{"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/conceptual-captions","name":"Conceptual Captions","full_name":"Conceptual Captions","description_markdown":"Automatic image captioning is the task of producing a natural-language utterance (usually a sentence) that correctly reflects the visual content of an image. Up to this point, the resource most used for this task was the MS-COCO dataset, containing around 120,000 images and 5-way image-caption annotations (produced by paid annotators).\r\n\r\nGoogle's Conceptual Captions dataset has more than 3 million images, paired with natural-language captions. In contrast with the curated style of the MS-COCO images, Conceptual Captions images and their raw descriptions are harvested from the web, and therefore represent a wider variety of styles. The raw descriptions are harvested from the Alt-text HTML attribute associated with web images. The authors developed an automatic pipeline that extracts, filters, and transforms candidate image/caption pairs, with the goal of achieving a balance of cleanliness, informativeness, fluency, and learnability of the resulting captions.\r\n\r\nSource: [Conceptual Captions](https://github.com/google-research-datasets/conceptual-captions)\r\nImage Source: [Sharma et al](https://www.aclweb.org/anthology/P18-1238)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/conceptual-captions","introduced_date":"2018-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/conceptual-captions-a-cleaned-hypernymed","title":"Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning","first_author":"Piyush Sharma","url":null},"license":{"name":"Custom","url":"https://github.com/google-research-datasets/conceptual-captions/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Conceptual Captions"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/conceptual_captions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/conceptual_captions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/conceptual-captions","url":"https://github.com/google-research-datasets/conceptual-captions","frameworks":[]}],"num_papers_in_archive":352,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-image-generation-on-conceptual","task":"Text-to-Image Generation","dataset_variant":"Conceptual Captions","rows":5,"metrics":["FID"],"first_row_in_archive_order":{"model":"Contextual RQ-Transformer","paper":"/paper/draft-and-revise-effective-image-generation","metrics":{"FID":"9.80"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-conceptual-captions","task":"Image Captioning","dataset_variant":"Conceptual Captions","rows":2,"metrics":["CIDEr","ROUGE-L","SPICE"],"first_row_in_archive_order":{"model":"ClipCap (MLP + GPT2 tuning)","paper":"/paper/clipcap-clip-prefix-for-image-captioning","metrics":{"CIDEr":"87.26","ROUGE-L":"26.71","SPICE":"18.5"},"code_links":[{"title":"rmokady/clip_prefix_caption","url":"https://github.com/rmokady/clip_prefix_caption"},{"title":"Japanese-Image-Captioning/ClipCap-for-Japanese","url":"https://github.com/Japanese-Image-Captioning/ClipCap-for-Japanese"},{"title":"sithu31296/image-captioning","url":"https://github.com/sithu31296/image-captioning"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/x_clip"}]},"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":6,"of":6,"counts":{"papers_with_a_benchmark_row":6,"with_a_code_link":5,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"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/draft-and-revise-effective-image-generation","slug":"draft-and-revise-effective-image-generation","title":"Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer","date":"2022-06-09","arxiv_id":"2206.04452","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/autoregressive-image-generation-using","slug":"autoregressive-image-generation-using","title":"Autoregressive Image Generation using Residual Quantization","date":"2022-03-03","arxiv_id":"2203.01941","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kakaobrain/rq-vae-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/autoregressive-image-generation-using#ran","syntology_url":"https://syntology.ai/paper/2203.01941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01941"}}}},{"paper":"/paper/high-resolution-image-synthesis-with-latent","slug":"high-resolution-image-synthesis-with-latent","title":"High-Resolution Image Synthesis with Latent Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10752","rows_on_this_dataset":1,"code_links":41,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":22,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":14,"samples_unverified":6,"pointer_only_for_licence":10,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/high-resolution-image-synthesis-with-latent#ran","syntology_url":"https://syntology.ai/paper/2112.10752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10752"}}}},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clipcap-clip-prefix-for-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2111.09734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09734"}}}},{"paper":"/paper/imagebart-bidirectional-context-with","slug":"imagebart-bidirectional-context-with","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","date":"2021-08-19","arxiv_id":"2108.08827","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/taming-transformers-for-high-resolution-image","slug":"taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","arxiv_id":"2012.09841","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["CompVis/taming-transformers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/taming-transformers-for-high-resolution-image#ran","syntology_url":"https://syntology.ai/paper/2012.09841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09841"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/draft-and-revise-effective-image-generation","slug":"draft-and-revise-effective-image-generation","title":"Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer","date":"2022-06-09","arxiv_id":"2206.04452","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/autoregressive-image-generation-using","slug":"autoregressive-image-generation-using","title":"Autoregressive Image Generation using Residual Quantization","date":"2022-03-03","arxiv_id":"2203.01941","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kakaobrain/rq-vae-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/autoregressive-image-generation-using#ran","syntology_url":"https://syntology.ai/paper/2203.01941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01941"}}}},{"paper":"/paper/high-resolution-image-synthesis-with-latent","slug":"high-resolution-image-synthesis-with-latent","title":"High-Resolution Image Synthesis with Latent Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10752","rows_on_this_dataset":1,"code_links":41,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":28,"samples_ran":22,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":14,"samples_unverified":6,"pointer_only_for_licence":10,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/high-resolution-image-synthesis-with-latent#ran","syntology_url":"https://syntology.ai/paper/2112.10752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10752"}}}},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clipcap-clip-prefix-for-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2111.09734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09734"}}}},{"paper":"/paper/imagebart-bidirectional-context-with","slug":"imagebart-bidirectional-context-with","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","date":"2021-08-19","arxiv_id":"2108.08827","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/taming-transformers-for-high-resolution-image","slug":"taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","arxiv_id":"2012.09841","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["CompVis/taming-transformers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/taming-transformers-for-high-resolution-image#ran","syntology_url":"https://syntology.ai/paper/2012.09841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09841"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/conceptual-captions/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/conceptual-captions/papers/ran/1","json":"/dataset/conceptual-captions/papers/ran/1.json","rows":4}],"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":4,"samples_harvested":41,"samples_ran":35,"samples_constructed":1,"samples_ran_checked":16,"samples_ran_instrument_failed":19,"samples_unverified":6,"pointer_only_for_licence":17,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":4,"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":"d45d140d2257b5607c076f5589ac17119153432279c5b2e43ffa9f8e8115359c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}