L1 (follow-up): figure PNGs written by make_tables.py (dpi documented input) — orphan PNGs of FIRC0001-DATA-15 now generated
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
7 changed files +16 −322
modified
code/make_tables.py
+11 −4
@@ -658,6 +658,13 @@ if di("brief_definition"): macro("brief", di("brief_definition"), "data/document | ||
| 658 | 658 | |
| 659 | 659 | # ---- Figures --------------------------------------------------------------------------------------------- |
| 660 | 660 | BLUE, GOLD, GREY = "#16365c", "#c9a227", "#8a8a8a" |
| 661 | + | |
| 662 | + | |
| 663 | +def save(fig, name): | |
| 664 | + """PDF for the paper and PNG (same figure) for the Word export; no other script produces the PNGs.""" | |
| 665 | + fig.savefig(F / f"{name}.pdf", metadata={"CreationDate": None}) | |
| 666 | + fig.savefig(F / f"{name}.png", dpi=int(DI["png_dpi"]["value"])) | |
| 667 | + plt.close(fig) | |
| 661 | 668 | yrs = [int(r["yr"]) for r in iy] |
| 662 | 669 | fig, ax1 = plt.subplots(figsize=(7.2, 3.4)) |
| 663 | 670 | ax1.bar(yrs, [int(r["filings"]) for r in iy], color=BLUE, alpha=.85, label="Filings (10-K, 10-Q, 8-K)") |
@@ -667,14 +674,14 @@ ax2 = ax1.twinx(); ax2.plot(yrs, [int(r["issuers"]) for r in iy], color=GOLD, ma | ||
| 667 | 674 | ax2.set_ylabel("Issuers"); ax2.set_ylim(0, U["n"] * 1.05) |
| 668 | 675 | h1, l1 = ax1.get_legend_handles_labels(); h2, l2 = ax2.get_legend_handles_labels(); ax1.legend(h1 + h2, l1 + l2, loc="upper left", frameon=False, fontsize=8) |
| 669 | 676 | for a in (ax1, ax2): a.spines[["top"]].set_visible(False) |
| 670 | −fig.tight_layout(); fig.savefig(F / "fig_coverage.pdf", metadata={"CreationDate": None}); plt.close(fig) | |
| 677 | +fig.tight_layout(); save(fig, "fig_coverage") | |
| 671 | 678 | |
| 672 | 679 | fig, ax = plt.subplots(figsize=(7.2, 5.2)) |
| 673 | 680 | labs = [LAB[r["project_type"]].replace("\\&", "&") for r in pt][::-1]; vals = [int(r["n"]) for r in pt][::-1] |
| 674 | 681 | ax.barh(labs, vals, color=BLUE); ax.set_xlabel("Resolved projects"); ax.spines[["top", "right"]].set_visible(False) |
| 675 | 682 | for i, v in enumerate(vals): ax.text(v + max(vals) * 0.007, i, f"{v:,}", va="center", fontsize=7) |
| 676 | 683 | ax.xaxis.set_major_locator(MaxNLocator(integer=True)) |
| 677 | −fig.tight_layout(); fig.savefig(F / "fig_types.pdf", metadata={"CreationDate": None}); plt.close(fig) | |
| 684 | +fig.tight_layout(); save(fig, "fig_types") | |
| 678 | 685 | |
| 679 | 686 | fig, (ax, axb) = plt.subplots(2, 1, figsize=(7.2, 5.6), sharex=True, gridspec_kw={"height_ratios": [3, 2]}) |
| 680 | 687 | ax.plot(yrs, [int(my[str(y)]["mentions"]) for y in yrs], color=BLUE, marker="o", lw=2, label="Project mentions") |
@@ -687,14 +694,14 @@ axb.plot(yrs, [int(my[str(y)]["mentions"]) / int(my[str(y)]["issuers"]) for y in | ||
| 687 | 694 | axb.plot(yrs, [int(py[str(y)]["n"]) / int(my[str(y)]["issuers"]) for y in yrs], color=GOLD, marker="s", lw=2, label="Projects first observed per issuer with $\\geq$1 mention") |
| 688 | 695 | axb.set_xlabel("Filing year"); axb.set_ylabel("Per issuer"); axb.set_ylim(0, None); axb.legend(frameon=False, fontsize=8); axb.spines[["top", "right"]].set_visible(False) |
| 689 | 696 | axb.xaxis.set_major_locator(MaxNLocator(integer=True)) |
| 690 | −fig.tight_layout(); fig.savefig(F / "fig_mentions_year.pdf", metadata={"CreationDate": None}); plt.close(fig) | |
| 697 | +fig.tight_layout(); save(fig, "fig_mentions_year") | |
