[ { "key": "BSHJRJVA", "version": 24, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/BSHJRJVA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/BSHJRJVA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "BSHJRJVA", "version": 24, "itemType": "attachment", "linkMode": "imported_url", "title": "Large Scale Page-Based Book Similarity Clustering", "accessDate": "2015-04-21T19:50:56Z", "url": "http://www.icdar2011.org/fileup/PDF/4520a119.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "4520a119.pdf", "md5": "8f5566dc56b0eb4b0db3ee9c2d899c77", "mtime": 1429645858000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-04-21T19:50:56Z", "dateModified": "2015-04-21T19:51:36Z" } }, { "key": "TGE35269", "version": 25, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/TGE35269", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/TGE35269", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "TGE35269", "version": 25, "itemType": "attachment", "linkMode": "imported_url", "title": "Large Scale Page-Based Book Similarity Clustering - 4520a119.pdf", "accessDate": "2015-04-21T19:51:20Z", "url": "http://www.icdar2011.org/fileup/PDF/4520a119.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "4520a119.pdf", "md5": "8f5566dc56b0eb4b0db3ee9c2d899c77", "mtime": 1429645882000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-04-21T19:51:20Z", "dateModified": "2015-04-21T19:51:22Z" } }, { "key": "P7RID4SN", "version": 21, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/P7RID4SN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/P7RID4SN", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/338207/items/FF42IC5U", "type": "application/json" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } } }, "data": { "key": "P7RID4SN", "version": 21, "parentItem": "FF42IC5U", "itemType": "attachment", "linkMode": "imported_url", "title": "Google Scholar Citations", "accessDate": "2015-04-21T19:49:55Z", "url": "https://scholar.google.com/citations?view_op=view_citation&hl=en&user=iK3jdIUAAAAJ&citation_for_view=iK3jdIUAAAAJ:d1gkVwhDpl0C", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citations.html", "md5": "c3622ff2a6f576e392789518b01a1e6e", "mtime": 1429645794000, "tags": [], "relations": {}, "dateAdded": "2015-04-21T19:49:55Z", "dateModified": "2015-04-21T19:49:55Z" } }, { "key": "TT7M94IR", "version": 19, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/TT7M94IR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/TT7M94IR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "TT7M94IR", "version": 19, "itemType": "attachment", "linkMode": "imported_url", "title": "Winnowing: Local Algorithms for Document Fingerprinting", "accessDate": "2015-04-21T19:49:12Z", "url": "http://theory.stanford.edu/~aiken/publications/papers/sigmod03.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "sigmod03.pdf", "md5": "232512a681d2488f61ade07516f899b5", "mtime": 1429645752000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-04-21T19:49:12Z", "dateModified": "2015-04-21T19:49:27Z" } }, { "key": "55PZ9TQP", "version": 16, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/55PZ9TQP", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/55PZ9TQP", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "55PZ9TQP", "version": 16, "itemType": "attachment", "linkMode": "imported_url", "title": "Utilizing Big Data in Identification and Correction of OCR Errors", "accessDate": "2015-04-10T10:47:15Z", "url": "http://digitalscholarship.unlv.edu/cgi/viewcontent.cgi?article=2915&context=thesesdissertations", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "viewcontent.pdf", "md5": "e77bfcdfd2713cb0803fd846d86a3f85", "mtime": 1428662836000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-04-10T10:47:15Z", "dateModified": "2015-04-10T10:47:29Z" } }, { "key": "QJAEK2HG", "version": 14, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/QJAEK2HG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/QJAEK2HG", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "QJAEK2HG", "version": 14, "itemType": "attachment", "linkMode": "imported_url", "title": "String techniques for detecting duplicates in document databases", "accessDate": "2015-04-10T08:54:30Z", "url": "http://download-v2.springer.com/static/pdf/973/art%253A10.1007%252FPL00021525.pdf?token2=exp=1428657146~acl=%2Fstatic%2Fpdf%2F973%2Fart%25253A10.1007%25252FPL00021525.pdf*~hmac=1f3659ba20b2a3cc4d4e5d6aa02746e3a0a515737b1825266bd5fbf5e662a063", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "art%3A10.1007%2FPL00021525.pdf", "md5": "65d468e300829f54f6a06a331861fa99", "mtime": 1428656070000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-04-10T08:54:30Z", "dateModified": "2015-04-10T08:54:36Z" } }, { "key": "TU9WPWAU", "version": 12, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/TU9WPWAU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/TU9WPWAU", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "TU9WPWAU", "version": 12, "itemType": "attachment", "linkMode": "imported_url", "title": "Character confusion versus focus word-based correction of spelling and OCR variants in corpora", "accessDate": "2015-03-27T13:46:57Z", "url": "http://download.springer.com/static/pdf/303/art%253A10.1007%252Fs10032-010-0133-5.pdf?auth66=1427464868_c4467374c5885422eed8ecc453a27efb&ext=.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "art%3A10.1007%2Fs10032-010-0133-5.pdf", "md5": "7025142bf4162703309272bd00a213bf", "mtime": 1427464017000, "tags": [ { "tag": "ocr" } ], "collections": [], "relations": {}, "dateAdded": "2015-03-27T13:46:57Z", "dateModified": "2015-03-27T13:47:03Z" } }, { "key": "WPT9TU52", "version": 9, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/WPT9TU52", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/WPT9TU52", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "WPT9TU52", "version": 9, "itemType": "attachment", "linkMode": "imported_url", "title": "Classification and distribution of optical character recognition errors", "accessDate": "2015-03-27T13:43:13Z", "url": "http://www.cs.lehigh.edu/~lopresti/Publications/1994/dr04.