1", "1523": "I.2.3; I.5.1; H.3", "1524": "I.2.3; I.5.2", "1525": "I.2.3; I.5.3", "1526": "I.2.3;F.4.1", "1527": "I.2.3;I.2.11;H.3.3", "1528": "I.2.3;I.2.4", "1529": "I.2.3;I.2.4;F.4.1", "1530": "I.2.3;I.2.4;I.2.8", "1531": "I.2.3;I.2.4;I.2.8;F.4.1;F.2.2", "1532": "I.2.3;I.2.8", "1533": "I.2.4", "1534": "I.2.4, F.1.3", "1535": "I.2.4, F.4.1", "1536": "I.2.4, F.4.1, I.2.3", "1537": "I.2.4; C.1.4", "1538": "I.2.4; D.1.5; D.3.2; F.4.1", "1539": "I.2.4; D.1.5; D.3.3", "1540": "I.2.4; D.1.5; D.3.3; F.4.1", "1541": "I.2.4; D.1.5; D.3.3; F.4.1; E.2", "1542": "I.2.4; D.1.6; F.4.1", "1543": "I.2.4; D.2.1", "1544": "I.2.4; E.2; D.1.5; D.3.3", "1545": "I.2.4; F.2.1", "1546": "I.2.4; F.2.1; F.2.2", "1547": "I.2.4; F.4.1", "1548": "I.2.4; F.4.1; D.1.5; D.3.3; E.2", "1549": "I.2.4; F.4.1; F.2.2", "1550": "I.2.4; F.4.1; H.3.5", "1551": "I.2.4; F.4.q", "1552": "I.2.4; G.2.2; D.1.5", "1553": "I.2.4; G.3", "1554": "I.2.4; H.2.4", "1555": "I.2.4; H.2.8", "1556": "I.2.4; H.3.3", "1557": "I.2.4; H.3.5", "1558": "I.2.4; H.3.5; J.4; G.2.3; C.2.4", "1559": "I.2.4; I.2.10; I.4.6; I.4.8; I.5.3; I.5.4; G.1.6", "1560": "I.2.4; I.2.11", "1561": "I.2.4; I.2.3; F.4.1", "1562": "I.2.4; I.2.3; H.2.4", "1563": "I.2.4; I.2.3; I.2.8", "1564": "I.2.4; I.2.5; H.3.7; H.3.4", "1565": "I.2.4; I.2.6", "1566": "I.2.4; I.2.6; G.1.6; J.4; J.3", "1567": "I.2.4; I.2.6; I.2.7", "1568": "I.2.4; I.2.6; I.2.8; I.2.9; I.2.10; I.4.8; I.5.1", "1569": "I.2.4; I.2.6; I.2.9; I.2.11; I.5.1", "1570": "I.2.4; I.2.7", "1571": "I.2.4; I.2.7; I.2", "1572": "I.2.4; I.2.8", "1573": "I.2.4; I.2.8; F.4.1; F.2.2", "1574": "I.2.4; I.2.8; I.2.3", "1575": "I.2.4; I.2.8; I.2.3; I.2.6; D.2.5", "1576": "I.2.4; I.6.2; I.6.7; F.4.1; D.3.2", "1577": "I.2.4;F.4.1", "1578": "I.2.4;I.2.3", "1579": "I.2.4;I.2.6", "1580": "I.2.5", "1581": "I.2.5; F.1.1", "1582": "I.2.6", "1583": "I.2.6 ; I.2.11", "1584": "I.2.6 ; I.2.3", "1585": "I.2.6, I.2.7", "1586": "I.2.6, I.2.7, H.3.1", "1587": "I.2.6, I.4, I.5", "1588": "I.2.6, I.5.1", "1589": "I.2.6, I.5.2, I.7.5", "1590": "I.2.6, K.6.5", "1591": "I.2.6; C.1.4", "1592": "I.2.6; D.2.10; I.2.2", "1593": "I.2.6; D.2.11", "1594": "I.2.6; E.1", "1595": "I.2.6; E.4; G.3", "1596": "I.2.6; E.4; G.3; F.1.3", "1597": "I.2.6; F.1.1; C.1.3; I.5.1", "1598": "I.2.6; F.1.3; E.4; F.2", "1599": "I.2.6; F.2.2", "1600": "I.2.6; F.2.2; G.3", "1601": "I.2.6; F.4.1", "1602": "I.2.6; F.4.2", "1603": "I.2.6; G.1", "1604": "I.2.6; G.1.2; G.3; I.2.8", "1605": "I.2.6; G.1.6", "1606": "I.2.6; G.3", "1607": "I.2.6; G.3; F.2.2", "1608": "I.2.6; G.3; J.3", "1609": "I.2.6; H.1.1; E.4", "1610": "I.2.6; H.2.8", "1611": "I.2.6; H.2.8; I.2.1", "1612": "I.2.6; H.3.1", "1613": "I.2.6; H.3.3", "1614": "I.2.6; H.5.5", "1615": "I.2.6; I.2.1", "1616": "I.2.6; I.2.10; G.3; I.5.3", "1617": "I.2.6; I.2.10; I.4.8", "1618": "I.2.6; I.2.11", "1619": "I.2.6; I.2.1; J.4", "1620": "I.2.6; I.2.3", "1621": "I.2.6; I.2.3; D.3.2", "1622": "I.2.6; I.2.3; H.3", "1623": "I.2.6; I.2.4", "1624": "I.2.6; I.2.4; I.2.8", "1625": "I.2.6; I.2.6", "1626": "I.2.6; I.2.7", "1627": "I.2.6; I.2.7; H.2.8", "1628": "I.2.6; I.2.7; H.3.1; H.3.3", "1629": "I.2.6; I.2.7; H.3.1; J.5", "1630": "I.2.6; I.2.7; H.5.2", "1631": "I.2.6; I.2.7; I.2.1", "1632": "I.2.6; I.2.7; I.2.10", "1633": "I.2.6; I.2.7; I.5.1", "1634": "I.2.6; I.2.7; I.5.1; I.5.4", "1635": "I.2.6; I.2.7; I.5.1; I.5.4; G.3", "1636": "I.2.6; I.2.7; I.5.3", "1637": "I.2.6; I.2.7; I.7.5", "1638": "I.2.6; I.2.8", "1639": "I.2.6; I.2.8; G.1.6", "1640": "I.2.6; I.2.8; I.2.11", "1641": "I.2.6; I.2.8; I.2.9", "1642": "I.2.6; I.2.8; I.2.9; I.2.11", "1643": "I.2.6; I.2.9", "1644": "I.2.6; I.2.9; I.2.10", "1645": "I.2.6; I.4", "1646": "I.2.6; I.4.3; J.3", "1647": "I.2.6; I.4.6; I.5.5", "1648": "I.2.6; I.4.7; I.4.8", "1649": "I.2.6; I.4.8", "1650": "I.2.6; I.4.9; J.5", "1651": "I.2.6; I.4; I.5", "1652": "I.2.6; I.4; I.5; I.6", "1653": "I.2.6; I.5", "1654": "I.2.6; I.5.0", "1655": "I.2.6; I.5.1", "1656": "I.2.6; I.5.1; G.3; G.1.6", "1657": "I.2.6; I.5.1; I.2.11", "1658": "I.2.6; I.5.1; I.5.2", "1659": "I.2.6; I.5.1; I.5.4; H.5.1", "1660": "I.2.6; I.5.1; I.5.4; I.2.10", "1661": "I.2.6; I.5.1; I.5.4; I.4.6", "1662": "I.2.6; I.5.1; I.5.5", "1663": "I.2.6; I.5.2", "1664": "I.2.6; I.5.2; E.4", "1665": "I.2.6; I.5.2; I.5.4", "1666": "I.2.6; I.5.2; I.5.4; J.2", "1667": "I.2.6; I.5.2; I.6.5; G.3; G.4", "1668": "I.2.6; I.5.3; I.2.4", "1669": "I.2.6; I.5.4", "1670