library(dplyr)
library(tibble)
library(knitr)
library(kableExtra)

# Unique topics per author
majid_topics        <- unique(majid_works_long$topic)
abbasi_topics       <- unique(abbasi_works_long$topic)
masoud_topics       <- unique(masoud_works_long$topic)
hosseinpour_topics  <- unique(hosseinpour_works_long$topic)

# Helper to pad columns with '---'
pad_column <- function(x, n) { length(x) <- n; x[is.na(x)] <- "---"; x }

# Height of the table (max col length)
n <- max(length(majid_topics), length(abbasi_topics), length(masoud_topics), length(hosseinpour_topics))

topics_4col_all <- tibble(
  `M. Shahriari`      = pad_column(majid_topics,       n),
  `F. Abbasi Davani`  = pad_column(abbasi_topics,      n),
  `M. Alimohammadi`   = pad_column(masoud_topics,      n),
  `A. Hosseinpour`    = pad_column(hosseinpour_topics, n)
)

# Append counts row at the bottom
topics_4col_all <- bind_rows(
  topics_4col_all,
  tibble(
    `M. Shahriari`      = paste0("n = ", length(majid_topics)),
    `F. Abbasi Davani`  = paste0("n = ", length(abbasi_topics)),
    `M. Alimohammadi`   = paste0("n = ", length(masoud_topics)),
    `A. Hosseinpour`    = paste0("n = ", length(hosseinpour_topics))
  )
)

# Render (HTML)
kable(
  topics_4col_all,
  caption = "Unique Topics per Author"
) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped","hover"))

library(dplyr)
library(purrr)
library(tibble)
library(stringr)

# Your unique topic vectors
# majid_topics, abbasi_topics, masoud_topics, hosseinpour_topics

sets <- list(
  Majid       = majid_topics,
  Abbasi      = abbasi_topics,
  Masoud      = masoud_topics,
  Hosseinpour = hosseinpour_topics
)

# Helper: count intersections for all combinations of given sizes
combo_counts <- function(sets, sizes = 2:length(sets)) {
  map_dfr(sizes, function(k) {
    combn(names(sets), k, simplify = FALSE) %>%
      map_dfr(function(nms) {
        inter <- Reduce(intersect, sets[nms])
        tibble(
          Size        = k,
          Combination = paste(nms, collapse = " & "),
          n_topics    = length(inter)
          # If you also want to inspect which topics, add:
          # Topics      = list(inter)
        )
      })
  }) %>%
    arrange(Size, desc(n_topics), Combination)
}

# Build the table (pairs, triples, all four)
overlap_table <- combo_counts(sets, sizes = 2:4)

# Show the table
overlap_table

library(dplyr)

targets <- c(
  "Atomic and Subatomic Physics Research",
  "Nuclear Physics and Applications",
  "Pulsed Power Technology Applications"
)


# Set the full path to your file
file_path <- "/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic/extra_data/shahid_beheshti_university_cleanedLONG.rds"

# Read the RDS file
shahid_beheshti_university_cleanedLONG <- readRDS(file_path)


# 1) Papers that appear at least 3 times in the LONG table
titles_3plus <- shahid_beheshti_university_cleanedLONG %>%
  group_by(title) %>% mutate(n_rows_title = n()) %>% ungroup() %>%
  filter(n_rows_title >= 3)

# 2) Among those, papers that have at least one of the target topics
candidate_titles <- titles_3plus %>%
  filter(topic %in% targets) %>%
  group_by(topic, title) %>%
  summarise(
    n_rows_title = first(n_rows_title),
    first_date   = suppressWarnings(min(publication_date, na.rm = TRUE)),
    .groups = "drop"
  ) %>%
  arrange(factor(topic, levels = targets), desc(n_rows_title), first_date)

# Choose ONE paper per target topic
chosen_titles <- candidate_titles %>%
  group_by(topic) %>% slice_head(n = 1) %>% ungroup()
# chosen_titles has the 3 titles (one per topic)

# 3) For each chosen title, keep the 3 rows for that paper (join by title ONLY)
result_9_rows <- titles_3plus %>%
  semi_join(chosen_titles, by = "title") %>%      # pull all rows for those titles
  group_by(title) %>% slice_head(n = 3) %>% ungroup() %>%
  # attach which target-topic this title was selected for (so we can order nicely)
  left_join(chosen_titles %>% select(target_topic = topic, title), by = "title") %>%
  select(target_topic, id, title, publication_date, topic, score, type, institution) %>%
  arrange(factor(target_topic, levels = targets), title, publication_date)