| 691 | 698 | macro("newProjectsPerIssuerFirstYear", f"{int(py[str(y_first)]['n'])/int(my[str(y_first)]['issuers']):.1f}", "data/projects_by_first_seen_year.csv, mentions_by_year.csv", "first seen / issuers with mentions") |
| 692 | 699 | macro("newProjectsPerIssuerLastFullYear", f"{int(py[str(inner[-1])]['n'])/int(my[str(inner[-1])]['issuers']):.1f}", "data/projects_by_first_seen_year.csv, mentions_by_year.csv", "first seen / issuers with mentions") |
| 693 | 700 | |
| 694 | 701 | fig, ax = plt.subplots(figsize=(7.2, 3.0)) |
| 695 | 702 | ax.bar([float(r["conf"]) for r in cf], [int(r["n"]) for r in cf], width=0.08, color=BLUE) |
| 696 | 703 | ax.set_xlabel("Self-reported extraction confidence"); ax.set_ylabel("Mentions"); ax.spines[["top", "right"]].set_visible(False) |
| 697 | −fig.tight_layout(); fig.savefig(F / "fig_confidence.pdf", metadata={"CreationDate": None}); plt.close(fig) | |
| 704 | +fig.tight_layout(); save(fig, "fig_confidence") | |
| 698 | 705 | print("figures ok") |
| 699 | 706 | |
| 700 | 707 | # ---- inline-number macros --------------------------------------------------------------------------------- |
modified
data/documented_inputs.json
+5 −0
@@ -19,5 +19,10 @@ | ||
| 19 | 19 | "value": 170, |
| 20 | 20 | "source": "presentation rule of Table 9 (first characters of the stored snippet shown)", |
| 21 | 21 | "status": "convention" |
| 22 | + }, | |
| 23 | + "png_dpi": { | |
| 24 | + "value": 200, | |
| 25 | + "source": "raster resolution of the PNG copies used by code/tex2docx", | |
| 26 | + "status": "convention" | |
| 22 | 27 | } |
| 23 | 28 | } |
| \ No newline at end of file | ||
modified
paper/figures/fig_confidence.png
+0 −0
Binary file not shown.
modified
paper/figures/fig_coverage.png
+0 −0
Binary file not shown.
modified
paper/figures/fig_mentions_year.png
+0 −0
Binary file not shown.
modified
paper/figures/fig_types.png
+0 −0
Binary file not shown.
modified
results/tables_diff.txt
+0 −318
@@ -1,318 +0,0 @@ | ||
| 1 | −diff --git a/paper/tables/prompt_verbatim.tex b/paper/tables/prompt_verbatim.tex | |
| 2 | −index 60359fa..78d298e 100644 | |
| 3 | −--- a/paper/tables/prompt_verbatim.tex | |
| 4 | −+++ b/paper/tables/prompt_verbatim.tex | |
| 5 | −@@ -20,7 +20,27 @@ Return STRICT JSON: {"projects": [ ... ]}. Each project object has: | |
| 6 | − confidence : 0.0-1.0 (how clearly this is a real, concrete project) | |
| 7 | − | |
| 8 | − Allowed project_type values: | |
| 9 | −- - <code>: <label> (the 21 taxonomy entries of Table A1) | |
| 10 | −+ - manufacturing_expansion: Manufacturing / Capacity Expansion | |
| 11 | −+ - plant_construction: Plant / Site Construction | |
| 12 | −+ - data_center: Data Center | |
| 13 | −+ - cloud_migration: Cloud Migration | |
| 14 | −+ - ai_initiative: AI / ML Initiative | |
| 15 | −+ - digital_transformation: Digital Transformation | |
| 16 | −+ - erp_implementation: ERP / Systems Implementation | |
| 17 | −+ - rd_program: R&D Program | |
| 18 | −+ - product_launch: New Product / Launch | |
| 19 | −+ - drug_pipeline: Drug / Clinical Pipeline | |
| 20 | −+ - ma_integration: M&A / Integration | |
| 21 | −+ - geographic_expansion: Geographic Expansion | |
| 22 | −+ - capex_program: Capital Expenditure Program | |
| 23 | −+ - supply_chain: Supply Chain Initiative | |
| 24 | −+ - automation: Automation / Robotics | |
| 25 | −+ - sustainability: Sustainability / ESG | |
| 26 | −+ - energy_transition: Energy Transition / Renewables | |