": "I.2.6; I.5.4; J.2", "1671": "I.2.6; I.5.5", "1672": "I.2.6; I.5; C.1.3", "1673": "I.2.6; I.6.8; D.2.2", "1674": "I.2.6; I.7.5", "1675": "I.2.6; J.1; K.4.3", "1676": "I.2.6; J.2; I.2.7; I.5", "1677": "I.2.6; J.3", "1678": "I.2.6; J.3; G.3; G.4; I.5.2", "1679": "I.2.6; J.4; I.2.7", "1680": "I.2.6; J.5", "1681": "I.2.6; K.2.3", "1682": "I.2.6; K.3.2", "1683": "I.2.6; K.4.1", "1684": "I.2.6;G.1.2;G.3;I.6.5", "1685": "I.2.6;H.2.8", "1686": "I.2.6;I.2.11", "1687": "I.2.6;I.2.67", "1688": "I.2.6;I.2.7", "1689": "I.2.6;I.2.7;I.5.4", "1690": "I.2.6;I.2.7;J.5", "1691": "I.2.6;I.6.4;J.2;G.3", "1692": "I.2.6;J.3", "1693": "I.2.6;J.4;I.2.7", "1694": "I.2.7", "1695": "I.2.7, G.3", "1696": "I.2.7, I.2.0", "1697": "I.2.7, I.2.6, I.5.1, I.5.4", "1698": "I.2.7; D.1.6", "1699": "I.2.7; D.3.1", "1700": "I.2.7; F.2.2", "1701": "I.2.7; F.2.2; G.2.2", "1702": "I.2.7; F.4.1", "1703": "I.2.7; F.4.1; H.5.2", "1704": "I.2.7; F.4.2", "1705": "I.2.7; G.2.3; G.1.2", "1706": "I.2.7; G.3", "1707": "I.2.7; H.2.8; H.3.1", "1708": "I.2.7; H.3.1", "1709": "I.2.7; H.3.1; H.3.3; H.3.6", "1710": "I.2.7; H.3.3", "1711": "I.2.7; H.3.3; H.3.4; H.3.5", "1712": "I.2.7; H.3.3; H.3.4; H.5.1", "1713": "I.2.7; H.3.3; H.3.5", "1714": "I.2.7; H.3.3; H.3.6", "1715": "I.2.7; H.3.3; H.5.1", "1716": "I.2.7; H.3.3; H.5.2", "1717": "I.2.7; H.3.4", "1718": "I.2.7; H.3.m; H.2.8; J.4", "1719": "I.2.7; H.5", "1720": "I.2.7; H.5.0", "1721": "I.2.7; H.5.1", "1722": "I.2.7; H.5.2", "1723": "I.2.7; H.5.2; H.3.4; H.3.3", "1724": "I.2.7; I.1.2; J.3", "1725": "I.2.7; I.2.1", "1726": "I.2.7; I.2.1; I.2.10; H.5.5", "1727": "I.2.7; I.2.4", "1728": "I.2.7; I.2.4; I.2.6", "1729": "I.2.7; I.2.4; I.5.2", "1730": "I.2.7; I.2.6", "1731": "I.2.7; I.2.6; I.2.1", "1732": "I.2.7; I.2.6; I.5.1", "1733": "I.2.7; I.2.6; I.5.1; I.5.4", "1734": "I.2.7; I.2.8", "1735": "I.2.7; I.2.9", "1736": "I.2.7; I.5", "1737": "I.2.7; I.5.2; I.5.4; I.6.4", "1738": "I.2.7; I.5.3", "1739": "I.2.7; I.5.4", "1740": "I.2.7; I.5.4; I.7.m", "1741": "I.2.7; I.7.2", "1742": "I.2.7; J.3", "1743": "I.2.7; J.4", "1744": "I.2.7; J.4; J.5", "1745": "I.2.7; J.4; K.4.1; K.4.4", "1746": "I.2.7; J.5", "1747": "I.2.7; J.5; F.4.2", "1748": "I.2.7; K.3.1", "1749": "I.2.7;F.4.2;F.4.3", "1750": "I.2.7;I.2.6", "1751": "I.2.7;I.5.4", "1752": "I.2.7;I.7", "1753": "I.2.8", "1754": "I.2.8 I.2.9", "1755": "I.2.8, I.2.11", "1756": "I.2.8; C.2.2; F.2.2; I.2.4", "1757": "I.2.8; D.2.11;F.1.13; I.2.11", "1758": "I.2.8; D.3.3", "1759": "I.2.8; F.0; D.1.3", "1760": "I.2.8; F.1.1", "1761": "I.2.8; F.2.0", "1762": "I.2.8; F.2.2", "1763": "I.2.8; F.2.2; I.6; J.2", "1764": "I.2.8; F.2.m", "1765": "I.2.8; F.4.1", "1766": "I.2.8; F.4.1; I.6.5", "1767": "I.2.8; G.1.6", "1768": "I.2.8; G.1.6; D.3.3", "1769": "I.2.8; G.3", "1770": "I.2.8; I.2.1", "1771": "I.2.8; I.2.11", "1772": "I.2.8; I.2.11; F.2.2", "1773": "I.2.8; I.2.11; F.2.2; G.3", "1774": "I.2.8; I.2.1; J.6; I.2.4; F.2.2", "1775": "I.2.8; I.2.3", "1776": "I.2.8; I.2.3; F.3.3; F.4.1; D.1.6; D3.3", "1777": "I.2.8; I.2.3; F.4.1", "1778": "I.2.8; I.2.6", "1779": "I.2.8; I.2.6; F.2", "1780": "I.2.8; I.2.6; G.1.6", "1781": "I.2.8; I.2.6; G.1.6; I.5.3", "1782": "I.2.8; I.2.6; G.3", "1783": "I.2.8; I.2.9", "1784": "I.2.8; I.2.9; I.2.6", "1785": "I.2.8; I.5.3; I.7.1", "1786": "I.2.8; J.4; K.4.0", "1787": "I.2.8; J.6; K.4.3", "1788": "I.2.8; J.6; K.4.3; F.2.2", "1789": "I.2.8;I.2.6;I.2.11;I.2;I.2.3", "1790": "I.2.9", "1791": "I.2.9, G.1.6", "1792": "I.2.9; I.2.10", "1793": "I.2.9; I.2.10; I.2.11; I.4.7; I.4.8; I.4.9; I.4.10; I.5.1; I.5.2;\n I.5.4; I.5.5", "1794": "I.2.9; I.2.10; I.2.6; H.1.2; H.2.8; I.5.4", "1795": "I.2.9; I.2.10; I.2.7; I.2.6", "1796": "I.2.9; I.2.11", "1797": "I.2.9; I.2.11; H.5.3; I.5.5; J.5", "1798": "I.2.9; I.2.3; I.2.11", "1799": "I.2.9; I.2.6", "1800": "I.2.9; I.2.8; I.2.6", "1801": "I.2.M", "1802": "I.2.m", "1803": "I.2.m; I.2.4", "1804": "I.2; D.1.6; I.2.1; I.2.2; I.2.4; I.2.8", "1805": "I.2; D.4.8; F.1.1", "1806": "I.2; E.4; J.3; J.4", "1807": "I.2; F.1.1; I.2.11; I.2.8; G.1.6; C.2.4", "1808": "I.2; F.1.2; G.3; F.4.1", "1809": "I.2; F.1.3; E.4", "1810": "I.2; G.3", "1811": "I.2; H.2.8; J.1", "1812": "I.2; H.4.1", "1813": "I.2; I.2.0; I.2.4; I.2.10", "1814": "I.2; I.2.0; J.4", "1815": "I.2; I.2.10", "1816": "I.2; I.2.11; F.3; H.2.4", "1817": "I.2; I.2.1; I.2.6; I.2.10; I.3; I.3.3; I.4.3; I.4.4; I.4.9; J.3", "1818": "I.2; I.2.1; I.2.6; I.2.10; I.4.