# Sanity checks
nrow(result_9_rows)                  # should be 9 (3 rows x 3 papers)

table(result_9_rows$target_topic)    # should be 3 per target topic

library(dplyr)
library(kableExtra)

# 1) Keep only the requested columns
result_9_rows_min <- result_9_rows %>%
  select(id, title, publication_date, topic, score) %>%
  arrange(title, publication_date)

# (Optional) nice column labels + light formatting
result_9_rows_min <- result_9_rows_min %>%
  mutate(
    publication_date = as.character(publication_date),
    score = round(score, 4)
  )

# 2) Build LaTeX table
library(kableExtra)

tbl_topics <- result_9_rows_min %>%
  kbl(
    caption  = "Sample of three nuclear-related works from Shahid Beheshti University.",
    format   = "latex",
    booktabs = TRUE,
    col.names = c("ID", "Title", "Publication Date", "Topic", "Topic Score")
  ) %>%
  kable_styling(
    latex_options = c("hold_position", "scale_down"),
    font_size     = 10
  ) %>%
  kableExtra::footnote(
    general = "Note: Sample data shown in long format as used for DiD format. One row per work-topic, where the Topic Score is OpenAlex classifier confidence score.",
    footnote_as_chunk = TRUE
  )


# 3) Save table to .tex file
writeLines(tbl_topics, file.path(data_path, "sbu_example_works_topics.tex"))

library(kableExtra)

# Your palette
layer_colors <- c(
  "Majid"  = "#587CA0",  # blue-gray
  "Abbasi" = "#B3C7D6",  # light blue-gray
  "Masoud" = "#808080"   # base gray (we'll use 50% over white -> #C0C0C0)
)
masoud_50_over_white <- "#C0C0C0"  # 50% alpha of #808080 on white

tbl_topics <- result_9_rows_min %>%
  kbl(
    caption  = "Sample of three nuclear-related works from Shahid Beheshti University (OpenAlex).",
    format   = "latex",
    booktabs = TRUE,
    col.names = c("ID", "Title", "Publication Date", "Topic", "Topic Score")
  ) %>%
  kable_styling(
    latex_options = c("hold_position", "scale_down"),
    font_size     = 10
  ) %>%
  # Shade rows by blocks of 3
  row_spec(1:3, background = layer_colors["Majid"],  color = "white") %>%  # darker bg -> white text
  row_spec(4:6, background = layer_colors["Abbasi"]) %>%
  row_spec(7:9, background = masoud_50_over_white)%>%
  kableExtra::footnote(
    general = "Note: Sample data shown in long format as used for DiD format. One row per work-topic, where the Topic Score is OpenAlex classifier confidence score.",
    footnote_as_chunk = TRUE
  )

writeLines(tbl_topics, file.path(data_path, "sbu_example_works_topics.tex"))

library(dplyr)
library(tibble)
library(knitr)
library(kableExtra)

# Limit each author’s topics to the first 30
majid_topics_top30       <- head(majid_topics, 30)
abbasi_topics_top30      <- head(abbasi_topics, 30)
masoud_topics_top30      <- head(masoud_topics, 30)
hosseinpour_topics_top30 <- head(hosseinpour_topics, 30)

# Pad all columns to same length (30 rows)
n <- 30
pad_column <- function(x, n) { length(x) <- n; x[is.na(x)] <- "---"; x }

topics_top30_tbl <- tibble(
  `M. Shahriari`     = pad_column(majid_topics_top30,       n),
  `F. Abbasi Davani` = pad_column(abbasi_topics_top30,      n),
  `M. Alimohammadi`  = pad_column(masoud_topics_top30,      n),
  `A. Hosseinpour`   = pad_column(hosseinpour_topics_top30, n)
)

# Add a row of ellipses ("...")
topics_top30_tbl <- bind_rows(
  topics_top30_tbl,
  tibble(
    `M. Shahriari`     = "...",
    `F. Abbasi Davani` = "...",
    `M. Alimohammadi`  = "...",
    `A. Hosseinpour`   = "..."
  ),
  tibble(
    `M. Shahriari`     = paste0("n = ", length(majid_topics)),
    `F. Abbasi Davani` = paste0("n = ", length(abbasi_topics)),
    `M. Alimohammadi`  = paste0("n = ", length(masoud_topics)),
    `A. Hosseinpour`   = paste0("n = ", length(hosseinpour_topics))
  )
)