| 27 | −+ - infrastructure: Infrastructure Investment | |
| 28 | −+ - cost_reduction: Cost Reduction / Restructuring | |
| 29 | −+ - partnership: Strategic Partnership | |
| 30 | −+ - technology_deployment: Technology Deployment | |
| 31 | − | |
| 32 | − Rules: | |
| 33 | − - Extract ONLY real initiatives, not generic risk-factor boilerplate or hypotheticals. | |
| 34 | −diff --git a/paper/tables/tab_amounts.tex b/paper/tables/tab_amounts.tex | |
| 35 | −index 0576150..0551234 100644 | |
| 36 | −--- a/paper/tables/tab_amounts.tex | |
| 37 | −+++ b/paper/tables/tab_amounts.tex | |
| 38 | −@@ -5,4 +5,4 @@ | |
| 39 | − Largest amount cited per project{,} M USD ($N$ = 56{{,}}500) & 3.2 & 23 & 128.5 & 500 & 1{,}503 & 12{,}501 \\ | |
| 40 | − Projects per issuer ($N$ = 2{{,}}492) & 12 & 24 & 42 & 67 & 94 & 140 \\ | |
| 41 | − \bottomrule | |
| 42 | −-\end{tabular} | |
| 43 | −\ No newline at end of file | |
| 44 | −+\end{tabular} | |
| 45 | −diff --git a/paper/tables/tab_confidence.tex b/paper/tables/tab_confidence.tex | |
| 46 | −index 7b5bc9c..808aff6 100644 | |
| 47 | −--- a/paper/tables/tab_confidence.tex | |
| 48 | −+++ b/paper/tables/tab_confidence.tex | |
| 49 | −@@ -9,4 +9,4 @@ Self-reported confidence (rounded) & Mentions \\ | |
| 50 | − 0.9 & 100{,}831 \\ | |
| 51 | − 1.0 & 108{,}418 \\ | |
| 52 | − \bottomrule | |
| 53 | −-\end{tabular} | |
| 54 | −\ No newline at end of file | |
| 55 | −+\end{tabular} | |
| 56 | −diff --git a/paper/tables/tab_coverage_year.tex b/paper/tables/tab_coverage_year.tex | |
| 57 | −index 04d5edd..093ed79 100644 | |
| 58 | −--- a/paper/tables/tab_coverage_year.tex | |
| 59 | −+++ b/paper/tables/tab_coverage_year.tex | |
| 60 | −@@ -1,23 +1,23 @@ | |
| 61 | −-\begin{tabular}{lrrrrrrr} | |
| 62 | −+\begin{tabular}{lrrrrrrrr} | |
| 63 | − \toprule | |
| 64 | −-Year & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Projects first seen \\ | |
| 65 | −+Year & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Mentions per issuer & Projects first seen \\ | |
| 66 | − \midrule | |
| 67 | −-2010 & 1{,}392 & 1{,}357 & 4{,}152 & 17{,}672 & 11{,}908 & 1{,}224 & 7{,}835 \\ | |
| 68 | −-2011 & 1{,}424 & 1{,}409 & 4{,}260 & 18{,}533 & 13{,}551 & 1{,}287 & 6{,}679 \\ | |
| 69 | −-2012 & 1{,}472 & 1{,}436 & 4{,}363 & 19{,}437 & 14{,}302 & 1{,}333 & 6{,}444 \\ | |
| 70 | −-2013 & 1{,}539 & 1{,}483 & 4{,}530 & 19{,}773 & 14{,}611 & 1{,}408 & 6{,}286 \\ | |
| 71 | −-2014 & 1{,}619 & 1{,}549 & 4{,}780 & 20{,}927 & 16{,}274 & 1{,}490 & 6{,}732 \\ | |
| 72 | −-2015 & 1{,}689 & 1{,}635 & 4{,}983 & 22{,}077 & 17{,}073 & 1{,}535 & 6{,}675 \\ | |
| 73 | −-2016 & 1{,}744 & 1{,}692 & 5{,}146 & 22{,}447 & 16{,}429 & 1{,}579 & 6{,}240 \\ | |
| 74 | −-2017 & 1{,}810 & 1{,}745 & 5{,}359 & 22{,}897 & 17{,}350 & 1{,}636 & 6{,}490 \\ | |
| 75 | −-2018 & 1{,}893 & 1{,}827 & 5{,}582 & 23{,}709 & 18{,}064 & 1{,}737 & 6{,}815 \\ | |
| 76 | −-2019 & 1{,}973 & 1{,}903 & 5{,}829 & 24{,}256 & 18{,}737 & 1{,}806 & 6{,}837 \\ | |
| 77 | −-2020 & 2{,}089 & 1{,}985 & 6{,}095 & 27{,}424 & 17{,}970 & 1{,}919 & 7{,}212 \\ | |
| 78 | −-2021 & 2{,}247 & 2{,}116 & 6{,}606 & 27{,}944 & 21{,}312 & 2{,}077 & 8{,}216 \\ | |
| 79 | −-2022 & 2{,}291 & 2{,}258 & 6{,}830 & 26{,}533 & 22{,}720 & 2{,}105 & 8{,}158 \\ | |
| 80 | −-2023 & 2{,}329 & 2{,}295 & 6{,}938 & 26{,}851 & 22{,}955 & 2{,}129 & 7{,}977 \\ | |
| 81 | −-2024 & 2{,}387 & 2{,}341 & 7{,}092 & 27{,}438 & 22{,}503 & 2{,}204 & 7{,}819 \\ | |