5; I.4.9", "1819": "I.2; I.2.3", "1820": "I.2; I.2.3; I.2.4; G.3; F.3.2; F.4.1", "1821": "I.2; I.2.3; I.2.6; I.2.8; F.1.3; F.2", "1822": "I.2; I.2.4; I.2.6; I.5; I.5.2; I.5.3; G.2.2", "1823": "I.2; I.2.6", "1824": "I.2; I.2.6; H.2.8; H.3.3", "1825": "I.2; I.2.6; I.2.8", "1826": "I.2; I.2.6; I.2.8; F.1.3", "1827": "I.2; I.2.6; I.2.8; F.2", "1828": "I.2; I.2.7", "1829": "I.2; I.2.8", "1830": "I.2; I.2.8; I.2.11; I.2.6; G.1.6", "1831": "I.2; I.2.9", "1832": "I.2; I.4; I.5", "1833": "I.2; I.5", "1834": "I.2; I.5.2", "1835": "I.2; I.5; J.5; H.2; H.3; H.4; H.2.8; E.2; E.4", "1836": "I.2; I.6", "1837": "I.2; J.2", "1838": "I.2; K.3.2; J.5", "1839": "I.2;I.2.9;I.2.11", "1840": "I.3", "1841": "I.3.1; I.4.8", "1842": "I.3.3; I.4.0", "1843": "I.3.3; I.4.6", "1844": "I.3.3; I.4; J.5", "1845": "I.3.5", "1846": "I.3.5, I.2.6", "1847": "I.3.5; I.5.1", "1848": "I.3.5; I.5.1; G.2.2", "1849": "I.3.6; I.2.6", "1850": "I.3.6; I.4.8", "1851": "I.3.7", "1852": "I.3.7; I.2.8", "1853": "I.3; I.2.6", "1854": "I.4", "1855": "I.4.0", "1856": "I.4.0, I.5.1, I.5.4, I.7.5", "1857": "I.4.0; I.4.10", "1858": "I.4.0; I.4.3", "1859": "I.4.0; I.4.3; I.4.5", "1860": "I.4.0; I.4.6; I.4.8; I.4.9; I.5.4; I.5.5; J.2; I.2.5; I.2.10", "1861": "I.4.0; I.5.0", "1862": "I.4.1", "1863": "I.4.1, I.4.4, I.2.6", "1864": "I.4.10", "1865": "I.4.10; I.4.7", "1866": "I.4.1; I.4.2; D.1.3", "1867": "I.4.1; I.4.5; I.4.7; I.4.10; I.5.4; I.7.5", "1868": "I.4.1; I.4.6; I.4.7; I.4.9; I.4.10; I.5.1; I.5.4; G.3", "1869": "I.4.2", "1870": "I.4.2; E.3", "1871": "I.4.2; I.4.10; G.1.2", "1872": "I.4.2; I.4.7", "1873": "I.4.3", "1874": "I.4.3; G.1.3", "1875": "I.4.3; G.1.8", "1876": "I.4.3; I.4.4", "1877": "I.4.3; I.4.4; G.1.9", "1878": "I.4.3; I.4.5; I.4", "1879": "I.4.3; I.4.6; I.2.10; G.1.8; G.2.2", "1880": "I.4.3; I.4.8", "1881": "I.4.3; I.4.9", "1882": "I.4.4", "1883": "I.4.4; F.2.1", "1884": "I.4.4; G.1.6", "1885": "I.4.5", "1886": "I.4.5; I.2.6", "1887": "I.4.5; I.2.6; I.5.1", "1888": "I.4.5; I.4.4", "1889": "I.4.5; I.4.4; G.3", "1890": "I.4.5; I.4.6; I.4.7; I.4.8", "1891": "I.4.5; I.4.8; G.3", "1892": "I.4.5; I.5.4", "1893": "I.4.6", "1894": "I.4.6; G.1.8", "1895": "I.4.6; G.3", "1896": "I.4.6; I.2.10; J.3", "1897": "I.4.6; I.4.3; G.1.8", "1898": "I.4.6; I.4.7; I.4.8", "1899": "I.4.6; I.4.7; I.4.9; I.5.4; I.2.10", "1900": "I.4.6; I.4.7; I.5.4", "1901": "I.4.6; I.4.8", "1902": "I.4.6; I.4.8; G.3; I.5.1; I.5.4", "1903": "I.4.6; I.4.8; I.4.9", "1904": "I.4.6; I.4.8; I.5.4; I.2.10", "1905": "I.4.6; I.4.9; I.5.4; I.5.3; K.6.5", "1906": "I.4.6; I.5", "1907": "I.4.6; I.5.1; I.5.3; I.5.4", "1908": "I.4.6; I.5.4", "1909": "I.4.7", "1910": "I.4.7, H.3.3", "1911": "I.4.7.c; I.4.7; I.4; I.4.7.b; I.5", "1912": "I.4.7; I.4.10", "1913": "I.4.7; I.4.10; I.5.1; I.5.4", "1914": "I.4.7; I.4.6; G.2.2; I.2.10; G.1.2", "1915": "I.4.7; I.4.8", "1916": "I.4.7; I.4.8; I.4.9", "1917": "I.4.7; I.4.8; I.4.9; I.5.1", "1918": "I.4.7; I.4.9", "1919": "I.4.7; I.5.3; I.6.4", "1920": "I.4.7; I.5.4; I.4.8; I.4.9; I.5.2", "1921": "I.4.8", "1922": "I.4.8, I.4.10, G.1.3, G.1.6", "1923": "I.4.8; I.2.10", "1924": "I.4.8; I.2.10; I.5.2; I.5.1", "1925": "I.4.8; I.2.9; I.4.1", "1926": "I.4.8; I.4.1", "1927": "I.4.8; I.4.10", "1928": "I.4.8; I.4.10; I.5.1; I.6.8; I.2.10; I.4.4; I.2.9; I.3.1", "1929": "I.4.8; I.4.6; I.4.0; I.2.9; I.2.10; J.2.; I.5.5; I.5.4; I.4.9", "1930": "I.4.8; I.4.7", "1931": "I.4.8; I.4.9", "1932": "I.4.8; I.5", "1933": "I.4.8; I.5.1", "1934": "I.4.8; I.5.1; G.3", "1935": "I.4.8; I.5.1; I.2.10; G.1.2; G.3", "1936": "I.4.8; I.5.2", "1937": "I.4.8; I.5.3", "1938": "I.4.8; I.5.4", "1939": "I.4.8; I.5.4; I.2.10; I.5", "1940": "I.4.8; I.5; I.5.1", "1941": "I.4.8;I.2.10", "1942": "I.4.8;I.5.1;I.2.10;G.3;G.1.2", "1943": "I.4.9", "1944": "I.4.9; I.2.10; D.4.7; C.3", "1945": "I.4.9; I.4.8; I.3.3", "1946": "I.4.9; I.4.9; I.5.0; I.5.4", "1947": "I.4.9; I.5.4", "1948": "I.4.9; I.5.4; H.5.1; H.5.5", "1949": "I.4.9; I.5.4; I.6.8; J.2", "1950": "I.4.m", "1951": "I.4; G.1.6; G.4", "1952": "I.4; I.2.7", "1953": "I.4; I.4.3; I.4.7; I.5", "1954": "I.4; I.4.3; I.5.1; I.5.4", "1955": "I.4; I.4.5; I.5.4", "1956": "I.4; I.4.6;I.4.8", "1957": "I.4; I.4.8; I.5.4; I.4.3", "1958": "I.4; I.5", "1959": "I.4; I.5.4", "1960": "I.4; I.5.4; H.3.3", "1961": "I.4; I.5.4; J.3", "1962": "I.4; I.5; I.2.10", "1963": "I.4; I.5; I.5.1", "1964": "I.5", "1965": "I.5, I.5", "1966": "I.5.0", "1967": "I.5.0; I.5.1", "1968": "I.5.1", "1969": "I.5.1 ; G.3", "1970": "I.5.1 ; J.3", "1971": "I.5.1, I.5.2", "1972": "I.5.1, I.5.2, I.4", "1973": "I.5.1; F.4.1; H.2.1", "1974": "I.5.1; G.1.6; H.2.8", "1975": "I.5.1; H.2.8; G.1.6", "1976": "I.5.1; I.2.0, I.2.6", "1977": "I.5.1; I.2.6", "1978": "I.5.1; I.2.6; G.3", "1979": "I.5.1; I.2.6; I.2.7", "1980": "I.5.1; I.2.7", "1981": "I.5.1; I.4.8; J.3", "1982": "I.5.1; I.5.2", "1983": "I.5.1; I.5.2; G.3", "1984": "I.5.1; I.5.2; I.2.6; I.3.5", "1985": "I.5.1; I.5.2; I.5.4", "1986": "I.5.1; I.5.2; I.5.4; I.2.6", "1987": "I.5.1; I.5.4", "1988": "I.5.1; I.5.4; G.3; I.2.7; I.2.6", "1989": "I.5.1; I.5.4; I.2", "1990": "I.5.1; I.5.4; I.2.10", "1991": "I.5.1; I.5.4; I.2.10; I.4.7; I.4.8; I.4.10", "1992": "I.5.1; I.5.4; I.4.7; I.4.8; I.2.10", "1993": "I.5.1; I.6.4; J.7", "1994": "I.5.1; I.6.8; J.4", "1995": "I.5.1; J.2", "1996": "I.5.1;I5.3", "1997": "I.5.2", "1998": "I.5.2, I.5.4", "1999": "I.5.2; G.1.6; H.1.1", "2000": "I.5.2; I.2.0", "2001": "I.5.2; I.2.11; I.5.3; J.3", "2002": "I.5.2; I.2.1; J.3", "2003": "I.5.2; I.2.6", "2004": "I.5.2; I.4.1", "2005": "I.5.2; I.4.7", "2006": "I.5.2; I.5.3", "2007": "I.5.2; I.5.3; I.5.4", "2008": "I.5.2; I.5.3; J.3", "2009": "I.5.2; I.7.5", "2010": "I.5.3", "2011": "I.5.3; D.1.3", "2012": "I.5.3; F.4.0", "2013": "I.5.3; G.3; G.4", "2014": "I.5.3; H.2.8", "2015": "I.5.3; H.2.8; I.2.6; I.2.4", "2016": "I.5.3; H.3.1; H.3.3", "2017": "I.5.3; H.3.3", "2018": "I.5.3; H.3.3; G.3", "2019": "I.5.3; I.5.2", "2020": "I.5.3; I.7.2; H.3", "2021": "I.5.4", "2022": "I.5.4; D.2.9", "2023": "I.5.4; H.3.1; I.2.7", "2024": "I.5.4; I.2.1", "2025": "I.5.4; I.2.10", "2026": "I.5.4; I.2.10; I.2.6", "2027": "I.5.4; I.2.10; I.4.9", "2028": "I.5.4; I.2.7; H.2.8; H.3.3", "2029": "I.5.4; I.2.7; H.3.1", "2030": "I.5.4; I.2.7; H.5.2; H.4.3", "2031": "I.5.4; I.4", "2032": "I.5.4; I.4.5; I.4.6", "2033": "I.5.4; I.4.7; I.5.3; G.3", "2034": "I.5.4; I.4.8", "2035": "I.5.4; I.4.9; J.2", "2036": "I.5.4; I.5.1; H.3.3", "2037": "I.5.5", "2038": "I.5; E.4; H.5; I.2.6; I.2.7; I.6", "2039": "I.5; F.1.1; F.4.1; K.3.2; I.4; I.4.8", "2040": "I.5; G.3; G.1.2", "2041": "I.5; G.3; H.2.8", "2042": "I.5; G.3; H.3; I.7; J.4", "2043": "I.5; I.2", "2044": "I.5; I.2.6; D.2.10; D.2.11; D.2.5; D.2.2; I.2.7", "2045": "I.5; I.2.6; H.2.8", "2046": "I.5; I.5.1; I.5.4; G.3", "2047": "I.5; I.5.2; I.2.1", "2048": "I.5; I.5.3", "2049": "I.5; I.5.3; I.4; I.2.11", "2050": "I.5; J.3", "2051": "I.5; J.4; J.3", "2052": "I.6.0", "2053": "I.6.1", "2054": "I.6.3; I.6.4; I.2.11", "2055": "I.6.3; I.6.8", "2056": "I.6.3; I.6.8; J.2; J.3", "2057": "I.6.3; I.6.8; J.3", "2058": "I.6.4; J.3", "2059": "I.6.5", "2060": "I.6.5; I.2.4; H.1.0", "2061": "I.6.5; J.4", "2062": "I.7", "2063": "I.7.0; I.5.3; G.3; I.5.2", "2064": "I.7.2, H.3.7", "2065": "I.7.2; E.2; H.1.1; G.2.3", "2066": "I.7.2; I.7.3; I.7.5; H.3.1; H.3.3", "2067": "I.7.2; I.7.4", "2068": "I.7.5", "2069": "I.7.5, I.5.4, I.4.6, I.5.1", "2070": "I.7.5; I.4.1; I.5.4; I.4.1; I.4.3; I.4.6; I.4.7", "2071": "I.7; I.7.5; I.4.6; I.4.8; I.2.10", "2072": "I1.2;F.1.1;F1.2;C1.3", "2073": "I2.10; I.4.10", "2074": "I2.2;I2.3;I2.4;I2.8;F4.1", "2075": "I2.6", "2076": "I2.6; I5.2", "2077": "IEEE", "2078": "J.1; I.2.2; D.2.8", "2079": "J.1; I.2.8", "2080": "J.2, J.6", "2081": "J.2; D.1.3; G.3; I.2; D.2", "2082": "J.2; J.3; I.5; C.1.3; G.2.1", "2083": "J.2; J.4", "2084": "J.3", "2085": "J.3; E.4", "2086": "J.3; H.2.8", "2087": "J.3; H.2.8; G.1.6; I.5", "2088": "J.3; I.4.6; I.4.7; I.4.9", "2089": "J.3; I.4.8", "2090": "J.3; I.4; I.5", "2091": "J.3; K.6.5; H.1.2; C.5.2", "2092": "J.4", "2093": "J.4; H.2.8", "2094": "J.4; I.2.11", "2095": "J.4; I.2.6", "2096": "J.4; I.2.6; K.4.1", "2097": "J.4; J.5", "2098": "J.4;H.3.5;I.2.m", "2099": "J.5", "2100": "J.5; D.3.3", "2101": "J.5; H.5.2; I.2.7; H.3.5; H.5.3", "2102": "J.5; I.2.7", "2103": "J.5; I.2.7; G.3", "2104": "J.6; I.2; I.2.8; A.1; C.2.1", "2105": "K.3.1", "2106": "K.3.1; I.2.3; I.2.6", "2107": "K.3.1; I.2.7; H.2.8", "2108": "K.3.1; I.2.7; I.2.11", "2109": "K.3.2", "2110": "K.3.2, I.5.4", "2111": "K.3.2; I.2.8", "2112": "K.3.2; I.5.1", "2113": "K.3.2;I.2.11", "2114": "K.4.1; H.1.2; H.3", "2115": "K.4.1; I.2.0", "2116": "K.4.1; I.7.5; I.2.7", "2117": "K.4.2", "2118": "K.4.2; I.2.7; H.5.2; I.2.1", "2119": "K.4.3", "2120": "K.5.0; H.2.8", "2121": "K.6.3; D.2.5; F.4.1", "2122": "K.6.3; I.2; I.2.4", "2123": "K.6.5", "2124": "K.6; H.2", "2125": "MIMO, relay, queue-aware, distributive