# Build LaTeX table
tbl_topics_top30 <- topics_top30_tbl %>%
  kbl(
    caption  = "List of Unique Topics per Author",
    format   = "latex",
    booktabs = TRUE
  ) %>%
  kable_styling(
    latex_options = c("hold_position", "scale_down"),
    font_size     = 10
  )

# Save to .tex file
writeLines(tbl_topics_top30, file.path(data_path, "30_topics_per_author.tex"))

# Build LaTeX table
tbl_topics <- topics_4col_all %>%
  kbl(
    caption  = "Unique Topics per Author",
    format   = "latex",
    booktabs = TRUE
  ) %>%
  kable_styling(
    latex_options = c("hold_position", "scale_down"),
    font_size     = 10
  )

# Save table to .tex file
writeLines(tbl_topics, file.path(data_path, "unique_topics_per_author.tex"))

topic_summary <- readRDS("/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic/extra_data/topic_summary.rds")


# Filter topic_summary separately
majid_keywords  <- topic_summary[topic_summary$Topic %in% majid_topics, ]
abbasi_keywords <- topic_summary[topic_summary$Topic %in% abbasi_topics, ]

# If you prefer dplyr syntax:
library(dplyr)

majid_keywords <- topic_summary %>%
  filter(Topic %in% majid_topics)

abbasi_keywords <- topic_summary %>%
  filter(Topic %in% abbasi_topics)

library(dplyr)
library(purrr)
library(tidyr)

data_path <- "/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic/Iran"

files <- c("works_5028976637.rds", "works_5102177495.rds",
           "works_5111646381.rds", "works_5112039075.rds")
ids   <- c("A5028976637", "A5102177495", "A5111646381", "A5112039075")

majid_works_long <- map2_dfr(files, ids, ~
  readRDS(file.path(data_path, .x)) %>% mutate(author_id = .y)
) %>%
  select(id, title, publication_date, publication_year, topics, authorships, author_id) %>%
  # Prefix nested columns so they don't clash with outer names (e.g., topics_id)
  unnest(cols = topics, keep_empty = TRUE, names_sep = "_") %>%
  # Keep only the topic fields you care about (plus topic id if present)
  select(
    id, title, publication_date, publication_year,
    topic            = topics_display_name,
    score            = topics_score,
    subfield         = `topics_subfield.display_name`,
    field            = `topics_field.display_name`,
    domain           = `topics_domain.display_name`,
    topics_id, authorships, author_id
  ) %>%
  # Clean OpenAlex URLs from character columns (list-cols like authorships unaffected)
  mutate(across(where(is.character),
                ~ gsub("https://openalex.org/", "", .x, fixed = TRUE)))

library(dplyr)
library(knitr)
library(kableExtra)

majid_works_long %>%
  distinct(title) %>%
  mutate(ID = row_number()) %>%  # generates 1 to n automatically
  select(ID, title) %>%
  kable(
    caption = "List of Distinct Publications by Majid Shahriari"
  ) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover")) %>%
  scroll_box(width = "100%", height = "500px")

topic_summary <- readRDS("/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic/extra_data/topic_summary.rds")

# Get unique topics from majid_works_long
majid_unique_topics <- unique(majid_works_long$topic)

# Subset topic_summary where Topic matches
majid_keywords_v1 <- topic_summary[topic_summary$Topic %in% majid_unique_topics, ]

# Save
#saveRDS(majid_keywords_v1, file = file.path(data_path, "majid_keywords_v1.rds"))

extract_institutions_for_authors <- function(works_df, author_ids) {
  # Dependencies: dplyr, tidyr, purrr
  # author_ids: character vector like c("A5046683464", "A5053153243", ...)
  