| 82 | −-2025 & 2{,}453 & 2{,}406 & 7{,}300 & 28{,}716 & 23{,}220 & 2{,}280 & 7{,}990 \\ | |
| 83 | −-2026 & 2{,}498 & 2{,}338 & 5{,}322 & 23{,}972 & 19{,}086 & 2{,}260 & 6{,}694 \\ | |
| 84 | −+2010 & 1{,}392 & 1{,}357 & 4{,}152 & 17{,}672 & 11{,}908 & 1{,}224 & 9.7 & 7{,}835 \\ | |
| 85 | −+2011 & 1{,}424 & 1{,}409 & 4{,}260 & 18{,}533 & 13{,}551 & 1{,}287 & 10.5 & 6{,}679 \\ | |
| 86 | −+2012 & 1{,}472 & 1{,}436 & 4{,}363 & 19{,}437 & 14{,}302 & 1{,}333 & 10.7 & 6{,}444 \\ | |
| 87 | −+2013 & 1{,}539 & 1{,}483 & 4{,}530 & 19{,}773 & 14{,}611 & 1{,}408 & 10.4 & 6{,}286 \\ | |
| 88 | −+2014 & 1{,}619 & 1{,}549 & 4{,}780 & 20{,}927 & 16{,}274 & 1{,}490 & 10.9 & 6{,}732 \\ | |
| 89 | −+2015 & 1{,}689 & 1{,}635 & 4{,}983 & 22{,}077 & 17{,}073 & 1{,}535 & 11.1 & 6{,}675 \\ | |
| 90 | −+2016 & 1{,}744 & 1{,}692 & 5{,}146 & 22{,}447 & 16{,}429 & 1{,}579 & 10.4 & 6{,}240 \\ | |
| 91 | −+2017 & 1{,}810 & 1{,}745 & 5{,}359 & 22{,}897 & 17{,}350 & 1{,}636 & 10.6 & 6{,}490 \\ | |
| 92 | −+2018 & 1{,}893 & 1{,}827 & 5{,}582 & 23{,}709 & 18{,}064 & 1{,}737 & 10.4 & 6{,}815 \\ | |
| 93 | −+2019 & 1{,}973 & 1{,}903 & 5{,}829 & 24{,}256 & 18{,}737 & 1{,}806 & 10.4 & 6{,}837 \\ | |
| 94 | −+2020 & 2{,}089 & 1{,}985 & 6{,}095 & 27{,}424 & 17{,}970 & 1{,}919 & 9.4 & 7{,}212 \\ | |
| 95 | −+2021 & 2{,}247 & 2{,}116 & 6{,}606 & 27{,}944 & 21{,}312 & 2{,}077 & 10.3 & 8{,}216 \\ | |
| 96 | −+2022 & 2{,}291 & 2{,}258 & 6{,}830 & 26{,}533 & 22{,}720 & 2{,}105 & 10.8 & 8{,}158 \\ | |
| 97 | −+2023 & 2{,}329 & 2{,}295 & 6{,}938 & 26{,}851 & 22{,}955 & 2{,}129 & 10.8 & 7{,}977 \\ | |
| 98 | −+2024 & 2{,}387 & 2{,}341 & 7{,}092 & 27{,}438 & 22{,}503 & 2{,}204 & 10.2 & 7{,}819 \\ | |
| 99 | −+2025 & 2{,}453 & 2{,}406 & 7{,}300 & 28{,}716 & 23{,}220 & 2{,}280 & 10.2 & 7{,}990 \\ | |
| 100 | −+2026 & 2{,}498 & 2{,}338 & 5{,}322 & 23{,}972 & 19{,}086 & 2{,}260 & 8.4 & 6{,}694 \\ | |
| 101 | − \bottomrule | |
| 102 | −-\end{tabular} | |
| 103 | −\ No newline at end of file | |
| 104 | −+\end{tabular} | |
| 105 | −diff --git a/paper/tables/tab_filings.tex b/paper/tables/tab_filings.tex | |
| 106 | −index 625a1f0..0e3f777 100644 | |
| 107 | −--- a/paper/tables/tab_filings.tex | |
| 108 | −+++ b/paper/tables/tab_filings.tex | |
| 109 | −@@ -8,4 +8,4 @@ Form & Filings & First filing & Last filing & Raw HTML (GB) & Not parsed \\ | |
| 110 | − \midrule | |
| 111 | − Total & 527{,}548 & 2010-01-04 & 2026-10-27 & 254.5 & 16 \\ | |
| 112 | − \bottomrule | |
| 113 | −-\end{tabular} | |
| 114 | −\ No newline at end of file | |
| 115 | −+\end{tabular} | |
| 116 | −diff --git a/paper/tables/tab_graph.tex b/paper/tables/tab_graph.tex | |
| 117 | −index 7dd3c7e..4444a61 100644 | |
| 118 | −--- a/paper/tables/tab_graph.tex | |
| 119 | −+++ b/paper/tables/tab_graph.tex | |
| 120 | −@@ -11,4 +11,4 @@ Nodes & \texttt{Location} & 14{,}508 \\ | |
| 121 | − Nodes & \texttt{Technology} & 8{,}551 \\ | |
| 122 | − Nodes & \texttt{Company} & 2{,}492 \\ | |
| 123 | − \bottomrule | |
| 124 | −-\end{tabular} | |
| 125 | −\ No newline at end of file | |
| 126 | −+\end{tabular} | |
| 127 | −diff --git a/paper/tables/tab_items.tex b/paper/tables/tab_items.tex | |
| 128 | −index 8b4f50f..6411493 100644 | |
| 129 | −--- a/paper/tables/tab_items.tex | |
| 130 | −+++ b/paper/tables/tab_items.tex | |
| 131 | −@@ -1,21 +1,21 @@ | |
| 132 | −-\begin{tabular}{llrr} | |
| 133 | −+\begin{tabular}{llrrr} | |
| 134 | − \toprule | |
