{ "version": "1.0", "source_chunks_path": "01_chunks.json", "strategy": { "front_ratio": 0.15, "middle_positions": [ 0.25, 0.5, 0.75 ], "tail_ratio": 0.1, "high_density_limit": 30, "front_cap": 12, "tail_cap": 8, "middle_radius": 1, "preview_chars": 220 }, "samples": [ { "sample_id": "OS0001", "chunk_id": "C0001", "start_para": 1, "end_para": 14, "sampling_reason": "front_loaded", "char_len": 2193, "text_preview": "楔子 張天師祈禳瘟疫 洪太尉誤走妖魔 紛紛五代亂離間，一旦雲開復見天！草木百年新雨露，車書萬里舊江山。尋常巷陌陳羅綺，幾處樓臺奏管絃。天下太平無事日，鶯花無限日高眠。 話說這八句詩乃是故宋神宗天子朝中一個名儒，姓邵，諱堯夫，道號康節先生所作；為歎五代殘唐，天下干戈不息。那時朝屬梁，暮屬晉，正謂是： 朱李石劉郭，梁唐晉漢周：都來十五帝，播亂五十秋。 後來感得天道循環，向甲馬營中生下太祖武德皇帝來，這朝聖人出世，紅光滿天，異香經宿不散，乃是...", "chunk_index": 1, "all_reasons": [ "front_loaded", "high_entity_density" ], "density_score": 5.5, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "如今東京柴世宗讓位與趙檢點登基", "天下從此定矣！正乃上合天心，下合地理，中合人和", "文有文曲，武有武曲", "三登之世", "有事出班早奏，無事卷簾退朝", "天師今在何處", "目今天子宣詔，如何得見真人" ], "named_places": [ "騎驢下山", "步行上山" ], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [ "騎驢下山", "步行上山" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 7, "named_places": 2, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 2 } } }, { "sample_id": "OS0002", "chunk_id": "C0002", "start_para": 14, "end_para": 22, "sampling_reason": "front_loaded", "char_len": 2110, "text_preview": "太尉居中坐下，執事人等獻茶，就進齋供，水陸俱備。齋罷，太尉再問真人道：「既然天師在山頂庵中，何下著人請將下來相見，開宣丹詔？」真人稟道：「這代祖師雖在山頂，其實道行非常：能駕霧興雲，蹤跡不定。貧道等時常亦難得見，怎生教人請得下來？」太尉道：「似此如何得見？目今京師瘟疫盛行，今上天子特遣下官齎捧御書丹詔，親捧龍香，來請天師，要做三千六百分羅天大醮以禳天災，救濟萬民。似此怎生奈何？」真人稟道：「天子要救萬民，只除是太尉辦一點志誠心，齋戒沐浴...", "chunk_index": 2, "all_reasons": [ "front_loaded", "high_entity_density" ], "density_score": 5.5, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "太尉要救萬民，休生退悔之心，只顧志誠上去", "阿呀", "皇帝御限，差俺來這裏，教我受這場驚恐", "我今番死也", "慚愧！驚殺下官", "你從那裏來？認得我麽", "你來此問，莫非要見天師麽", "你是牧童，如何得知" ], "named_places": [ "步行上山", "送到後山" ], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [ "步行上山", "送到後山" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 14, "named_places": 2, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 2 } } }, { "sample_id": "OS0003", "chunk_id": "C0003", "start_para": 22, "end_para": 35, "sampling_reason": "middle_stratified", "char_len": 2065, "text_preview": "洪太尉道：「我直如此有眼不識真師，當面錯過！」真人道：「太尉，且請放心。既然祖師法旨道是去了，比及太尉回京之日，這場醮事，祖師已都完了。」太尉見說，方纔放心。真人一面教安排筵宴管待太尉，請將丹詔收藏於御書匣內，留在上清宮中；龍香就三清殿上燒了。當日方丈內大排齋供，設宴飲酌。至晚席罷，止宿到曉。 次日早膳已後，真人道衆並提點執事人等請太尉遊山。太尉大喜。許多人從跟隨著，步行出方丈，前面兩個道童引路，行至宮前宮後，看翫許多景致。