  # Build URL set from IDs
  target_urls <- paste0("https://openalex.org/", unique(na.omit(author_ids)))
  
  # 1-row NA placeholder for missing institutions
  na_inst <- tibble::tibble(
    id           = NA_character_,
    display_name = NA_character_,
    ror          = NA_character_,
    country_code = NA_character_,
    type         = NA_character_
  )
  
  works_df %>%
    dplyr::transmute(
      work_id          = id,
      work_title       = title,
      publication_year = dplyr::coalesce(
        publication_year,
        suppressWarnings(as.integer(substr(as.character(publication_date), 1, 4)))
      ),
      authorships
    ) %>%
    tidyr::unnest(authorships, keep_empty = TRUE) %>%              # one row per author
    dplyr::filter(author.id %in% target_urls) %>%                  # keep only your target author(s)
    dplyr::mutate(
      institutions = purrr::map(institutions, function(x) {        # handle empty institutions
        if (is.data.frame(x) && nrow(x) > 0) {
          x[, intersect(names(x), c("id","display_name","ror","country_code","type")), drop = FALSE]
        } else {
          na_inst
        }
      }),
      matched_author_id = gsub("^https://openalex.org/", "", author.id)
    ) %>%
    tidyr::unnest(institutions, keep_empty = TRUE) %>%
    dplyr::rename(
      inst_openalex = id,
      inst_name     = display_name,
      inst_ror      = ror,
      inst_country  = country_code,
      inst_type     = type,
      author_openalex = author.id
    ) %>%
    dplyr::mutate(
      source_author_id = matched_author_id
    ) %>%
    dplyr::select(
      work_id, work_title, publication_year,
      author_position, is_corresponding,
      author_openalex,
      inst_openalex, inst_name, inst_ror, inst_country, inst_type,
      source_author_id
    ) %>%
    dplyr::distinct()
}

library(dplyr)
library(kableExtra)
library(tidyr)

# Build the data with consistent types (use NA for missing numeric values)
authors_raw <- tibble::tribble(
  ~`Author ID`, ~`Author Name`,              ~`Alternate Names`,                                                                                                                                          ~Institution,                  ~`Past institutions`,                                                                                                                                            ~ORCID, ~`H-index`, ~`i10-index`, ~Works, ~Citations,
  "<a href='https://openalex.org/authors/a5046683464' target='_blank'>A5046683464</a>", "Feryidoon Abbasi Davani", "Feryidoon Abbasi Davani",                                                                                                                  "Shahid Beheshti University", "Shahid Beheshti University",                                                                                                                                        NA,     NA,        NA,          1,      NA,
  "<a href='https://openalex.org/authors/a5053153243' target='_blank'>A5053153243</a>", "Freidoon Abbasi Davani",   "Freidoon Abbasi Davani",                                                                                                                    NA,                          NA,                                                                                                                                                              NA,     1,         NA,          1,      3,
  "<a href='https://openalex.org/authors/a5019064523' target='_blank'>A5019064523</a>", "Abbasi Davani Fereydoun",  "Abbasi Davani Fereydoun",                                                                                                                   "Shahid Beheshti University", "Shahid Beheshti University",                                                                                                                                        NA,     1,         NA,          2,      2,
  "<a href='https://openalex.org/authors/a5103485250' target='_blank'>A5103485250</a>", "Fereidon Abbasi Davani",   "Fereidon Abbasi Davani",                                                                                                                    "Shahid Beheshti University", "Shahid Beheshti University",                                                                                                                                        NA,     NA,        NA,          2,      NA,
  "<a href='https://openalex.org/authors/a5030806477' target='_blank'>A5030806477</a>", "Abbasi Davani Fereydoon",  "Abbasi Davani Fereydoon",                                                                                                                   NA,                          NA,                                                                                                                                                              NA,     NA,        NA,          1,      NA,
  "<a href='https://openalex.org/authors/a5103401909' target='_blank'>A5103401909</a>", "Fereydoon Abbasi Davani",  "Fereydoon Abbasi Davani",                                                                                                                   "Shahid Beheshti University", "Shahid Beheshti University",                                                                                                                                        NA,     2,         NA,          13,     6,
  "<a href='https://openalex.org/authors/a5103918614' target='_blank'>A5103918614</a>", "Ferydoon Abbasi Davani",   "Ferydoon Abbasi Davani",                                                                                                                    "Shahid Beheshti University", "Shahid Beheshti University",                                                                                                                                        NA,     NA,        NA,          1,      NA,
  "<a href='https://openalex.org/authors/a5024862143' target='_blank'>A5024862143</a>", "Fereydoon Abbassi Davani", "Fereydoon Abbassi Davani",                                                                                                                  "Shahid Beheshti University", "Shahid Beheshti University",                                                                                                                                        NA,     1,         NA,          1,      2,
  "<a href='https://openalex.org/authors/a5037724110' target='_blank'>A5037724110</a>", "F. Abbasi Davani",         "Freydon AbbasiDavani; Fereydoun Abbasi Davani; F. Abbasi‐Davani; Freydoun Abbasi Davani; Fereydoun Abbasi‐Davani; F. Abbasi Davani; F.AbbasiDavani", "Shahid Beheshti University", "Shahid Beheshti University; University of Tehran; Institute for Research in Fundamental Sciences; Islamic Azad University Bandar Abbas; Atomic Energy Organization of Iran; Nuclear Science and Technology Research Institute", "Yes",  11,        14,         104,    414
)