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "dr04.pdf", "md5": "f5e5fc6e67548abbcb7a38f3ed5af887", "mtime": 1427463793000, "tags": [ { "tag": "ocr" } ], "collections": [], "relations": {}, "dateAdded": "2015-03-27T13:43:13Z", "dateModified": "2015-03-27T13:43:42Z" } }, { "key": "IFVTACAK", "version": 9, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/IFVTACAK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/IFVTACAK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "IFVTACAK", "version": 9, "itemType": "attachment", "linkMode": "imported_url", "title": "An Evaluation of OCR Accuracy", "accessDate": "2015-03-27T13:39:16Z", "url": "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.80.7878&rep=rep1&type=pdf#page=9", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "download.pdf", "md5": "9b63be0c3ed052d3314b79b7680ba65f", "mtime": 1427463558000, "tags": [ { "tag": "ocr" } ], "collections": [], "relations": {}, "dateAdded": "2015-03-27T13:39:16Z", "dateModified": "2015-03-27T13:39:41Z" } }, { "key": "EPTTD67G", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/EPTTD67G", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/EPTTD67G", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/338207/items/4DKMHHNX", "type": "application/json" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } } }, "data": { "key": "EPTTD67G", "version": 4, "parentItem": "4DKMHHNX", "itemType": "attachment", "linkMode": "imported_url", "title": "CiteSeerX — Generating Synthetic Data for Text Analysis Systems", "accessDate": "2015-03-02T10:57:39Z", "url": "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.45.9370", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "summary.html", "md5": "19cbe3c302174995a6df4601b2e8ba23", "mtime": 1426925988000, "tags": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "7GZWQX55", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/7GZWQX55", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/7GZWQX55", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "7GZWQX55", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Extracting two thousand years of latin from a million book library", "accessDate": "2015-03-20T16:11:50Z", "url": "http://nlp.perseus.tufts.edu/docs/etc/jocch.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "jocch.pdf", "md5": "7107de7dcd6814046b8f5eec5d5d8f9c", "mtime": 1426925988000, "tags": [ { "tag": "internet archive" }, { "tag": "ocr" } ], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "8T5WNBTB", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/8T5WNBTB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/8T5WNBTB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "8T5WNBTB", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Organizing the OCA: Learning Faceted Subjects from a Library of Digital Books", "accessDate": "2015-03-20T08:42:11Z", "url": "http://maroo.cs.umass.edu/pdf/IR-571.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "IR-571.pdf", "md5": "d05f4dfb7e5a834e63a138b13d0bec85", "mtime": 1426925988000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "RVQJC6PD", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/RVQJC6PD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/RVQJC6PD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "RVQJC6PD", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Finding Translations in Scanned Book Collections", "accessDate": "2015-03-18T13:21:44Z", "url": "http://people.cs.umass.edu/~zeki/pubs/yalniz_manmatha_SIGIR12.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "yalniz_manmatha_SIGIR12.pdf", "md5": "3b531ee06fcfad6f5973def3299f3056", "mtime": 1426925988000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "H4BBZE8T", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/H4BBZE8T", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/H4BBZE8T", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "H4BBZE8T", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Similarity Estimation Techniques from Rounding Algorithms", "accessDate": "2015-02-26T17:56:44Z", "url": "http://www.cs.princeton.edu/courses/archive/spring04/cos598B/bib/CharikarEstim.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "CharikarEstim.pdf", "md5": "ef974b5863e9f3075ed011697621e45a", "mtime": 1426925987000, "tags": [ { "tag": "simhash" } ], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "BEFXPUS3", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/BEFXPUS3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/BEFXPUS3", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "BEFXPUS3", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Detecting Near-Duplicates for Web Crawling", "accessDate": "2015-02-26T13:24:05Z", "url": "http://www.wwwconference.org/www2007/papers/paper215.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "paper215.pdf", "md5": "352dec236cc71e1142940d0bd2d53287", "mtime": 1426925987000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "6XJBV2TS", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/6XJBV2TS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/6XJBV2TS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "6XJBV2TS", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "MMDS: 3. Finding Similar Items", "accessDate": "2015-02-26T09:19:05Z", "url": "http://infolab.stanford.edu/~ullman/mmds/ch3.