| 135 | −-Form & Section (item) & Sections extracted & Mentions \\ | |
| 136 | −+Form & Section (item) & Ledgered sections & Mentions & Gate passed (calls) \\ | |
| 137 | − \midrule | |
| 138 | −-10-K & \texttt{business} & 29{,}285 & 30{,}492 \\ | |
| 139 | −-10-K & \texttt{risk\_factors} & 29{,}158 & 2{,}797 \\ | |
| 140 | −-10-K & \texttt{md\_and\_a} & 28{,}919 & 39{,}099 \\ | |
| 141 | −-10-K & \texttt{properties} & 28{,}236 & 7{,}879 \\ | |
| 142 | −-10-K & \texttt{quantitative\_disclosures} & 26{,}876 & 531 \\ | |
| 143 | −-10-K & \texttt{full\_body} & 1{,}230 & 824 \\ | |
| 144 | −+10-K & \texttt{business} & 29{,}285 & 30{,}492 & 29{,}118 \\ | |
| 145 | −+10-K & \texttt{risk\_factors} & 29{,}158 & 2{,}797 & 28{,}941 \\ | |
| 146 | −+10-K & \texttt{md\_and\_a} & 28{,}919 & 39{,}099 & 28{,}050 \\ | |
| 147 | −+10-K & \texttt{properties} & 28{,}236 & 7{,}879 & 25{,}940 \\ | |
| 148 | −+10-K & \texttt{quantitative\_disclosures} & 26{,}876 & 531 & 22{,}032 \\ | |
| 149 | −+10-K & \texttt{full\_body} & 1{,}230 & 824 & 1{,}229 \\ | |
| 150 | − \midrule | |
| 151 | −-10-Q & \texttt{controls\_and\_procedures} & 92{,}393 & 7{,}082 \\ | |
| 152 | −-10-Q & \texttt{financial\_statements} & 91{,}882 & 30{,}159 \\ | |
| 153 | −-10-Q & \texttt{md\_and\_a} & 91{,}371 & 99{,}305 \\ | |
| 154 | −-10-Q & \texttt{quantitative\_disclosures} & 83{,}138 & 808 \\ | |
| 155 | −-10-Q & \texttt{unregistered\_sales} & 80{,}210 & 9{,}535 \\ | |
| 156 | −-10-Q & \texttt{risk\_factors} & 72{,}560 & 4{,}420 \\ | |
| 157 | −-10-Q & \texttt{legal\_proceedings} & 66{,}998 & 845 \\ | |
| 158 | −-10-Q & \texttt{full\_document} & 241 & 107 \\ | |
| 159 | −+10-Q & \texttt{controls\_and\_procedures} & 92{,}393 & 7{,}082 & 20{,}913 \\ | |
| 160 | −+10-Q & \texttt{financial\_statements} & 91{,}882 & 30{,}159 & 90{,}106 \\ | |
| 161 | −+10-Q & \texttt{md\_and\_a} & 91{,}371 & 99{,}305 & 90{,}269 \\ | |
| 162 | −+10-Q & \texttt{quantitative\_disclosures} & 83{,}138 & 808 & 46{,}720 \\ | |
| 163 | −+10-Q & \texttt{unregistered\_sales} & 80{,}210 & 9{,}535 & 61{,}867 \\ | |
| 164 | −+10-Q & \texttt{risk\_factors} & 72{,}560 & 4{,}420 & 33{,}826 \\ | |
| 165 | −+10-Q & \texttt{legal\_proceedings} & 66{,}998 & 845 & 20{,}031 \\ | |
| 166 | −+10-Q & \texttt{full\_document} & 241 & 107 & 241 \\ | |
| 167 | − \bottomrule | |
| 168 | −-\end{tabular} | |
| 169 | −\ No newline at end of file | |
| 170 | −+\end{tabular} | |
| 171 | −diff --git a/paper/tables/tab_provenance.tex b/paper/tables/tab_provenance.tex | |
| 172 | −index 153ace1..65c772a 100644 | |
| 173 | −--- a/paper/tables/tab_provenance.tex | |
| 174 | −+++ b/paper/tables/tab_provenance.tex | |
| 175 | −@@ -11,4 +11,4 @@ Accession & Filed & Form & Status / amount & Evidence snippet (model-generated d | |
| 176 | − \texttt{0001193125-15-186045} & 2015-05-13 & 8-K & in\_progress / 11.5 B USD & The project involves the development, construction, operation, and maintenance of a natural gas liquefaction and export facility and related infrastructure in San Patrici \\ | |
| 177 | − \texttt{0000003570-22-000029} & 2022-03-07 & 8-K & in\_progress / 5.5 B USD & The project involves the engineering, procurement, construction, pre-commissioning, commissioning, start-up, and testing of a mid-scale natural gas liquefaction facility \\ | |
| 178 | − \bottomrule | |
| 179 | −-\end{tabular} | |
| 180 | −\ No newline at end of file | |
| 181 | −+\end{tabular} | |
