First implementation (#1)

Reviewed-on: #1

vectors/projections.jsonl

@@ -0,0 +1,29 @@
+{"align_key":"bd1193ec5e58680b96a5c7b0d8200e1b42f1ff74a7b6ddc4858d470e949cbf9a","complex":[],"id":"h2o-math","lossy":"thesolventish2o.","match_hash":"45ae8b6b0b3c7c0acea0ab1bb873f0afbddb1a3cc7bae762a6304e86d8e11442","normalized":"The solvent is $H_2O$.","plain":"The solvent is $H_2O$.","runs":[{"kind":"text","text":"The solvent is "},{"kind":"math","notation":"tex","source":"H_2O"},{"kind":"text","text":"."}],"strict":"The solvent is H_{2}O.","text_hash":"db7febd83f01411039085c52f807f536ab9307f2a89f04a18dac9f744d4d9a38"}
+{"align_key":"bd1193ec5e58680b96a5c7b0d8200e1b42f1ff74a7b6ddc4858d470e949cbf9a","complex":[],"id":"h2o-split-math","lossy":"thesolventish2o.","match_hash":"45ae8b6b0b3c7c0acea0ab1bb873f0afbddb1a3cc7bae762a6304e86d8e11442","normalized":"The solvent is H$_2$O.","plain":"The solvent is H$_2$O.","runs":[{"kind":"text","text":"The solvent is H"},{"kind":"math","notation":"tex","source":"_2"},{"kind":"text","text":"O."}],"strict":"The solvent is H_{2}O.","text_hash":"11cb89a8460bd1c34d530f70474695ff301ed1a320ee2d9ef297fa42b6607cb4"}
+{"align_key":"bd1193ec5e58680b96a5c7b0d8200e1b42f1ff74a7b6ddc4858d470e949cbf9a","complex":[],"id":"h2o-mathrm","lossy":"thesolventish2o.","match_hash":"45ae8b6b0b3c7c0acea0ab1bb873f0afbddb1a3cc7bae762a6304e86d8e11442","normalized":"The solvent is $\\mathrm{H}_{2}\\mathrm{O}$.","plain":"The solvent is $\\mathrm{H}_{2}\\mathrm{O}$.","runs":[{"kind":"text","text":"The solvent is "},{"kind":"math","notation":"tex","source":"\\mathrm{H}_{2}\\mathrm{O}"},{"kind":"text","text":"."}],"strict":"The solvent is H_{2}O.","text_hash":"c1123ca8e33cce46335fdb27d94cf25a725fc6fa5e3c490faf590dbe7d74a12b"}
+{"align_key":"bd1193ec5e58680b96a5c7b0d8200e1b42f1ff74a7b6ddc4858d470e949cbf9a","complex":[],"id":"h2o-sub","lossy":"thesolventish2o.","match_hash":"45ae8b6b0b3c7c0acea0ab1bb873f0afbddb1a3cc7bae762a6304e86d8e11442","normalized":"The solvent is H2O.","plain":"The solvent is H2O.","runs":[{"kind":"text","text":"The solvent is H"},{"kind":"text","style":["sub"],"text":"2"},{"kind":"text","text":"O."}],"strict":"The solvent is H_{2}O.","text_hash":"4eda9afcb99d2e6ee8ccebdda0162bab85dc96efdaff38fd6dbc898c661ca91a"}
+{"align_key":"bd1193ec5e58680b96a5c7b0d8200e1b42f1ff74a7b6ddc4858d470e949cbf9a","complex":[],"id":"h2o-unicode","lossy":"thesolventish2o.","match_hash":"45ae8b6b0b3c7c0acea0ab1bb873f0afbddb1a3cc7bae762a6304e86d8e11442","normalized":"The solvent is H₂O.","plain":"The solvent is H₂O.","runs":[{"kind":"text","text":"The solvent is H₂O."}],"strict":"The solvent is H_{2}O.","text_hash":"2c0dd2f6a6adb414aa2fd642276c0cb5d0cf2248ef2cfc3b0ed77f2332aa2129"}
+{"align_key":"bd1193ec5e58680b96a5c7b0d8200e1b42f1ff74a7b6ddc4858d470e949cbf9a","complex":[],"id":"h2o-typst","lossy":"thesolventish2o.","match_hash":"45ae8b6b0b3c7c0acea0ab1bb873f0afbddb1a3cc7bae762a6304e86d8e11442","normalized":"The solvent is $H_2 O$.","plain":"The solvent is $H_2 O$.","runs":[{"kind":"text","text":"The solvent is "},{"kind":"math","notation":"typst","source":"H_2 O"},{"kind":"text","text":"."}],"strict":"The solvent is H_{2}O.","text_hash":"ed0698f969e83d036babeee757eddede4fd4cba5b4f3af336644f5a8c6808954"}