# Convert NAs to "--" for display, keeping hyperlinks intact
authors_tbl <- authors_raw %>%
  mutate(across(c(`H-index`,`i10-index`,`Works`,`Citations`), as.numeric)) %>%
  mutate(across(everything(), ~ifelse(is.na(.), "--", as.character(.))))

kbl(
  authors_tbl,
  caption = "OpenAlex Author IDs for Abbasi Davani Variants",
  escape  = FALSE,
  format  = "html"
) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped","hover","condensed","responsive")) %>%
  row_spec(0, bold = TRUE, color = "#001f4d", background = "#F8F9FA")

library(dplyr)
library(purrr)
library(tidyr)

data_path_iran <- "/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic/Iran"

# Map of file names to author IDs
files_authors <- tibble(
  file = c(
    "works_FAD_5046.rds","works_FAD_5053.rds","works_FAD_5019.rds",
    "works_FAD_5103.rds","works_FAD_5030.rds","works_FAD_510340.rds",
    "works_FAD_51039.rds","works_FAD_5024.rds","works_FAD_5037.rds"
  ),
  author_id = c(
    "A5046683464","A5053153243","A5019064523",
    "A5103485250","A5030806477","A5103401909",
    "A5103918614","A5024862143","A5037724110"
  )
)

# Make data_path explicit in the function signature
read_and_process <- function(file, author_id, data_path) {
  df <- readRDS(file.path(data_path, file)) %>%
    select(id, title, publication_date, publication_year, topics, authorships)

  if (file == "works_FAD_5019.rds") {
    df <- df %>% filter(map_lgl(topics, ~ nrow(.x) > 0))
  }

  df %>%
    mutate(
      topics = map(
        topics,
        ~ select(.x, display_name, score, subfield.display_name, field.display_name, domain.display_name)
      ),
      author_id = author_id
    ) %>%
    unnest(topics)
}

# Pass data_path explicitly via pmap_dfr
abbasi_works_long <- pmap_dfr(
  list(file = files_authors$file,
       author_id = files_authors$author_id,
       data_path = list(data_path_iran)),             # <- stable path
  read_and_process
) %>%
  rename(topic = display_name) %>%
  rename_with(~ gsub("\\.?display_name", "", .x)) %>%
  mutate(across(where(is.character), ~ gsub("https://openalex.org/", "", .x, fixed = TRUE)))

abbasi_works <- abbasi_works_long %>%
  group_by(id) %>%
  mutate(row_num = row_number()) %>%
  ungroup() %>%
  pivot_wider(
    id_cols = c(title, publication_date, publication_year, id, author_id, authorships),
    names_from = row_num,
    values_from = c(topic, score, subfield, field, domain),
    names_glue = "{.value}_{row_num}"
  )

#extra_data_path <- file.path("/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic", "extra_data")

#if (!dir.exists(extra_data_path)) dir.create(extra_data_path, recursive = TRUE)

#saveRDS(abbasi_works, file.path(extra_data_path, "abbasi_works.rds"))
#saveRDS(abbasi_works_long, file.path(extra_data_path, "abbasi_works_long.rds"))

nrow(abbasi_works)

topic_summary <- readRDS("/standard/nsdpi_storage/people/czj9zj/DiD_data_3topic/extra_data/topic_summary.rds")

# Get unique topics
abbasi_unique_topics <- unique(abbasi_works_long$topic)

# Subset topic_summary where Topic matches
abbasi_keywords_v1 <- topic_summary[topic_summary$Topic %in% abbasi_unique_topics, ]