三清殿上，富...", "chunk_index": 3, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 29.5, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "我直如此有眼不識真師，當面錯過", "伏魔之殿", "如何上面重重疊疊貼著許多封皮", "你且開門來，我看魔王甚麽模樣", "遇洪而開", "太尉，不可掘動，恐有利害，傷犯於人，不當穩便", "恐有不好", "不可掘動" ], "named_places": [ "九天殿", "紫微殿", "北極殿", "太乙殿", "三官殿", "驅邪殿", "伏魔之殿", "進得汴梁城" ], "titled_people": [], "organizations": [ "九天殿", "紫微殿", "北極殿", "太乙殿", "三官殿", "驅邪殿", "伏魔之殿", "有分教" ], "artifacts": [], "term_highlights": [ "九天殿", "紫微殿", "北極殿", "太乙殿", "三官殿", "驅邪殿", "伏魔之殿", "進得汴梁城", "有分教" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 9, "named_places": 8, "titled_people": 0, "organizations": 8, "artifacts": 0, "conservative_terms": 9 } } }, { "sample_id": "OS0004", "chunk_id": "C0004", "start_para": 35, "end_para": 44, "sampling_reason": "middle_stratified", "char_len": 2136, "text_preview": "第一回 王教頭私走延安府 九紋龍大鬧史家村 話說故宋，哲宗皇帝在時，其時去仁宗天子已遠，東京，開封府，汴梁，宣武軍便有一個浮浪破落戶子弟，姓高，排行第二，自小不成家業，只好刺鎗使棒，最是得好腳氣毬。京師人口順，不叫高二，卻都叫他做高毬。後來發跡，便將氣毬那字去了「毛傍」，添作「立人」，改作姓高，名俅。這人吹彈歌舞，刺鎗使棒，相撲頑耍，亦胡亂學詩書詞賦；若論仁義禮智，信行忠良，卻是不會，只在東京城裏城外幫閒。 因幫了一個生鐵王員外兒子使錢...", "chunk_index": 4, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 7.1, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "毛傍", "立人", "日遠日疏，日親日近", "深謝厚意；想那筆架必是更妙", "明日取出來送至宮中便見", "小人是王駙馬府中特送玉玩器來進大王", "殿下在庭心裏和小黃門踢氣毬，你自過去", "相煩引進" ], "named_places": [ "開封府", "臨淮州" ], "titled_people": [], "organizations": [ "開封府" ], "artifacts": [], "term_highlights": [ "開封府", "臨淮州" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 14, "named_places": 2, "titled_people": 0, "organizations": 1, "artifacts": 0, "conservative_terms": 2 } } }, { "sample_id": "OS0005", "chunk_id": "C0005", "start_para": 44, "end_para": 50, "sampling_reason": "middle_stratified", "char_len": 2195, "text_preview": "那端王且不理玉玩器下落，卻先問高俅道：「你原來會踢氣毬？你喚做甚麽？」高俅叉手跪覆道：「小的叫做高俅，胡亂踢得幾腳。」端王道：「好，你便下場來踢一回耍。」高俅拜道：「小的是何等樣人，敢與恩王下腳！」端王道：「這是齊雲社，名爲天下圓，但踼何傷。」高俅再拜道：「怎敢。」三回五次告辭，端王定要他踼，高俅只得叩頭謝罪，解膝下場。纔踼幾腳，端王喝采，高俅只得把平生本事都使出來奉承端王，那身分，模樣，這氣毬一似鰾膠黏在身上的！端王大喜，那肯放高俅回...", "chunk_index": 5, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 1.9, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "你原來會踢氣毬？你喚做甚麽", "這是齊雲社，名爲天下圓，但踼何傷", "怎敢", "這高俅踢得兩腳好氣毬，孤欲索此人做親隨，如何", "既殿下欲用此人，就留在宮中伏侍殿下", "小人便是", "小人怎敢；其實患病未痊", "賊配軍！你既害病，如何來得" ], "named_places": [], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 15, "named_places": 0, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 0 } } }, { "sample_id": "OS0006", "chunk_id": "C0006", "start_para": 50, "end_para": 54, "sampling_reason": "middle_stratified", "char_len": 1449, "text_preview": "且說兩個牌軍買了福物煮熟，在廟等到巳牌，也不見來。李牌心焦，走回到家中尋時，只見鎖了門，兩頭無路，尋了半日，並無有人。看看待晚，嶽廟裏張牌疑忌，一直奔回家來，又和李牌尋了一黃昏。看看黑了，兩個見他當夜不歸，又不見了他老娘。次日，兩個牌軍又去他親戚之家訪問，亦無尋處。兩個恐怕連累，只得去殿帥府首告：「王教頭棄家在逃，母子不知去向。」高太尉見告，大怒道：「賊配軍在逃，看那廝待走那裏去！」隨即押下文書，行開諸州各府捉拿逃軍王進。二人首告，免其...", "chunk_index": 6, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 3.662, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "王教頭棄家在逃，母子不知去向", "賊配軍在逃，看那廝待走那裏去", "來俺莊上有甚事", "大哥方便", "莊主太公教你兩個入來", "村落中無甚相待，休得見怪", "小人母子無故相擾，此恩難報", "休這般說，且請喫酒" ], "named_places": [ "前不巴村" ], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [ "前不巴村" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 10, "named_places": 1, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 1 } } }, { "sample_id": "OS0007", "chunk_id": "C0007", "start_para": 54, "end_para": 58, "sampling_reason": "middle_stratified", "char_len": 2025, "text_preview": "次日，睡到天曉，不見起來。