+{"align_key":"9467109667c9a35fb2df6a06327af4c63ef511a45e1a50e2c9386796d52d8bc9","complex":[],"id":"wavenumber-unicode","lossy":"abandnear1595cm−1.","match_hash":"d234490f1f606604bc9ff4f4c619bb81c91cc2683c0dd2cf412c9b03daf116bc","normalized":"A band near 1595 cm⁻¹.","plain":"A band near 1595 cm⁻¹.","runs":[{"kind":"text","text":"A band near 1595 cm⁻¹."}],"strict":"A band near 1595 cm^{−1}.","text_hash":"f9f6d5a155dadc7a3616969582c1d6f635185e17f41b88be611e8eb5f4e3a539"}
+{"align_key":"9467109667c9a35fb2df6a06327af4c63ef511a45e1a50e2c9386796d52d8bc9","complex":[],"id":"wavenumber-sup","lossy":"abandnear1595cm−1.","match_hash":"d234490f1f606604bc9ff4f4c619bb81c91cc2683c0dd2cf412c9b03daf116bc","normalized":"A band near 1595 cm-1.","plain":"A band near 1595 cm-1.","runs":[{"kind":"text","text":"A band near 1595 cm"},{"kind":"text","style":["sup"],"text":"-1"},{"kind":"text","text":"."}],"strict":"A band near 1595 cm^{−1}.","text_hash":"432ef2dda04d532b8e81febdff75b6a7f69bfe88fd8020518b3741c486f0cc51"}
+{"align_key":"9467109667c9a35fb2df6a06327af4c63ef511a45e1a50e2c9386796d52d8bc9","complex":[],"id":"wavenumber-math","lossy":"abandnear1595cm−1.","match_hash":"d234490f1f606604bc9ff4f4c619bb81c91cc2683c0dd2cf412c9b03daf116bc","normalized":"A band near 1595 $\\mathrm{cm}^{-1}$.","plain":"A band near 1595 $\\mathrm{cm}^{-1}$.","runs":[{"kind":"text","text":"A band near 1595 "},{"kind":"math","notation":"tex","source":"\\mathrm{cm}^{-1}"},{"kind":"text","text":"."}],"strict":"A band near 1595 cm^{−1}.","text_hash":"058f804ca85bd2742b40f871798e4697029ac1d34ae3fe84f08ea4549b771149"}
+{"align_key":"9467109667c9a35fb2df6a06327af4c63ef511a45e1a50e2c9386796d52d8bc9","complex":[],"id":"wavenumber-typst","lossy":"abandnear1595cm−1.","match_hash":"d234490f1f606604bc9ff4f4c619bb81c91cc2683c0dd2cf412c9b03daf116bc","normalized":"A band near 1595 $\"cm\"^(-1)$.","plain":"A band near 1595 $\"cm\"^(-1)$.","runs":[{"kind":"text","text":"A band near 1595 "},{"kind":"math","notation":"typst","source":"\"cm\"^(-1)"},{"kind":"text","text":"."}],"strict":"A band near 1595 cm^{−1}.","text_hash":"40c687f3ba83dadcd1c577c804b5621ca334637d3e227026b4c9b1a5f4b2c85e"}
+{"align_key":"8644140828bf1f481bb4afde325e12197b5284340e23a2c4defbfefd0db93398","complex":[],"id":"milli-unicode","lossy":"valuesbelow10−3weredropped.","match_hash":"402f18f84b6f9883c8014d2f7cf6278e6f5524f92079b1d0442debf544932fa0","normalized":"Values below 10⁻³ were dropped.","plain":"Values below 10⁻³ were dropped.","runs":[{"kind":"text","text":"Values below 10⁻³ were dropped."}],"strict":"Values below 10^{−3} were dropped.","text_hash":"01f80701006bb83a888b131f807424e880c379d290dfe579209f27ea544e4693"}