# Save
#saveRDS(abbasi_keywords_v1, file = file.path(data_path, "abbasi_keywords_v1.rds"))

library(dplyr)
library(knitr)
library(kableExtra)

masoud_53works <- readRDS("/standard/nsdpi_storage/people/czj9zj/extra_data/masoud_53works.rds")

masoud_53works %>%
  distinct(title) %>%
  mutate(ID = row_number()) %>%
  select(ID, title) %>%
  kable(
    caption = "List of 53 Possible Publications of Masoud Alimohammadi",
    escape  = FALSE
  ) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped","hover")) %>%
  kableExtra::add_footnote(
    label = "Source: <a href='https://imiranian.com/masoud-alimohammadi/' target='_blank'>imiranian.com/masoud-alimohammadi</a>.",
    notation = "none",
    escape = FALSE
  ) %>%
  scroll_box(width = "100%", height = "500px")

#your_email <- "czj9zj@virginia.edu"  # Replace with your email for better API performance

#Fetch all works for Masoud Alimohammadi candidate IDs
#works_5111436477 <- get_author_works("A5111436477", email = your_email)
#works_5059661145 <- get_author_works("A5059661145", email = your_email)  


#saveRDS(works_5111436477, "/standard/nsdpi_storage/people/czj9zj/extra_data/works_5111436477.rds")
#saveRDS(works_5059661145, "/standard/nsdpi_storage/people/czj9zj/extra_data/works_5059661145.rds")


# Read the two possible Masoud Alimohammadi author IDs
works_5111 <- readRDS("/standard/nsdpi_storage/people/czj9zj/extra_data/works_5111436477.rds")  # A5111436477
works_5059 <- readRDS("/standard/nsdpi_storage/people/czj9zj/extra_data/works_5059661145.rds")  # A5059661145


library(dplyr)
library(knitr)
library(kableExtra)
library(dplyr)

all_masoud_works_openalex <- bind_rows(
  works_5111 %>%
    select(id, title, publication_date, publication_year, topics, authorships) %>%
    mutate(author_id = "A5111436477"),
  works_5059 %>%
    select(id, title, publication_date, publication_year, topics, authorships) %>%
    mutate(author_id = "A5059661145")
) %>%
  mutate(across(where(is.character),
                ~ gsub("https://openalex.org/", "", .x, fixed = TRUE)))


all_masoud_works_openalex %>%
  mutate(ID = row_number()) %>%
  select(ID, title) %>%
  kable(
    caption = "List of OpenAlex Works for Masoud Alimohammadi (two candidate author IDs)",
    escape  = FALSE
  ) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped","hover")) %>%
  kableExtra::add_footnote(
    label = paste0(
      "Source: OpenAlex (Author IDs: ",
      "<a href='https://openalex.org/authors/a5111436477' target='_blank'>A5111436477</a> and ",
      "<a href='https://openalex.org/authors/a5059661145' target='_blank'>A5059661145</a>)."
    ),
    notation = "none",
    escape = FALSE
  ) %>%
  scroll_box(width = "100%", height = "500px")

map_5111 <- tribble(
  ~work_number, ~author_id,    ~title_matched,
   3,           "5111436477",  "SOME CORRELATORS OF <font>SU</font>(3)<sub>3</sub> WZW MODELS ON HIGHER-GENUS RIEMANN SURFACES",
   7,           "5111436477",  "Quantum chains with GL<i>q</i>(2) symmetry",
  22,           "5111436477",  "Generalized simplicial chiral models",
  28,           "5111436477",  "On the phase structure of two-dimensional generalized Yang–Mills theories",
  39,           "5111436477",  "A Statistical Mechanical Deconvolution of the Differential Scanning Calorimetric Profiles of the Thermal Denaturation of Cyanomethemoglobin",
  43,           "5111436477",  "Solvable reaction-diffusion processes without exclusion",
  50,           "5111436477",  "Asymptotic behavior of ω in general quintom model"
)

library(dplyr)
library(tibble)