| 182 | −diff --git a/paper/tables/tab_reconciliation.tex b/paper/tables/tab_reconciliation.tex | |
| 183 | −index a1f0a84..aa41007 100644 | |
| 184 | −--- a/paper/tables/tab_reconciliation.tex | |
| 185 | −+++ b/paper/tables/tab_reconciliation.tex | |
| 186 | −@@ -2,7 +2,7 @@ | |
| 187 | − \toprule | |
| 188 | − Step & Count \\ | |
| 189 | − \midrule | |
| 190 | −-iShares IWV holdings file, equity lines with a ticker (as of Oct 23, 2026) & 2{,}587 \\ | |
| 191 | −+iShares IWV holdings file, equity lines with a ticker (as of Oct 23, 2026); count reported by the build log, source file not archived & 2{,}587 \\ | |
| 192 | − \quad of which mapped to an SEC CIK (CVRs, escrow lines and FDIC-only banks excluded) & 2{,}573 \\ | |
| 193 | − \quad distinct CIKs (share classes collapsed) & 2{,}555 \\ | |
| 194 | − S\&P~500 constituents, cached snapshot of 2026-05-25 (500 CIKs) & 503 \\ | |
| 195 | −@@ -16,4 +16,4 @@ Issuers with at least one 10-K, 10-Q or 8-K since 2010 & 2{,}499 \\ | |
| 196 | − Issuers without any such filing (foreign private issuers filing 20-F/40-F, FDIC-only banks) & 65 \\ | |
| 197 | − Issuers with at least one resolved project & 2{,}492 \\ | |
| 198 | − \bottomrule | |
| 199 | −-\end{tabular} | |
| 200 | −\ No newline at end of file | |
| 201 | −+\end{tabular} | |
| 202 | −diff --git a/paper/tables/tab_sections.tex b/paper/tables/tab_sections.tex | |
| 203 | −index 57983ae..1c741a2 100644 | |
| 204 | −--- a/paper/tables/tab_sections.tex | |
| 205 | −+++ b/paper/tables/tab_sections.tex | |
| 206 | −@@ -1,11 +1,11 @@ | |
| 207 | −-\begin{tabular}{lrrrrrr} | |
| 208 | −+\begin{tabular}{lrrrrrrrr} | |
| 209 | − \toprule | |
| 210 | −-Form & Parsed sections & Median words & Sections sent to the extractor & Sections with $\geq 1$ mention & Mentions & Issuers \\ | |
| 211 | −+Form & Parsed sections & Median words & Ledgered sections ($\geq$ 30 words) & Gate-passing calls & Sections with $\geq 1$ mention & Mentions returned by the model (ledger) & Mentions stored & Issuers \\ | |
| 212 | − \midrule | |
| 213 | −-10-K & 341{,}207 & 875 & 143{,}704 & 30{,}877 & 81{,}622 & 2{,}464 \\ | |
| 214 | −-10-Q & 600{,}471 & 500 & 578{,}793 & 75{,}705 & 152{,}261 & 2{,}494 \\ | |
| 215 | −-8-K & 400{,}605 & 575 & 400{,}601 & 61{,}648 & 74{,}594 & 2{,}499 \\ | |
| 216 | −+10-K & 341{,}207 & 875 & 143{,}704 & 135{,}310 & 30{,}877 & 81{,}622 & 81{,}495 & 2{,}464 \\ | |
| 217 | −+10-Q & 600{,}471 & 500 & 578{,}793 & 363{,}973 & 75{,}705 & 152{,}261 & 152{,}004 & 2{,}494 \\ | |
| 218 | −+8-K & 400{,}605 & 575 & 400{,}601 & 204{,}442 & 61{,}648 & 74{,}594 & 74{,}566 & 2{,}499 \\ | |
| 219 | − \midrule | |
| 220 | −-Total & 1{,}342{,}283 & & 1{,}123{,}098 & 168{,}230 & 308{,}477 & 2{,}499 \\ | |
| 221 | −+Total & 1{,}342{,}283 & & 1{,}123{,}098 & 703{,}725 & 168{,}230 & 308{,}477 & 308{,}065 & 2{,}499$^{\dagger}$ \\ | |
| 222 | − \bottomrule | |
| 223 | −-\end{tabular} | |
| 224 | −\ No newline at end of file | |
| 225 | −+\end{tabular} | |
| 226 | −diff --git a/paper/tables/tab_sectors.tex b/paper/tables/tab_sectors.tex | |
| 227 | −index 34a1b08..a35431e 100644 | |
| 228 | −--- a/paper/tables/tab_sectors.tex | |
| 229 | −+++ b/paper/tables/tab_sectors.tex | |
| 230 | −@@ -14,4 +14,4 @@ Consumer Staples & 103 & 36 & 103 & 5{,}921 & 57.5 \\ | |
| 231 | − Utilities & 68 & 31 & 66 & 4{,}920 & 74.5 \\ | |
| 232 | − Communication Services & 105 & 20 & 101 & 4{,}520 & 44.8 \\ | |
| 233 | − \bottomrule | |
| 234 | −-\end{tabular} | |
