{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/findvehicle","name":"FindVehicle","full_name":null,"description_markdown":"The ***first*** NER dataset in the field of traffic,  which is to extract the characteristics and attributes of the vehicle on the road.\r\n\r\n* Both flat and overlapped named entities annotation.\r\n* Both coarse-grained and fine-grained named entities.\r\n* It contains 8 kinds of coarse-grained entities and 12 kinds of fine-grained entities. (It includes 65 vehicle brands and 4793 vehicle models all over the world.)","description_withheld":null,"homepage":"https://github.com/GuanRunwei/FindVehicle","introduced_date":"2022-09-01","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC BY-NC","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"UIE","url":"/task/uie","datasets_with_task":"/datasets/task/uie"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FindVehicle"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-findvehicle","task":"Named Entity Recognition (NER)","dataset_variant":"FindVehicle","rows":3,"metrics":["F1 Score","F1"],"first_row_in_archive_order":{"model":"BiLSTM-CRF","paper":"/paper/bidirectional-lstm-crf-models-for-sequence","metrics":{"F1 Score":"49.5"},"code_links":[{"title":"determined22/zh-ner-tf","url":"https://github.com/determined22/zh-ner-tf"},{"title":"guillaumegenthial/tf_ner","url":"https://github.com/guillaumegenthial/tf_ner"},{"title":"baiyang2464/chatbot-base-on-Knowledge-Graph","url":"https://github.com/baiyang2464/chatbot-base-on-Knowledge-Graph"},{"title":"GlassyWing/bi-lstm-crf","url":"https://github.com/GlassyWing/bi-lstm-crf"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/lstm_crf"},{"title":"jidasheng/bi-lstm-crf","url":"https://github.com/jidasheng/bi-lstm-crf"},{"title":"aonotas/deep-crf","url":"https://github.com/aonotas/deep-crf"},{"title":"gxzzz/bilstm-crf","url":"https://github.com/gxzzz/bilstm-crf"},{"title":"epwalsh/pytorch-crf","url":"https://github.com/epwalsh/pytorch-crf"},{"title":"ngoquanghuy99/POS-Tagging-BiLSTM-CRF","url":"https://github.com/ngoquanghuy99/POS-Tagging-BiLSTM-CRF"},{"title":"HassanAzzam/Arabic-NER","url":"https://github.com/HassanAzzam/Arabic-NER"},{"title":"zysite/post","url":"https://github.com/zysite/post"},{"title":"DimasDMM/diseases-ner","url":"https://github.com/DimasDMM/diseases-ner"},{"title":"hazelnutsgz/Naive-LSTM-CRF","url":"https://github.com/hazelnutsgz/Naive-LSTM-CRF"},{"title":"kyzhouhzau/CCLNER","url":"https://github.com/kyzhouhzau/CCLNER"},{"title":"JZ-LIANG/CRF-LSTM-NER","url":"https://github.com/JZ-LIANG/CRF-LSTM-NER"},{"title":"moejoe95/crf-vs-rnn-ner","url":"https://github.com/moejoe95/crf-vs-rnn-ner"},{"title":"sarveshsparab/BiLSTMCRFSeqTag","url":"https://github.com/sarveshsparab/BiLSTMCRFSeqTag"},{"title":"sumehta/bilstm_crf_extract","url":"https://github.com/sumehta/bilstm_crf_extract"},{"title":"UcasLzz/ChineseWordSeg-POS","url":"https://github.com/UcasLzz/ChineseWordSeg-POS"},{"title":"Akshayanti/supersense-sequence-labelling","url":"https://github.com/Akshayanti/supersense-sequence-labelling"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/lstm_crf"},{"title":"UcasLzz/CWS","url":"https://github.com/UcasLzz/CWS"},{"title":"akshay-gupta123/BI-LSTM-CRF_Tensorflow","url":"https://github.com/akshay-gupta123/BI-LSTM-CRF_Tensorflow"},{"title":"2023-MindSpore-1/ms-code-5","url":"https://github.com/2023-MindSpore-1/ms-code-5/tree/main/lstm_crf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/uie-on-findvehicle","task":"UIE","dataset_variant":"FindVehicle","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"KnowCoder-7b-IE","paper":"/paper/knowcoder-coding-structured-knowledge-into","metrics":{"F1 score":"99.4"},"code_links":[{"title":"ICT-GoKnow/KnowCoder","url":"https://github.com/ICT-GoKnow/KnowCoder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":4,"of":4,"counts":{"papers_with_a_benchmark_row":4,"with_a_code_link":4,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/universalner-targeted-distillation-from-large","slug":"universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","arxiv_id":"2308.03279","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universalner-targeted-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2308.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03279"}}}},{"paper":"/paper/flert-document-level-features-for-named","slug":"flert-document-level-features-for-named","title":"FLERT: Document-Level Features for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06993","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bidirectional-lstm-crf-models-for-sequence","slug":"bidirectional-lstm-crf-models-for-sequence","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","date":"2015-08-09","arxiv_id":"1508.01991","rows_on_this_dataset":1,"code_links":25,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bidirectional-lstm-crf-models-for-sequence#ran","syntology_url":"https://syntology.ai/paper/1508.01991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.01991"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/universalner-targeted-distillation-from-large","slug":"universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","arxiv_id":"2308.03279","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universalner-targeted-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2308.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03279"}}}},{"paper":"/paper/flert-document-level-features-for-named","slug":"flert-document-level-features-for-named","title":"FLERT: Document-Level Features for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06993","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bidirectional-lstm-crf-models-for-sequence","slug":"bidirectional-lstm-crf-models-for-sequence","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","date":"2015-08-09","arxiv_id":"1508.01991","rows_on_this_dataset":1,"code_links":25,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bidirectional-lstm-crf-models-for-sequence#ran","syntology_url":"https://syntology.ai/paper/1508.01991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.01991"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/findvehicle/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/findvehicle/papers/ran/1","json":"/dataset/findvehicle/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"2660fd962162c04c7ea2a042a732a412f4fd2c22c29556c364c725f26b42ad59","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}