# Map canonical row numbers (1..53) to their exact works_5059 titles:
map_5059 <- tribble(
  ~work_number, ~author_id, ~title_matched,
   1, "5059661145", "LEVEL-ONE <font>SU</font>(N) WZNW MODELS ON HIGHER-GENUS RIEMANN SURFACES",
   2, "5059661145", "<font>SU</font>(N)<sub>1</sub> CORRELATION FUNCTIONS ON HIGHER-GENUS RIEMANN SURFACES",
   4, "5059661145", "SU(N) 1 fusion rule and modular transformation matrix by orthogonal polynomials",
   5, "5059661145", "GAUGING SL(2, R) AND SL(2, R)×U(1) BY THEIR NILPOTENT SUBGROUPS",
   6, "5059661145", "2-D GRAVITY AS A LIMIT OF THE SL(2, ${\\mathbb R}$) BLACK HOLE",
   8, "5059661145", "Quantum group symmetry of the quantum Hall effect on non-flat surfaces",
   9, "5059661145", "Laughlin states on the Poincaré half-plane and their quantum group symmetry",
  10, "5059661145", "n-Point Functions of 2d Yang–Mills Theories on Riemann Surfaces",
  11, "5059661145", "A Pseudo-Conformal Representation of the Virasoro Algebra",
  12, "5059661145", "Observables of the Generalized 2D Yang–Mills Theories on Arbitrary Surfaces: A Path Integral Approach",
  13, "5059661145", "Green functions of 2-dimensional Yang-Mills theories on nonorientable surfaces",
  14, "5059661145", "Large-N limit of the generalized two-dimensional Yang-Mills theories",
  15, "5059661145", "DERIVATION OF QUANTUM THEORIES: SYMMETRIES AND THE EXACT SOLUTION OF THE DERIVED SYSTEM",
  16, "5059661145", "Exact solution of a one-parameter family of asymmetric exclusion processes",
  17, "5059661145", "NEUTRINO OSCILLATION IN A SPACE–TIME WITH TORSION",
  18, "5059661145", "UNIQUENESS OF THE MINIMUM OF THE FREE ENERGY OF THE 2-D YANG–MILLS THEORY AT LARGE N",
  19, "5059661145", "Coulomb gas representation of quantum Hall effect on Riemann surfaces",
  20, "5059661145", "Phase structure of the generalized two-dimensional Yang-Mills theory on sphere",
  21, "5059661145", "A two--parametric family of asymmetric exclusion processes and its exact solution",
  23, "5059661145", "Large- limit of the generalized 2DYang–Mills theory on cylinder",
  24, "5059661145", "Class of integrable diffusion-reaction processes",
  25, "5059661145", "QUANTUM REFLECTION OF MASSLESS NEUTRINOS FROM A TORSION-INDUCED POTENTIAL",
  26, "5059661145", "Confinement and screening of the Schwinger model on the Poincare half plane",
  27, "5059661145", "MORE ON GENERALIZED SIMPLICIAL CHIRAL MODELS",
  29, "5059661145", "Massive Schwinger model and its confining aspects on curved space-time",
  30, "5059661145", "Berry phase for spin-1/2 particles moving in a space-time with torsion",
  31, "5059661145", "Exactly solvable models through the empty-interval method",
  32, "5059661145", "<i>p</i>-species integrable reaction–diffusion processes",
  33, "5059661145", "Exactly solvable models through the empty interval method, for more-than-two-site interactions",
  34, "5059661145", "Spin 0 and spin 1/2 quantum relativistic particles in a constant gravitational field",
  35, "5059661145", "Exactly solvable models through the generalized empty interval method, for multi-species interactions",
  36, "5059661145", "Spin-0 and spin-1/2 particles in a constant scalar-curvature background",
  37, "5059661145", "Large-N limit of the two-dimensional Yang–Mills theory on surfaces with boundaries",
  38, "5059661145", "Solvable multi-species reaction-diffusion processes, including the extended drop-push model",
  40, "5059661145", "Multispecies extension of the solvable partially asymmetric reaction–diffusion processes",
  41, "5059661145", "Electrostatic self-energy and Bekenstein entropy bound in the massive Schwinger model",
  42, "5059661145", "Large-N behavior of the Wilson loops of generalized two-dimensional Yang–Mills theories",
  44, "5059661145", "Phase transitions of large-N two-dimensional Yang–Mills and generalized Yang–Mills theories in the double scaling limit",
  45, "5059661145", "Attractor solutions for general hessence dark energy",
  46, "5059661145", "Transition from quintessence to the phantom phase in the quintom model",
  47, "5059661145", "Cosmological coincidence problem in interacting dark energy models",
  48, "5059661145", "The <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si1.gif\" overflow=\"scroll\"><mml:mi>ω</mml:mi><mml:mo>=</mml:mo><mml:mo>−</mml:mo><mml:mn>1</mml:mn></mml:math> crossing of the quintom model with slowly-varying potentials",
  49, "5059661145", "Non-Douglas–Kazakov phase transition of two-dimensional generalized Yang–Mills theories",
  51, "5059661145", "KLEIN–GORDON AND DIRAC PARTICLES IN NONCONSTANT SCALAR-CURVATURE BACKGROUND",
  52, "5059661145", "Quantum induced ω = −1 crossing of the quintessence and phantom models",
  53, "5059661145", "Remarks on generalized Gauss-Bonnet dark energy"
)

library(dplyr)