resource control", "2126": "Mathematical logic and foundations", "2127": "Primary 03D10, Secondary 65P20, 68Q05, 68Q87, 68T05", "2128": "Primary 15A66, Secondary 68T40, 62M45, 68U10, 60G35", "2129": "Primary 62G05, 62G08, secondary 62H12", "2130": "Primary 62H30, Secondary 62G10", "2131": "Primary 62H30, Secondary 91C20, 62G07", "2132": "Primary 62H30, secondary 62H25", "2133": "Primary 62J05, Secondary 62F35, 62J07, 62H15", "2134": "Primary 62L05, secondary 62C20", "2135": "Primary: 68T20, Secondary: 60J20", "2136": "Primary: 68W27, 90B99, Secondary: 90B05, 90B50, 90C05", "2137": "Primary: 91A05, 49K35, Secondary: 91A20, 91A15", "2138": "Primary: 94A08. Secondary: 35H10, 53C17", "2139": "Primary: G.4, F.2.2; Secondary: 1.4.7, 1.4.8", "2140": "aaai.org", "2141": "adap-org", "2142": "artificial intelligence, approximate reasoning", "2143": "astro-ph", "2144": "astro-ph.CO", "2145": "astro-ph.EP", "2146": "astro-ph.GA", "2147": "astro-ph.HE", "2148": "astro-ph.IM", "2149": "astro-ph.SR", "2150": "cmp-lg", "2151": "cond-mat", "2152": "cond-mat.dis-nn", "2153": "cond-mat.mes-hall", "2154": "cond-mat.mtrl-sci", "2155": "cond-mat.other", "2156": "cond-mat.quant-gas", "2157": "cond-mat.soft", "2158": "cond-mat.stat-mech", "2159": "cond-mat.str-el", "2160": "cond-mat.supr-con", "2161": "cs.AI", "2162": "cs.AR", "2163": "cs.CC", "2164": "cs.CE", "2165": "cs.CG", "2166": "cs.CL", "2167": "cs.CL, cs.AI, math.CT", "2168": "cs.CR", "2169": "cs.CV", "2170": "cs.CY", "2171": "cs.DB", "2172": "cs.DC", "2173": "cs.DL", "2174": "cs.DM", "2175": "cs.DS", "2176": "cs.ET", "2177": "cs.FL", "2178": "cs.GL", "2179": "cs.GR", "2180": "cs.GT", "2181": "cs.HC", "2182": "cs.IR", "2183": "cs.IT", "2184": "cs.LG", "2185": "cs.LO", "2186": "cs.MA", "2187": "cs.MM", "2188": "cs.MS", "2189": "cs.NA", "2190": "cs.NE", "2191": "cs.NI", "2192": "cs.OH", "2193": "cs.OS", "2194": "cs.PF", "2195": "cs.PL", "2196": "cs.RO", "2197": "cs.SC", "2198": "cs.SD", "2199": "cs.SE", "2200": "cs.SI", "2201": "cs.SY", "2202": "econ.EM", "2203": "eess.AS", "2204": "eess.IV", "2205": "eess.SP", "2206": "gr-qc", "2207": "hep-ex", "2208": "hep-lat", "2209": "hep-ph", "2210": "hep-th", "2211": "math-ph", "2212": "math.AC", "2213": "math.AG", "2214": "math.AP", "2215": "math.AT", "2216": "math.CA", "2217": "math.CO", "2218": "math.CT", "2219": "math.CV", "2220": "math.DG", "2221": "math.DS", "2222": "math.FA", "2223": "math.GM", "2224": "math.GN", "2225": "math.GR", "2226": "math.GT", "2227": "math.HO", "2228": "math.IT", "2229": "math.LO", "2230": "math.MG", "2231": "math.MP", "2232": "math.NA", "2233": "math.NT", "2234": "math.OA", "2235": "math.OC", "2236": "math.PR", "2237": "math.QA", "2238": "math.RA", "2239": "math.RT", "2240": "math.SP", "2241": "math.ST", "2242": "nlin.AO", "2243": "nlin.AO, nlin.CD, q-bio.NC, physics.bio-ph, cond-mat.dis-nn", "2244": "nlin.CD", "2245": "nlin.CG", "2246": "nlin.PS", "2247": "nucl-ex", "2248": "nucl-th", "2249": "physics.ao-ph", "2250": "physics.app-ph", "2251": "physics.bio-ph", "2252": "physics.chem-ph", "2253": "physics.class-ph", "2254": "physics.comp-ph", "2255": "physics.data-an", "2256": "physics.flu-dyn", "2257": "physics.gen-ph", "2258": "physics.geo-ph", "2259": "physics.hist-ph", "2260": "physics.ins-det", "2261": "physics.med-ph", "2262": "physics.optics", "2263": "physics.pop-ph", "2264": "physics.soc-ph", "2265": "physics.space-ph", "2266": "q-bio", "2267": "q-bio.BM", "2268": "q-bio.BM, q-bio.MN, q-bio.NC, nlin.AO, nlin.CD", "2269": "q-bio.CB", "2270": "q-bio.GN", "2271": "q-bio.MN", "2272": "q-bio.NC", "2273": "q-bio.OT", "2274": "q-bio.PE", "2275": "q-bio.QM", "2276": "q-bio.SC", "2277": "q-bio.TO", "2278": "q-fin.CP", "2279": "q-fin.EC", "2280": "q-fin.GN", "2281": "q-fin.PM", "2282": "q-fin.PR", "2283": "q-fin.RM", "2284": "q-fin.ST", "2285": "q-fin.TR", "2286": "quant-ph", "2287": "stat.AP", "2288": "stat.CO", "2289": "stat.ME", "2290": "stat.ML", "2291": "stat.OT", "2292": "stat.TH"}
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ torch
2
+ transformers
3
+ accelerate
transformer_hug_face.ipynb ADDED
@@ -0,0 +1,423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "metadata": {},
7
+ "outputs": [],
8
+ "source": [
9
+ "import os\n",
10
+ "import ast\n",
11
+ "import pandas as pd\n",
12
+ "import kagglehub\n",
13