+{"align_key":"8644140828bf1f481bb4afde325e12197b5284340e23a2c4defbfefd0db93398","complex":[],"id":"milli-sup","lossy":"valuesbelow10−3weredropped.","match_hash":"402f18f84b6f9883c8014d2f7cf6278e6f5524f92079b1d0442debf544932fa0","normalized":"Values below 10−3 were dropped.","plain":"Values below 10−3 were dropped.","runs":[{"kind":"text","text":"Values below 10"},{"kind":"text","style":["sup"],"text":"−3"},{"kind":"text","text":" were dropped."}],"strict":"Values below 10^{−3} were dropped.","text_hash":"f85ff38541d4ef7c42982c0a6225a5159ddba3c3b03d554252b3e3fd9262cc70"}
+{"align_key":"8644140828bf1f481bb4afde325e12197b5284340e23a2c4defbfefd0db93398","complex":[],"id":"milli-math","lossy":"valuesbelow10−3weredropped.","match_hash":"402f18f84b6f9883c8014d2f7cf6278e6f5524f92079b1d0442debf544932fa0","normalized":"Values below $10^{-3}$ were dropped.","plain":"Values below $10^{-3}$ were dropped.","runs":[{"kind":"text","text":"Values below "},{"kind":"math","notation":"tex","source":"10^{-3}"},{"kind":"text","text":" were dropped."}],"strict":"Values below 10^{−3} were dropped.","text_hash":"510f7ffdcde8465761ee0be1277ea0c4a2ee2c3dbeeff66197c2b1e2a593967e"}
+{"align_key":"347038bde4eb9ddd4b7ead7285ffdcfd9296af9507fc2be04eae503b10290241","complex":[],"id":"kr-math","lossy":"theconstantkrislarge.","match_hash":"bcb9eafe84c3d52780bae37e433c0a25de552fc5c39efc6c0a2573ff74b9de78","normalized":"The constant $K_r$ is large.","plain":"The constant $K_r$ is large.","runs":[{"kind":"text","text":"The constant "},{"kind":"math","notation":"tex","source":"K_r"},{"kind":"text","text":" is large."}],"strict":"The constant K_{r} is large.","text_hash":"dfb8290ac5f6841ca8fd16cbf48bf02010db9f2d5bf4534c76bdb9843e630302"}
+{"align_key":"347038bde4eb9ddd4b7ead7285ffdcfd9296af9507fc2be04eae503b10290241","complex":[],"id":"kr-mathrm","lossy":"theconstantkrislarge.","match_hash":"bcb9eafe84c3d52780bae37e433c0a25de552fc5c39efc6c0a2573ff74b9de78","normalized":"The constant $K_{\\mathrm{r}}$ is large.","plain":"The constant $K_{\\mathrm{r}}$ is large.","runs":[{"kind":"text","text":"The constant "},{"kind":"math","notation":"tex","source":"K_{\\mathrm{r}}"},{"kind":"text","text":" is large."}],"strict":"The constant K_{r} is large.","text_hash":"1a78c9c621f0743d98f02364c474dfdc1d503f754359c16ac68d6c47d49c84de"}
+{"align_key":"347038bde4eb9ddd4b7ead7285ffdcfd9296af9507fc2be04eae503b10290241","complex":[],"id":"kr-sub","lossy":"theconstantkrislarge.","match_hash":"bcb9eafe84c3d52780bae37e433c0a25de552fc5c39efc6c0a2573ff74b9de78","normalized":"The constant Kr is large.","plain":"The constant Kr is large.","runs":[{"kind":"text","text":"The constant K"},{"kind":"text","style":["sub"],"text":"r"},{"kind":"text","text":" is large."}],"strict":"The constant K_{r} is large.","text_hash":"20b700fd3005722f68eba6f8e8656a4c646a77f618a11bd35a18665cfc7f4f5e"}
+{"align_key":"347038bde4eb9ddd4b7ead7285ffdcfd9296af9507fc2be04eae503b10290241","complex":[],"id":"kr-unicode","lossy":"theconstantkrislarge.","match_hash":"bcb9eafe84c3d52780bae37e433c0a25de552fc5c39efc6c0a2573ff74b9de78","normalized":"The constant Kᵣ is large.","plain":"The constant Kᵣ is large.","runs":[{"kind":"text","text":"The constant Kᵣ is large."}],"strict":"The constant K_{r} is large.","text_hash":"b636b6aa463b3a8648ef14f81ed699fb2dddd657363c4d35783e0b214d838392"}