# --- Build one lookup from BOTH works tables (title -> metadata) --------------
lookup_all <- bind_rows(
  works_5111 %>%
    transmute(
      title_key        = title,                     # exact string used in maps
      id               = id,
      publication_date = as.character(publication_date),
      publication_year = suppressWarnings(as.integer(substr(as.character(publication_date), 1, 4))),
      topics           = topics,
      authorships      = authorships              # <— keep authorships
    ),
  works_5059 %>%
    transmute(
      title_key        = title,
      id               = id,
      publication_date = as.character(publication_date),
      publication_year = suppressWarnings(as.integer(substr(as.character(publication_date), 1, 4))),
      topics           = topics,
      authorships      = authorships              # <— keep authorships
    )
)

# --- 1) Combine maps & collapse per work_number (no pub fields here) ----------
combined_map <- bind_rows(
  map_5111 %>% mutate(source = "a1"),
  map_5059 %>% mutate(source = "a2")
) %>%
  group_by(work_number) %>%
  summarise(
    author_id = {
      ids <- unique(na.omit(author_id))
      if (length(ids) > 1) "both" else if (length(ids) == 1) ids else NA_character_
    },
    title_key      = dplyr::first(na.omit(title_matched), default = NA_character_),
    title_matched  = paste(unique(na.omit(title_matched)), collapse = " | "),
    .groups = "drop"
  )

# --- 2) Join the metadata AFTER summarise -------------------------------------
combined_map <- combined_map %>%
  left_join(lookup_all, by = "title_key") %>%
  select(-title_key)

# --- 3) Join onto the canonical 53 & finalize columns -------------------------
masoud_53works <- masoud_53works %>%
  mutate(work_number = row_number()) %>%
  # drop only columns we are re-creating (add authorships here in case it already existed)
  select(-any_of(c("id","publication_date","publication_year","topics","authorships","author_id","author_number"))) %>%
  left_join(combined_map, by = "work_number") %>%
  mutate(
    author_id = factor(author_id, levels = c("5111436477","5059661145","both"))
  ) %>%
  # *** keep authorships in the final output ***
  select(id, title, title_matched, publication_date, publication_year, topics, authorships, author_id) %>%
  mutate(across(where(is.character),
                ~ gsub("https://openalex.org/", "", .x, fixed = TRUE)))


masoud_53works %>%
  mutate(ID = row_number()) %>%
  select(
    ID,
    `Title` = title,
    `Matched OpenAlex title` = title_matched,
    `Author ID` = author_id
  ) %>%
  kable(
    caption = "List of 53 Possible Publications of Masoud Alimohammadi (with OpenAlex matches)",
    escape  = FALSE
  ) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped","hover")) %>%
  kableExtra::add_footnote(
    label = paste0(
      "Source: OpenAlex (Author IDs: ",
      "<a href='https://openalex.org/authors/a5111436477' target='_blank'>A5111436477</a> and ",
      "<a href='https://openalex.org/authors/a5059661145' target='_blank'>A5059661145</a>)."
    ),
    notation = "none",
    escape = FALSE
  ) %>%
  scroll_box(width = "100%", height = "500px")

# rows in all_masoud_works_openalex$title that are NOT in masoud_53works$title_matched
not_masoud_53works <- all_masoud_works_openalex %>%
  distinct(title, .keep_all = TRUE) %>%
  anti_join(
    masoud_53works %>%
      filter(!is.na(title_matched)) %>%
      distinct(title_matched) %>%
      rename(title = title_matched),   # <-- make the join key names match
    by = "title"
  )

# (optional) pretty table
library(knitr)
library(kableExtra)
not_masoud_53works %>%
  mutate(ID = row_number()) %>%
  select(ID, title, publication_date, publication_year, author_id, authorships) %>%
  kable(caption = "List of the 15 OpenAlex works not the List of 53 Possible Publications of Masoud Alimohammadi") %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover")) %>%
  kableExtra::add_footnote(
    label = "Source: OpenAlex author IDs: <a href='https://openalex.org/authors/A5111436477' target='_blank'>A5111436477</a>, <a href='https://openalex.org/authors/A5059661145' target='_blank'>A5059661145</a>.",
    notation = "none", escape = FALSE
  ) %>%
  scroll_box(width = "100%", height = "500px")