+ "from kagglehub import KaggleDatasetAdapter"
14
+ ]
15
+ },
16
+ {
17
+ "cell_type": "code",
18
+ "execution_count": 2,
19
+ "metadata": {},
20
+ "outputs": [],
21
+ "source": [
22
+ "# file_path = kagglehub.dataset_download(\"neelshah18/arxivdataset\")\n",
23
+ "# arxiv_df = pd.read_json(os.path.join(file_path, 'arxivData.json'))\n",
24
+ "file_path = \"~/.cache/kagglehub/datasets/neelshah18/arxivdataset/versions/2/arxivData.json\"\n",
25
+ "arxiv_df = pd.read_json(file_path)\n",
26
+ "arxiv_df = arxiv_df.drop(columns=['author', 'day', 'id', 'link', 'month', 'year'])\n",
27
+ "arxiv_df['tag'] = arxiv_df['tag'].apply(ast.literal_eval)\n",
28
+ "arxiv_df = arxiv_df.explode('tag').reset_index(drop=True)\n",
29
+ "arxiv_df['tag'] = arxiv_df['tag'].apply(lambda x: x['term'])\n",
30
+ "arxiv_df['text'] = arxiv_df['title'] + ' ' + arxiv_df['summary']\n",
31
+ "arxiv_df = arxiv_df.drop(columns=['title', 'summary'])\n",
32
+ "arxiv_df = arxiv_df[['text', 'tag']]"
33
+ ]
34
+ },
35
+ {
36
+ "cell_type": "code",
37
+ "execution_count": 3,
38
+ "metadata": {},
39
+ "outputs": [
40
+ {
41
+ "data": {
42
+ "text/html": [
43
+ "<div>\n",
44
+ "<style scoped>\n",
45
+ " .dataframe tbody tr th:only-of-type {\n",
46
+ " vertical-align: middle;\n",
47
+ " }\n",
48
+ "\n",
49
+ " .dataframe tbody tr th {\n",
50
+ " vertical-align: top;\n",
51
+ " }\n",
52
+ "\n",
53
+ " .dataframe thead th {\n",
54
+ " text-align: right;\n",
55
+ " }\n",
56
+ "</style>\n",
57
+ "<table border=\"1\" class=\"dataframe\">\n",
58
+ " <thead>\n",
59
+ " <tr style=\"text-align: right;\">\n",
60
+ " <th></th>\n",
61
+ " <th>text</th>\n",
62
+ " <th>tag</th>\n",
63
+ " </tr>\n",
64
+ " </thead>\n",
65
+ " <tbody>\n",
66
+ " <tr>\n",
67
+ " <th>0</th>\n",
68
+ " <td>Dual Recurrent Attention Units for Visual Ques...</td>\n",
69
+ " <td>cs.AI</td>\n",
70
+ " </tr>\n",
71
+ " <tr>\n",
72
+ " <th>1</th>\n",
73
+ " <td>Dual Recurrent Attention Units for Visual Ques...</td>\n",
74
+ " <td>cs.CL</td>\n",
75
+ " </tr>\n",
76
+ " <tr>\n",
77
+ " <th>2</th>\n",
78
+ " <td>Dual Recurrent Attention Units for Visual Ques...</td>\n",
79
+ " <td>cs.CV</td>\n",
80
+ " </tr>\n",
81
+ " <tr>\n",
82
+ " <th>3</th>\n",
83
+ " <td>Dual Recurrent Attention Units for Visual Ques...</td>\n",
84
+ " <td>cs.NE</td>\n",
85
+ " </tr>\n",
86
+ " <tr>\n",
87
+ " <th>4</th>\n",
88
+ " <td>Dual Recurrent Attention Units for Visual Ques...</td>\n",
89
+ " <td>stat.ML</td>\n",
90
+ " </tr>\n",
91
+ " <tr>\n",
92
+ " <th>5</th>\n",
93
+ " <td>Sequential Short-Text Classification with Recu...</td>\n",
94
+ " <td>cs.CL</td>\n",
95
+ " </tr>\n",
96
+ " <tr>\n",
97
+ " <th>6</th>\n",
98
+ " <td>Sequential Short-Text Classification with Recu...</td>\n",
99
+ " <td>cs.AI</td>\n",
100
+ " </tr>\n",
101
+ " <tr>\n",
102
+ " <th>7</th>\n",
103
+ " <td>Sequential Short-Text Classification with Recu...</td>\n",
104
+ " <td>cs.LG</td>\n",
105
+ " </tr>\n",
106
+ " <tr>\n",
107
+ " <th>8</th>\n",
108
+ " <td>Sequential Short-Text Classification with Recu...</td>\n",
109
+ " <td>cs.NE</td>\n",
110
+ " </tr>\n",
111
+ " <tr>\n",
112
+ " <th>9</th>\n",
113
+ " <td>Sequential Short-Text Classification with Recu...</td>\n",
114
+ " <td>stat.ML</td>\n",
115
+ " </tr>\n",
116
+ " <tr>\n",
117
+ " <th>10</th>\n",
118
+ " <td>Multiresolution Recurrent Neural Networks: An ...</td>\n",
119
+ " <td>cs.CL</td>\n",
120
+ " </tr>\n",
121
+ " <tr>\n",
122
+ " <th>11</th>\n",
123
+ " <td>Multiresolution Recurrent Neural Networks: An ...</td>\n",
124
+ " <td>cs.AI</td>\n",
125
+ " </tr>\n",
126
+ " <tr>\n",
127
+ " <th>12</th>\n",
128
+ " <td>Multiresolution Recurrent Neural Networks: An ...</td>\n",
129
+ " <td>cs.LG</td>\n",
130
+ " </tr>\n",
131
+ " <tr>\n",
132
+ " <th>13</th>\n",
133
+ " <td>Multiresolution Recurrent Neural Networks: An ...</td>\n",
134
+ " <td>cs.NE</td>\n",
135
+ " </tr>\n",
136
+ " <tr>\n",
137
+ " <th>14</th>\n",
138
+ " <td>Multiresolution Recurrent Neural Networks: An ...</td>\n",
139
+ " <td>stat.ML</td>\n",
140
+ " </tr>\n",
141
+ " </tbody>\n",
142
+ "</table>\n",
143
+ "</div>"
144
+ ],
145
+ "text/plain": [
146
+ " text tag\n",
147
+ "0 Dual Recurrent Attention Units for Visual Ques... cs.AI\n",
148
+ "1 Dual Recurrent Attention Units for Visual Ques... cs.CL\n",
149
+ "2 Dual Recurrent Attention Units for Visual Ques... cs.CV\n",
150