+{"align_key":"c18a6f3dffdf8fcf355ef258e521f5dac9843bb9fc5d63c71c2d24b87a6f00a3","complex":[],"id":"ligature","lossy":"thefitisgood.","match_hash":"f2cafd933912c4ea86559633994fecbd344dfb0beaf15bf1858685c0ce471b6f","normalized":"The fit is good.","plain":"The fit is good.","runs":[{"kind":"text","text":"The fit is good."}],"strict":"The fit is good.","text_hash":"f9bbe4d605d8a243da53dfb2fc44f2b7b1e5df132116277fce9157a7f9c867f1"}
+{"align_key":"c18a6f3dffdf8fcf355ef258e521f5dac9843bb9fc5d63c71c2d24b87a6f00a3","complex":[],"id":"no-ligature","lossy":"thefitisgood.","match_hash":"f2cafd933912c4ea86559633994fecbd344dfb0beaf15bf1858685c0ce471b6f","normalized":"The fit is good.","plain":"The fit is good.","runs":[{"kind":"text","text":"The fit is good."}],"strict":"The fit is good.","text_hash":"f2cafd933912c4ea86559633994fecbd344dfb0beaf15bf1858685c0ce471b6f"}
+{"align_key":"20dd97f7d0a3372b59e2dcd3eee64fa213d7ead55dad8bc9e631d62c007c9b83","complex":[],"id":"micro-sign","lossy":"a5μmfilm.","match_hash":"e0266f7562269bc12d6d8bf51c52ffd6511c306b07a0db055aaf3890d7132c5c","normalized":"A 5 µm film.","plain":"A 5 µm film.","runs":[{"kind":"text","text":"A 5 µm film."}],"strict":"A 5 μm film.","text_hash":"0a120e4a1cd7b8f3ca2d4ea4c498dd075ae36be1b4cd78edf7475a3f4bbcff8b"}
+{"align_key":"20dd97f7d0a3372b59e2dcd3eee64fa213d7ead55dad8bc9e631d62c007c9b83","complex":[],"id":"greek-mu","lossy":"a5μmfilm.","match_hash":"e0266f7562269bc12d6d8bf51c52ffd6511c306b07a0db055aaf3890d7132c5c","normalized":"A 5 μm film.","plain":"A 5 μm film.","runs":[{"kind":"text","text":"A 5 μm film."}],"strict":"A 5 μm film.","text_hash":"e0266f7562269bc12d6d8bf51c52ffd6511c306b07a0db055aaf3890d7132c5c"}
+{"align_key":"c7788ac010791cdfc09f01c87089d499bc92cc558731818b7526a1a622cc7e93","complex":[],"id":"lost-superscript","lossy":"arateof103persecond.","match_hash":"59daf82ed56d0dce4eba9feac195e96c776461d5337deab9f935ff113e920d11","normalized":"A rate of 103 per second.","note":"OCR lost the superscript.","plain":"A rate of 103 per second.","runs":[{"kind":"text","text":"A rate of 103 per second."}],"strict":"A rate of 103 per second.","text_hash":"59daf82ed56d0dce4eba9feac195e96c776461d5337deab9f935ff113e920d11"}
+{"align_key":"c7788ac010791cdfc09f01c87089d499bc92cc558731818b7526a1a622cc7e93","complex":[],"id":"superscript","lossy":"arateof103persecond.","match_hash":"bcbd5154f56cbfe39b9c1ad80c0215fe1850106e796dd522669a95d31d4643d5","normalized":"A rate of 10³ per second.","plain":"A rate of 10³ per second.","runs":[{"kind":"text","text":"A rate of 10³ per second."}],"strict":"A rate of 10^{3} per second.","text_hash":"c490b1d6d08e9e0f1bef522f8a78a4f729cf981a7b6fc0c9cc41c1ec479d2115"}