莊主太公來到客房前過，聽得王進老母在房裏聲喚。太公問道：「客官，天曉好起了？」王進聽得，慌忙出房來見太公，施禮說道：「小人起多時了。夜來多多攪擾，甚是不當。」太公問道：「誰人如此聲喚？」王進道：「實不相瞞太公說，老母鞍馬勞倦，昨夜心痛病發。」太公道：「即然如此，客人休要煩惱，教你老母且在老夫莊上住幾日。我有個醫心痛的方，叫莊客去縣裏撮藥來與你老母親喫。教他放心慢慢地將息。」王進謝了。 話休絮繁。自此，王進母子二...", "chunk_index": 7, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 3.9, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "誰人如此聲喚", "實不相瞞太公說，老母鞍馬勞倦，昨夜心痛病發", "不得無禮", "客人莫不會使鎗棒", "頗曉得些。敢問長上，這後生是宅上何人", "來拜師父", "你來！你來！怕你不算好漢", "恕無禮" ], "named_places": [], "titled_people": [], "organizations": [ "只得請教" ], "artifacts": [], "term_highlights": [ "只得請教" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 11, "named_places": 0, "titled_people": 0, "organizations": 1, "artifacts": 0, "conservative_terms": 1 } } }, { "sample_id": "OS0008", "chunk_id": "C0008", "start_para": 58, "end_para": 62, "sampling_reason": "middle_stratified", "char_len": 2102, "text_preview": "不覺荏苒光陰，早過半年之上。史進十八般武藝，──矛，錘，弓，弩，銃，鞭，簡註：金字旁間，劍，鏈，撾，斧，鉞并戈，戟，牌，棒與鎗，扒，一一學得精熟。多得王進盡心指教，點撥得件件都有奧妙。王進見他學得精熟了，自思在此雖好，只是不了；一日，想起來，相辭要上延安府去。史進那裏肯放，說道：「師父只在此間過了。小弟奉養你母子二人以終天年，多少是好。」王進道：「賢弟，多蒙你好心，在此十分之好；只恐高太尉追捕到來，負累了你，不當穩便；以此兩難。我一心要...", "chunk_index": 8, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 5.3, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "好涼風", "作怪！誰在那裏張俺莊上", "李吉，張我莊內做甚麽？莫不是來相腳頭", "這廝們大弄，必要來薅惱村坊。既然如此．．．", "順溜紙", "我等村農只靠大郎做主，梆子響時，誰敢不來", "說得是。如今便去華陰縣裏先問他借糧，看他如何" ], "named_places": [ "安排莊院" ], "titled_people": [], "organizations": [ "安排莊院" ], "artifacts": [], "term_highlights": [ "安排莊院" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 7, "named_places": 1, "titled_people": 0, "organizations": 1, "artifacts": 0, "conservative_terms": 1 } } }, { "sample_id": "OS0009", "chunk_id": "C0009", "start_para": 62, "end_para": 65, "sampling_reason": "middle_stratified", "char_len": 1688, "text_preview": "且說少華山寨中三個頭領坐定商議：爲頭的神機軍師朱武，那人原是定遠人氏，能使兩口雙刀，雖無十分本事，郤精通陣法，廣有謀略；第二個好漢，姓陳，名達，原是鄴城人氏，使一條出白點鋼鎗；第三個好漢，姓楊，名春，蒲州解良縣人氏，使一口大桿刀。當日朱武郤與陳達，楊春說道：「如今我聽知華陰縣裏出三千賞錢，召人捉我們，誠恐來時要與他廝殺。只是山寨錢糧欠少，如何不去劫擄些來，以供山寨之用？聚積些糧食在寨裏，防備官軍來時，好和他打熬。」跳澗虎陳達道：「說得是...", "chunk_index": 9, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 1.9, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "說得是。如今便去華陰縣裏先問他借糧，看他如何", "好漢，叫我問誰", "你問得我手裏這口刀肯，便放你去", "趕人不要趕上！休得要逞精神", "怎當史進英雄", "我們盡數都去與他死拼，如何", "如何苦計", "只除恁地，．．．" ], "named_places": [], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 9, "named_places": 0, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 0 } } }, { "sample_id": "OS0010", "chunk_id": "C0010", "start_para": 65, "end_para": 72, "sampling_reason": "middle_stratified", "char_len": 2186, "text_preview": "休說衆人歡喜飲酒。