| 235 | −\ No newline at end of file | |
| 236 | −+\end{tabular} | |
| 237 | −diff --git a/paper/tables/tab_status.tex b/paper/tables/tab_status.tex | |
| 238 | −index 2b94374..dc3cc93 100644 | |
| 239 | −--- a/paper/tables/tab_status.tex | |
| 240 | −+++ b/paper/tables/tab_status.tex | |
| 241 | −@@ -8,4 +8,4 @@ Latest status & Projects & Mentions per project & Projects & Span of cited years | |
| 242 | − \texttt{mentioned} & 2{,}745 & 6-10 & 6{,}173 & $>$5 years & 10{,}326 \\ | |
| 243 | − & & >10 & 3{,}769 & unknown years & 17{,}599 \\ | |
| 244 | − \bottomrule | |
| 245 | −-\end{tabular} | |
| 246 | −\ No newline at end of file | |
| 247 | −+\end{tabular} | |
| 248 | −diff --git a/paper/tables/tab_top_issuers.tex b/paper/tables/tab_top_issuers.tex | |
| 249 | −index 03aae51..918e7b9 100644 | |
| 250 | −--- a/paper/tables/tab_top_issuers.tex | |
| 251 | −+++ b/paper/tables/tab_top_issuers.tex | |
| 252 | −@@ -15,4 +15,4 @@ CLSK & Cleanspark & 170 \\ | |
| 253 | − CWEN & Clearway Energy Inc Class C & 168 \\ | |
| 254 | − ALK & Alaska Air Group Inc & 168 \\ | |
| 255 | − \bottomrule | |
| 256 | −-\end{tabular} | |
| 257 | −\ No newline at end of file | |
| 258 | −+\end{tabular} | |
| 259 | −diff --git a/paper/tables/tab_types.tex b/paper/tables/tab_types.tex | |
| 260 | −index 78f685e..e2c2ff8 100644 | |
| 261 | −--- a/paper/tables/tab_types.tex | |
| 262 | −+++ b/paper/tables/tab_types.tex | |
| 263 | −@@ -1,29 +1,29 @@ | |
| 264 | −-\begin{tabular}{llrrrrr} | |
| 265 | −+\begin{tabular}{llrrrrrrr} | |
| 266 | − \toprule | |
| 267 | −-Code & Category & Projects & Share (\%) & With amount & Median amount (M USD) & Mentions / project \\ | |
| 268 | −+Code & Category & Projects & Share (\%) & With amount ($N$) & Median amount (M USD) & 95\% CI of the median & Mentions / project & $\geq 3$ distinct names (\%) \\ | |
| 269 | − \midrule | |
| 270 | −-\texttt{ma\_integration} & M\&A / integration & 41{,}742 & 34.5 & 28{,}044 & 155.0 & 3.12 \\ | |
| 271 | −-\texttt{capex\_program} & Capital expenditure program & 10{,}720 & 8.9 & 9{,}452 & 300.0 & 1.79 \\ | |
| 272 | −-\texttt{partnership} & Strategic partnership & 9{,}909 & 8.2 & 2{,}943 & 75.0 & 1.77 \\ | |
| 273 | −-\texttt{geographic\_expansion} & Geographic expansion & 7{,}868 & 6.5 & 1{,}431 & 36.7 & 2.25 \\ | |
| 274 | −-\texttt{plant\_construction} & Plant / site construction & 7{,}590 & 6.3 & 2{,}511 & 56.0 & 2.42 \\ | |
| 275 | −-\texttt{cost\_reduction} & Cost reduction / restructuring & 6{,}481 & 5.4 & 4{,}378 & 50.0 & 2.03 \\ | |
| 276 | −-\texttt{drug\_pipeline} & Drug / clinical pipeline & 5{,}360 & 4.4 & 778 & 46.1 & 4.99 \\ | |
| 277 | −-\texttt{product\_launch} & New product / launch & 5{,}356 & 4.4 & 447 & 26.7 & 2.33 \\ | |
| 278 | −-\texttt{rd\_program} & R\&D program & 5{,}080 & 4.2 & 1{,}272 & 20.0 & 2.31 \\ | |
| 279 | −-\texttt{infrastructure} & Infrastructure investment & 4{,}481 & 3.7 & 1{,}694 & 48.0 & 1.90 \\ | |
| 280 | −-\texttt{manufacturing\_expansion} & Manufacturing / capacity expansion & 4{,}140 & 3.4 & 1{,}040 & 45.0 & 2.13 \\ | |
| 281 | −-\texttt{technology\_deployment} & Technology deployment & 4{,}128 & 3.4 & 1{,}219 & 135.0 & 1.63 \\ | |
| 282 | −-\texttt{digital\_transformation} & Digital transformation & 2{,}642 & 2.2 & 240 & 34.2 & 1.99 \\ | |
| 283 | −-\texttt{erp\_implementation} & ERP / systems implementation & 1{,}735 & 1.4 & 184 & 15.0 & 2.44 \\ | |