+ "3 Dual Recurrent Attention Units for Visual Ques... cs.NE\n",
151
+ "4 Dual Recurrent Attention Units for Visual Ques... stat.ML\n",
152
+ "5 Sequential Short-Text Classification with Recu... cs.CL\n",
153
+ "6 Sequential Short-Text Classification with Recu... cs.AI\n",
154
+ "7 Sequential Short-Text Classification with Recu... cs.LG\n",
155
+ "8 Sequential Short-Text Classification with Recu... cs.NE\n",
156
+ "9 Sequential Short-Text Classification with Recu... stat.ML\n",
157
+ "10 Multiresolution Recurrent Neural Networks: An ... cs.CL\n",
158
+ "11 Multiresolution Recurrent Neural Networks: An ... cs.AI\n",
159
+ "12 Multiresolution Recurrent Neural Networks: An ... cs.LG\n",
160
+ "13 Multiresolution Recurrent Neural Networks: An ... cs.NE\n",
161
+ "14 Multiresolution Recurrent Neural Networks: An ... stat.ML"
162
+ ]
163
+ },
164
+ "execution_count": 3,
165
+ "metadata": {},
166
+ "output_type": "execute_result"
167
+ }
168
+ ],
169
+ "source": [
170
+ "arxiv_df.head(15)"
171
+ ]
172
+ },
173
+ {
174
+ "cell_type": "code",
175
+ "execution_count": 65,
176
+ "metadata": {},
177
+ "outputs": [],
178
+ "source": [
179
+ "import torch\n",
180
+ "from sklearn.preprocessing import LabelEncoder\n",
181
+ "from torch.utils.data import Dataset, DataLoader, random_split\n",
182
+ "\n",
183
+ "class ArticleDataset(Dataset):\n",
184
+ " def __init__(self, data, tokenizer, label_encoder, max_length=256):\n",
185
+ " self.tokenizer = tokenizer\n",
186
+ " self.label_encoder = label_encoder\n",
187
+ " self.max_length = max_length\n",
188
+ " self.texts = data['text'].to_list()\n",
189
+ " self.labels = torch.tensor(self.label_encoder.fit_transform(data['tag'].to_list()))\n",
190
+ " assert len(self.texts) == len(self.labels)\n",
191
+ " \n",
192
+ " def __getitem__(self, index):\n",
193
+ " encoded_text = self.tokenizer(\n",
194
+ " self.texts[index],\n",
195
+ " padding=\"max_length\",\n",
196
+ " truncation=True,\n",
197
+ " max_length=self.max_length,\n",
198
+ " return_tensors=\"pt\"\n",
199
+ " )\n",
200
+ " return encoded_text['input_ids'].squeeze(0), encoded_text['attention_mask'].squeeze(0), self.labels[index]\n",
201
+ "\n",
202
+ " def __len__(self):\n",
203
+ " return len(self.labels)"
204
+ ]
205
+ },
206
+ {
207
+ "cell_type": "code",
208
+ "execution_count": 66,
209
+ "metadata": {},
210
+ "outputs": [],
211
+ "source": [
212
+ "import torch.optim as optim\n",
213
+ "from transformers import DistilBertTokenizer, DistilBertForSequenceClassification\n",
214
+ "\n",
215
+ "tokenizer = DistilBertTokenizer.from_pretrained(\"distilbert-base-cased\")\n",
216
+ "label_encoder = LabelEncoder()\n",
217
+ "\n",
218
+ "dataset = ArticleDataset(arxiv_df, tokenizer, label_encoder)\n",
219
+ "\n",
220
+ "train_dataset, test_dataset = random_split(dataset, [0.8, 0.2])\n",
221
+ "train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
222
+ "test_loader = DataLoader(test_dataset, batch_size=32)"
223
+ ]
224
+ },
225
+ {
226
+ "cell_type": "code",
227
+ "execution_count": 67,
228
+ "metadata": {},
229
+ "outputs": [
230
+ {
231
+ "name": "stderr",
232
+ "output_type": "stream",
233
+ "text": [
234
+ "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-cased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']\n",
235
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
236
+ ]
237
+ }
238
+ ],
239
+ "source": [
240
+ "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
241
+ "\n",
242
+ "model = DistilBertForSequenceClassification.from_pretrained(\"distilbert-base-cased\", num_labels=len(label_encoder.classes_))\n",
243
+ "model = model.to(device)\n",
244
+ "optimizer = optim.Adam(model.parameters(), lr=2e-5)"
245
+ ]
246
+ },
247
+ {
248
+ "cell_type": "code",
249
+ "execution_count": 71,
250
+ "metadata": {},
251
+ "outputs": [],
252
+ "source": [
253
+ "from IPython.display import clear_output\n",
254
+ "import matplotlib.pyplot as plt\n",
255
+ "from tqdm import tqdm\n",
256
+ "\n",
257
+ "train_losses = []\n",
258
+ "train_accuracies = []\n",
259
+ "\n",
260
+ "os.makedirs(\"checkpoints\", exist_ok=True)\n",
261
+ "\n",
262
+ "def train(model, epochs):\n",
263
+ " model.train()\n",
264
+ " for epoch in range(epochs):\n",
265
+ " print(f\"\\nEpoch {epoch+1}/{epochs}\")\n",
266
+ " \n",
267
+ " total_loss = 0\n",
268
+ " correct = 0\n",
269
+ " total = 0\n",
270
+ "\n",
271