卻說朱武、楊春，兩個正在寨裏猜疑，捉摸不定，且教小嘍囉再去探聽消息。只見回去的人牽著空馬，奔到山前，只叫道：「苦也！陳家哥哥不聽二位哥哥所說，送了性命！」朱武問其緣故。小嘍羅備說交鋒一節，「怎當史進英雄！」朱武道：「我的言語不聽，果有此禍！」楊春道：「我們盡數都去與他死拼，如何？」朱武道：「亦是不可；他尚自輸了，你如何拼得他過？我有一條苦計，若救他不得，我和你都休。」楊春問道：「如何苦計？」朱武附耳低言說道：「只除恁地...", "chunk_index": 10, "all_reasons": [ "middle_stratified", "high_entity_density" ], "density_score": 1.9, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "怎當史進英雄", "我們盡數都去與他死拼，如何", "如何苦計", "只除恁地，．．．", "好計！我和你便去！事不宜遲", "你兩個跪下如何說", "不求同日生，只願同日死", "大蟲不吃伏肉" ], "named_places": [], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 15, "named_places": 0, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 0 } } }, { "sample_id": "OS0011", "chunk_id": "C0011", "start_para": 72, "end_para": 82, "sampling_reason": "tail_stratified", "char_len": 2117, "text_preview": "卻說莊客王四一覺直睡到二更方醒，覺來看見月光微微照在身上，吃了一驚，跳將起來，卻見四邊都是松樹；便去腰裏摸時，搭膊和書都不見了；四下裏尋時，只見空搭膊在莎草地上。王四只管叫苦，尋思道：「銀子不打緊，這封回書卻怎生得好？．．．正不知被甚人拿去了？．．．」眉頭一縱，計上心來，自道：「若回去莊上說脫了回書，大郎必然焦躁，定是趕我出來；不如只說不曾有回書，那裏查照？」計較定了，飛也似取路歸來莊上，卻好五更天氣。 史進見王四回來，問道：「你緣何方...", "chunk_index": 11, "all_reasons": [ "tail_stratified", "high_entity_density" ], "density_score": 9.1, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "你緣何方才歸來", "曾有回書麽", "既然如此，教人去縣裏買些果品案酒伺候", "不要開門", "卻怎生是好", "大郎，你兀自賴哩！見有原告人李吉在這裏", "李吉，你如何誣告平人", "你說無回書，如何卻又有書" ], "named_places": [ "步行下山", "圍住莊院" ], "titled_people": [], "organizations": [ "圍住莊院", "直教" ], "artifacts": [], "term_highlights": [ "步行下山", "圍住莊院", "直教" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 11, "named_places": 2, "titled_people": 0, "organizations": 2, "artifacts": 0, "conservative_terms": 3 } } }, { "sample_id": "OS0012", "chunk_id": "C0012", "start_para": 82, "end_para": 87, "sampling_reason": "tail_stratified", "char_len": 1874, "text_preview": "一連過了幾日，史進尋思：「一時間要救三人，放火燒了莊院。雖是有些細軟家財，麤重雜物，盡皆沒了！」心內躊躇，在此不了，開言對朱武等說道：「我師父王教頭在關西經略府勾當，我先要去尋他，只因父親死了，不曾去得；今來家私莊院廢盡，我如今要去尋他。」朱武三人道：「哥哥休去，只在我寨中且過幾日，又作商議。若哥哥不願落草時，待平靜了，小弟們與哥哥重整莊院，再作良民。」史進道：「雖是你們的好情分，只是我今去意難留。我若尋得師父，也要那裏討個出身，求半世...", "chunk_index": 12, "all_reasons": [ "tail_stratified", "high_entity_density" ], "density_score": 3.7, "signal_terms": { "chapter_headings": [], "quoted_phrases": [ "這裏也有個經略府，莫非師父王教頭在這裏", "客官，喫甚茶", "喫個泡茶", "這裏經略府在何處", "只在前面便是", "客官，要尋王教頭，只問這位提轄，便都認得", "客官，請坐，拜茶", "師父，多時不見" ], "named_places": [ "來到渭州" ], "titled_people": [], "organizations": [], "artifacts": [], "term_highlights": [ "來到渭州" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 14, "named_places": 1, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 1 } } } ], "stats": { "chunk_count": 12, "sample_count": 12, "counts_by_primary_reason": { "front_loaded": 2, "middle_stratified": 