| 284 | −-\texttt{sustainability} & Sustainability / ESG & 1{,}305 & 1.1 & 410 & 34.4 & 2.00 \\ | |
| 285 | −-\texttt{supply\_chain} & Supply-chain initiative & 684 & 0.6 & 139 & 38.0 & 1.71 \\ | |
| 286 | −-\texttt{data\_center} & Data center & 449 & 0.4 & 129 & 166.0 & 1.98 \\ | |
| 287 | −-\texttt{energy\_transition} & Energy transition / renewables & 415 & 0.3 & 109 & 109.0 & 2.09 \\ | |
| 288 | −-\texttt{ai\_initiative} & AI / ML initiative & 376 & 0.3 & 20 & 127.5 & 1.68 \\ | |
| 289 | −-\texttt{automation} & Automation / robotics & 374 & 0.3 & 25 & 13.7 & 1.68 \\ | |
| 290 | −-\texttt{cloud\_migration} & Cloud migration & 264 & 0.2 & 35 & 50.0 & 1.97 \\ | |
| 291 | −+\texttt{ma\_integration} & M\&A / integration & 41{,}742 & 34.5 & 28{,}044 & 155.0 & -- & 3.12 & 14.6 \\ | |
| 292 | −+\texttt{capex\_program} & Capital expenditure program & 10{,}720 & 8.9 & 9{,}452 & 300.0 & -- & 1.79 & 6.4 \\ | |
| 293 | −+\texttt{partnership} & Strategic partnership & 9{,}909 & 8.2 & 2{,}943 & 75.0 & -- & 1.77 & 6.7 \\ | |
| 294 | −+\texttt{geographic\_expansion} & Geographic expansion & 7{,}868 & 6.5 & 1{,}431 & 36.7 & -- & 2.25 & 10.2 \\ | |
| 295 | −+\texttt{plant\_construction} & Plant / site construction & 7{,}590 & 6.3 & 2{,}511 & 56.0 & -- & 2.42 & 13.5 \\ | |
| 296 | −+\texttt{cost\_reduction} & Cost reduction / restructuring & 6{,}481 & 5.4 & 4{,}378 & 50.0 & -- & 2.03 & 5.7 \\ | |
| 297 | −+\texttt{drug\_pipeline} & Drug / clinical pipeline & 5{,}360 & 4.4 & 778 & 46.1 & -- & 4.99 & 27.9 \\ | |
| 298 | −+\texttt{product\_launch} & New product / launch & 5{,}356 & 4.4 & 447 & 26.7 & -- & 2.33 & 12.2 \\ | |
| 299 | −+\texttt{rd\_program} & R\&D program & 5{,}080 & 4.2 & 1{,}272 & 20.0 & -- & 2.31 & 11.4 \\ | |
| 300 | −+\texttt{infrastructure} & Infrastructure investment & 4{,}481 & 3.7 & 1{,}694 & 48.0 & -- & 1.90 & 7.5 \\ | |
| 301 | −+\texttt{manufacturing\_expansion} & Manufacturing / capacity expansion & 4{,}140 & 3.4 & 1{,}040 & 45.0 & -- & 2.13 & 11.3 \\ | |
| 302 | −+\texttt{technology\_deployment} & Technology deployment & 4{,}128 & 3.4 & 1{,}219 & 135.0 & -- & 1.63 & 4.8 \\ | |
| 303 | −+\texttt{digital\_transformation} & Digital transformation & 2{,}642 & 2.2 & 240 & 34.2 & -- & 1.99 & 6.2 \\ | |
| 304 | −+\texttt{erp\_implementation} & ERP / systems implementation & 1{,}735 & 1.4 & 184 & 15.0 & -- & 2.44 & 3.5 \\ | |
| 305 | −+\texttt{sustainability} & Sustainability / ESG & 1{,}305 & 1.1 & 410 & 34.4 & -- & 2.00 & 6.1 \\ | |
| 306 | −+\texttt{supply\_chain} & Supply-chain initiative & 684 & 0.6 & 139 & 38.0 & -- & 1.71 & 3.5 \\ | |
| 307 | −+\texttt{data\_center} & Data center & 449 & 0.4 & 129 & 166.0 & -- & 1.98 & 9.3 \\ | |
| 308 | −+\texttt{energy\_transition} & Energy transition / renewables & 415 & 0.3 & 109 & 109.0 & -- & 2.09 & 10.1 \\ | |
| 309 | −+\texttt{ai\_initiative} & AI / ML initiative & 376 & 0.3 & 20 & \textcolor{gray}{127.5} & -- & 1.68 & 4.8 \\ | |
| 310 | −+\texttt{automation} & Automation / robotics & 374 & 0.3 & 25 & \textcolor{gray}{13.7} & -- & 1.68 & 2.7 \\ | |
| 311 | −+\texttt{cloud\_migration} & Cloud migration & 264 & 0.2 & 35 & \textcolor{gray}{50.0} & -- & 1.97 & 5.7 \\ | |
| 312 | − \midrule | |
| 313 | −- & Total & 121{,}099 & 100.0 & 56{,}500 & 128.5 & 2.54 \\ | |
| 314 | −+ & Total & 121{,}099 & 100.1 & 56{,}500 & 128.5 & -- & 2.54 & \\ | |
| 315 | − \bottomrule | |
| 316 | −-\end{tabular} | |
| 317 | −\ No newline at end of file | |
| 318 | −+\end{tabular} | |
| 319 | ||