+{"align_key":"73b02f8ceb20b94520bc5ca52100c56b14a46d9adb06dbb6c5a19810cf6137e0","complex":[],"id":"cite-mark","lossy":"theenergyislow.","match_hash":"98b2885f074339a8097b6c8c7f2253eb1bb66760684f5e216caccaf224d86d30","normalized":"The energy3 is low.","plain":"The energy3 is low.","runs":[{"kind":"text","text":"The energy"},{"kind":"cite","refs":[],"text":"3"},{"kind":"text","text":" is low."}],"strict":"The energy3 is low.","text_hash":"3166ad5ab03f88cd0c4868ebeb3475b9b3e13036c68ff57d0e6531d4e322fbb1"}
+{"align_key":"da65ae55cd55d409477a86e26876cf5f75556c79f612191b5a43af6d553ea0b0","complex":[],"id":"cite-as-text","lossy":"theenergy3islow.","match_hash":"3166ad5ab03f88cd0c4868ebeb3475b9b3e13036c68ff57d0e6531d4e322fbb1","normalized":"The energy3 is low.","plain":"The energy3 is low.","runs":[{"kind":"text","text":"The energy3 is low."}],"strict":"The energy3 is low.","text_hash":"3166ad5ab03f88cd0c4868ebeb3475b9b3e13036c68ff57d0e6531d4e322fbb1"}
+{"align_key":"6011a09330d84af0bbfaf227e9e23d8072dccd73513b1fc866df93808b43dd97","complex":["tex:\\frac{1}{2}kx^2"],"id":"complex","lossy":"theenergyisexactly.","match_hash":"d641b65aa2f6b697fd35c8e383e497abe456640af3cdecd28a8120fa92ea9664","normalized":"The energy is $\\frac{1}{2} k x^2$ exactly.","plain":"The energy is $\\frac{1}{2} k x^2$ exactly.","runs":[{"kind":"text","text":"The energy is "},{"kind":"math","notation":"tex","source":"\\frac{1}{2} k x^2"},{"kind":"text","text":" exactly."}],"strict":"The energy is  exactly.","text_hash":"d5a85176f4a53f91916b130e0b35b298e1b999132a6a925b4eccf8f20f2574b5"}
+{"align_key":"156cc56f1b8c79722ce3db0aec57879a4b2f467fdb69d75ac6bdae01b7bd4433","complex":[],"id":"hyphen-before-digit","lossy":"pages10−20andctctwith6−31g*","match_hash":"86f127250e5076b9c8b9b5c189361aed13705d1ceb7600cbe2b7ed07597a2313","normalized":"pages 10-20 and CT–CT with 6-31G*","plain":"pages 10-20 and CT–CT with 6-31G*","runs":[{"kind":"text","text":"pages 10-20 and CT–CT with 6-31G*"}],"strict":"pages 10−20 and CT–CT with 6−31G*","text_hash":"9dc7ad6bb0693572f0700420e1b2b1c723b39058784c76154e88fffa8fa0c8a8"}
+{"align_key":"156cc56f1b8c79722ce3db0aec57879a4b2f467fdb69d75ac6bdae01b7bd4433","complex":[],"id":"en-dash-before-digit","lossy":"pages10−20andctctwith6−31g*","match_hash":"1d9c138f8b902b350a1f4477e8b84b6a0a87f35a1dd38486112b7291db3aa150","normalized":"pages 10–20 and CT-CT with 6–31G*","plain":"pages 10–20 and CT-CT with 6–31G*","runs":[{"kind":"text","text":"pages 10–20 and CT-CT with 6–31G*"}],"strict":"pages 10−20 and CT-CT with 6−31G*","text_hash":"70b2e77b3966f2c506d87c12b13ebf7ae5193092f678eb101310f363d0ab605a"}
+{"align_key":"89658229bf51901882aae4f9543338d4321e4b666a2c191bca749e384fd0a1cc","complex":["tex:𝑥"],"id":"astral","lossy":"letvary.","match_hash":"3b6c539092c6c721ee808437e208b31a1fab3407b43d85e60d29edb65762ac20","normalized":"Let $𝑥$ vary.","plain":"Let $𝑥$ vary.","runs":[{"kind":"text","text":"Let "},{"kind":"math","notation":"tex","source":"𝑥"},{"kind":"text","text":" vary."}],"strict":"Let  vary.","text_hash":"43800bdb4e70f3613083dfe5ce728cf643a1d0d97d321f04cfbb4f9b2e56fc6f"}