+ " for input_ids, attn_mask, labels in tqdm(train_loader):\n",
272
+ " input_ids = input_ids.to(device)\n",
273
+ " attn_mask = attn_mask.to(device)\n",
274
+ " labels = labels.to(device)\n",
275
+ "\n",
276
+ " outputs = model(input_ids, attention_mask=attn_mask, labels=labels)\n",
277
+ " loss = outputs.loss\n",
278
+ " logits = outputs.logits\n",
279
+ "\n",
280
+ " total_loss += loss.item()\n",
281
+ " preds = torch.argmax(logits, dim=1)\n",
282
+ " correct += (preds == labels).sum().item()\n",
283
+ " total += labels.size(0)\n",
284
+ "\n",
285
+ " optimizer.zero_grad()\n",
286
+ " loss.backward()\n",
287
+ " optimizer.step()\n",
288
+ "\n",
289
+ " # Средний loss и accuracy за эпоху\n",
290
+ " avg_loss = total_loss / len(train_loader)\n",
291
+ " accuracy = correct / total\n",
292
+ "\n",
293
+ " train_losses.append(avg_loss)\n",
294
+ " train_accuracies.append(accuracy)\n",
295
+ "\n",
296
+ " print(f\"Loss: {avg_loss:.4f} | Accuracy: {accuracy:.4f}\")\n",
297
+ "\n",
298
+ " # График потерь\n",
299
+ " clear_output(True)\n",
300
+ " plt.figure(figsize=(10, 4))\n",
301
+ " plt.subplot(1, 2, 1)\n",
302
+ " plt.plot(train_losses, marker='o')\n",
303
+ " plt.title(\"Training Loss\")\n",
304
+ " plt.xlabel(\"Epoch\")\n",
305
+ " plt.ylabel(\"Loss\")\n",
306
+ "\n",
307
+ " # График точности\n",
308
+ " plt.subplot(1, 2, 2)\n",
309
+ " plt.plot(train_accuracies, marker='o', color='green')\n",
310
+ " plt.title(\"Training Accuracy\")\n",
311
+ " plt.xlabel(\"Epoch\")\n",
312
+ " plt.ylabel(\"Accuracy\")\n",
313
+ "\n",
314
+ " plt.tight_layout()\n",
315
+ " plt.show()\n",
316
+ "\n",
317
+ " # Сохраняем чекпойнт\n",
318
+ " if (epoch + 1) % 4 == 0:\n",
319
+ " checkpoint_path = f\"checkpoints/epoch_{epoch+1}.pt\"\n",
320
+ " torch.save(model.state_dict(), checkpoint_path)\n",
321
+ " print(f\"Saved checkpoint: {checkpoint_path}\")\n",
322
+ "\n",
323
+ " return model"
324
+ ]
325
+ },
326
+ {
327
+ "cell_type": "code",
328
+ "execution_count": 83,
329
+ "metadata": {},
330
+ "outputs": [],
331
+ "source": [
332
+ "import json\n",
333
+ "\n",
334
+ "dict_to_save = {}\n",
335
+ "for ind, el in enumerate(label_encoder.classes_):\n",
336
+ " dict_to_save[ind] = el\n",
337
+ "\n",
338
+ "with open('checkpoints/labels_info.json', 'w') as f:\n",
339
+ " json.dump(dict_to_save, f)"
340
+ ]
341
+ },
342
+ {
343
+ "cell_type": "code",
344
+ "execution_count": 72,
345
+ "metadata": {},
346
+ "outputs": [
347
+ {
348
+ "name": "stdout",
349
+ "output_type": "stream",
350
+ "text": [
351
+ "Обучаемых параметров: 2353909\n"
352
+ ]
353
+ }
354
+ ],
355
+ "source": [
356
+ "for param in model.distilbert.parameters():\n",
357
+ " param.requires_grad = False\n",
358
+ "\n",
359
+ "# Размораживаем только последний слой\n",
360
+ "# for param in model.distilbert.transformer.layer[-1].parameters():\n",
361
+ "# param.requires_grad = True\n",
362
+ "\n",
363
+ "# Также размораживаем классификационную голову\n",
364
+ "for param in model.classifier.parameters():\n",
365
+ " param.requires_grad = True\n",
366
+ " \n",
367
+ "def count_trainable_params(model):\n",
368
+ " total = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
369
+ " return total\n",
370
+ "\n",
371
+ "print(\"Обучаемых параметров:\", count_trainable_params(model))"
372
+ ]
373
+ },
374
+ {
375
+ "cell_type": "code",
376
+ "execution_count": 73,
377
+ "metadata": {},
378
+ "outputs": [
379
+ {
380
+ "data": {
381
+ "image/png": "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",
382
+ "text/plain": [
383
+ "<Figure size 1000x400 with 2 Axes>"
384
+ ]
385
+ },
386
+ "metadata": {},
387
+ "output_type": "display_data"
388
+ },
389
+ {
390
+ "name": "stdout",
391
+ "output_type": "stream",
392
+ "text": [
393
+ "Saved checkpoint: checkpoints/epoch_8.pt\n"
394
+ ]
395
+ }
396
+ ],
397
+ "source": [
398
+ "model = train(model=model, epochs=8)"
399
+ ]
400
+ }
401
+ ],
402
+ "metadata": {
403
+ "kernelspec": {
404
+ "display_name": "my_env",
405
+ "language": "python",
406
+ "name": "python3"
407
+ },
408
+ "language_info": {
409
+ "codemirror_mode": {
410
+ "name": "ipython",
411
+ "version": 3
412
+ },
413
+ "file_extension": ".py",
414
+ "mimetype": "text/x-python",
415
+ "name": "python",
416
+ "nbconvert_exporter": "python",
417
+ "pygments_lexer": "ipython3",
418
+ "version": "3.12.3"
419
+ }
420
+ },
421
+ "nbformat": 4,
422
+ "nbformat_minor": 2
423
+ }