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "ch3.pdf", "md5": "43fcbaed4d8151a150521c50f9270874", "mtime": 1426925987000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "3EMNQFSN", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/3EMNQFSN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/3EMNQFSN", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/338207/items/AI6VK2EA", "type": "application/json" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } } }, "data": { "key": "3EMNQFSN", "version": 4, "parentItem": "AI6VK2EA", "itemType": "attachment", "linkMode": "imported_url", "title": "Million Book Project : Free Texts : Download & Streaming : Internet Archive", "accessDate": "2015-03-20T16:19:34Z", "url": "https://archive.org/details/millionbooks", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "millionbooks.html", "md5": "553b98e94b8cf4a6c5dec9fe66517a6e", "mtime": 1426925988000, "tags": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "U886NJ4P", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/U886NJ4P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/U886NJ4P", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/338207/items/TQXZBSKW", "type": "application/json" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } } }, "data": { "key": "U886NJ4P", "version": 4, "parentItem": "TQXZBSKW", "itemType": "attachment", "linkMode": "imported_url", "title": "simhash", "accessDate": "2015-03-02T09:56:39Z", "url": "http://matpalm.com/resemblance/simhash/", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "simhash.html", "md5": "c5cc8bbcf7c6a91e7af6054ef3866de0", "mtime": 1426925988000, "tags": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "GPRT5J34", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/GPRT5J34", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/GPRT5J34", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "GPRT5J34", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Detecting Near-Duplicates in Large-Scale Short Text Databases", "accessDate": "2015-03-20T16:21:24Z", "url": "http://128.148.32.110/courses/csci2531/papers/duplicateshorttext.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "duplicateshorttext.pdf", "md5": "4791bd30c608d72585334c3b614fe3a2", "mtime": 1426925988000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "TW6J8E73", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/TW6J8E73", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/TW6J8E73", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "TW6J8E73", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Evaluating models of latent document semantics in the presence of OCR errors", "accessDate": "2015-03-20T16:05:26Z", "url": "http://www.aclweb.org/anthology/D10-1024", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "D10-1024.pdf", "md5": "7a842d7d17b005a4dea41ab42576c123", "mtime": 1426925988000, "tags": [ { "tag": "ocr" }, { "tag": "syntetic dataset" } ], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "9K2TN2QR", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/9K2TN2QR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/9K2TN2QR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "9K2TN2QR", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Partial Duplicate Detection for Large Book Collections", "accessDate": "2015-03-18T13:19:45Z", "url": "http://people.cs.umass.edu/~zeki/pubs/yalniz_et_al_CIKM_11.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "yalniz_et_al_CIKM_11.pdf", "md5": "21cf418d19bfc547b90ac83b1bc7db9a", "mtime": 1426925988000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "R8H3ZBJM", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/R8H3ZBJM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/R8H3ZBJM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "R8H3ZBJM", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Near Duplicate Detection in an Academic Digital Library", "accessDate": "2015-03-18T13:09:48Z", "url": "http://www.personal.psu.edu/kiw5209/papers/2013/williams_doceng2013.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "williams_doceng2013.pdf", "md5": "6e2c79d9cc1fe8ec7450f21c53b7392d", "mtime": 1426925988000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "T2ZP94DQ", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/T2ZP94DQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/T2ZP94DQ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "T2ZP94DQ", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Methods for identifying versioned and plagiarized documents - jasist03thz.pdf", "accessDate": "2015-02-27T09:33:36Z", "url": "http://people.eng.unimelb.edu.au/jzobel/fulltext/jasist03thz.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "jasist03thz.pdf", "md5": "3951ff7eca050df61d8104071544a23d", "mtime": 1426925987000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "E2ECZ4NR", "version": 4, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/E2ECZ4NR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/E2ECZ4NR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "E2ECZ4NR", "version": 4, "itemType": "attachment", "linkMode": "imported_url", "title": "Similarity Preserving Hashing", "accessDate": "2015-02-25T12:21:21Z", "url": "https://www.fbi.h-da.de/fileadmin/gruppen/FG-IT-Sicherheit/Lectures/selected-topics-it-sec/vorlesung_it-sec_ss12_kap03_sphf.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "vorlesung_it-sec_ss12_kap03_sphf.pdf", "md5": "24c5c94a779bde61c0a97261e222b10b", "mtime": 1426925987000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } }, { "key": "6VF6IWKX", "version": 3, "library": { "type": "group", "id": 338207, "name": "bookhash", "links": { "alternate": { "href": "https://www.zotero.org/groups/bookhash", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/338207/items/6VF6IWKX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/bookhash/items/6VF6IWKX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 549936, "username": "klemo", "name": "klemo", "links": { "alternate": { "href": "https://www.zotero.org/klemo", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "6VF6IWKX", "version": 3, "itemType": "attachment", "linkMode": "imported_url", "title": "Evaluating topic models for digital libraries", "accessDate": "2015-03-20T16:01:43Z", "url": "http://people.eng.unimelb.edu.au/tbaldwin/pubs/jcdl2010.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "jcdl2010.pdf", "md5": "35751ee7890f2d031de4daed729c72dd", "mtime": 1426925988000, "tags": [], "collections": [], "relations": {}, "dateAdded": "2015-03-21T08:19:47Z", "dateModified": "2015-03-21T08:19:47Z" } } ]