8, "tail_stratified": 2 }, "counts_by_any_reason": { "front_loaded": 2, "high_entity_density": 12, "middle_stratified": 8, "tail_stratified": 2 }, "top_density_chunks": [ { "chunk_id": "C0003", "chunk_index": 3, "density_score": 29.5, "term_highlights": [ "九天殿", "紫微殿", "北極殿", "太乙殿", "三官殿", "驅邪殿" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 9, "named_places": 8, "titled_people": 0, "organizations": 8, "artifacts": 0, "conservative_terms": 9 } }, { "chunk_id": "C0011", "chunk_index": 11, "density_score": 9.1, "term_highlights": [ "步行下山", "圍住莊院", "直教" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 11, "named_places": 2, "titled_people": 0, "organizations": 2, "artifacts": 0, "conservative_terms": 3 } }, { "chunk_id": "C0004", "chunk_index": 4, "density_score": 7.1, "term_highlights": [ "開封府", "臨淮州" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 14, "named_places": 2, "titled_people": 0, "organizations": 1, "artifacts": 0, "conservative_terms": 2 } }, { "chunk_id": "C0001", "chunk_index": 1, "density_score": 5.5, "term_highlights": [ "騎驢下山", "步行上山" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 7, "named_places": 2, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 2 } }, { "chunk_id": "C0002", "chunk_index": 2, "density_score": 5.5, "term_highlights": [ "步行上山", "送到後山" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 14, "named_places": 2, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 2 } }, { "chunk_id": "C0008", "chunk_index": 8, "density_score": 5.3, "term_highlights": [ "安排莊院" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 7, "named_places": 1, "titled_people": 0, "organizations": 1, "artifacts": 0, "conservative_terms": 1 } }, { "chunk_id": "C0007", "chunk_index": 7, "density_score": 3.9, "term_highlights": [ "只得請教" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 11, "named_places": 0, "titled_people": 0, "organizations": 1, "artifacts": 0, "conservative_terms": 1 } }, { "chunk_id": "C0012", "chunk_index": 12, "density_score": 3.7, "term_highlights": [ "來到渭州" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 14, "named_places": 1, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 1 } }, { "chunk_id": "C0006", "chunk_index": 6, "density_score": 3.662, "term_highlights": [ "前不巴村" ], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 10, "named_places": 1, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 1 } }, { "chunk_id": "C0005", "chunk_index": 5, "density_score": 1.9, "term_highlights": [], "signal_counts": { "chapter_headings": 0, "quoted_phrases": 15, "named_places": 0, "titled_people": 0, "organizations": 0, "artifacts": 0, "conservative_terms": 0 } } ] }, "resolved_strategy": { "front_count": 2, "tail_count": 2, "middle_radius": 1, "preview_chars": 220 } }