{"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/wise","name":"WISE","full_name":null,"description_markdown":"WISE, the first benchmark specifically designed for World Knowledge-Informed Semantic Evaluation. WISE moves beyond simple word-pixel mapping by challenging models with 1000 meticulously crafted prompts across 25 sub-domains in cultural common sense, spatio-temporal understanding, and natural science.","description_withheld":null,"homepage":"https://github.com/PKU-YuanGroup/WISE","introduced_date":"2025-03-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/wise-a-world-knowledge-informed-semantic","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","first_author":"Yuwei Niu","url":null},"license":{"name":"MIT","url":null},"modalities":[],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"}],"languages":[],"variants":["WISE"],"data_loaders":[],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset_variant":"WISE","rows":14,"metrics":["Overall","Cultural","Time","Space","Biology","Physics","Chemistry"],"first_row_in_archive_order":{"model":"MindOmni\n(w/ cot)","paper":"/paper/mindomni-unleashing-reasoning-generation-in","metrics":{"Biology":"0.76","Chemistry":"0.52","Cultural":"0.75","Overall":"0.71","Physics":"0.72","Space":"0.76","Time":"0.70"},"code_links":[{"title":"easonxiao-888/mindomni","url":"https://github.com/easonxiao-888/mindomni"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/on-wise","task":"","dataset_variant":"WISE","rows":11,"metrics":["Overall","Cultural","Time","Space","Biology","Physics","Chemistry"],"first_row_in_archive_order":{"model":"UniWorld-V1","paper":"/paper/uniworld-v1-high-resolution-semantic-encoders","metrics":{"Biology":"0.45","Chemistry":"0.41","Cultural":"0.53","Overall":"0.55","Physics":"0.59","Space":"0.73","Time":"0.55"},"code_links":[{"title":"PKU-YuanGroup/UniWorld-V1","url":"https://github.com/PKU-YuanGroup/UniWorld-V1"},{"title":"pku-yuangroup/imgedit","url":"https://github.com/pku-yuangroup/imgedit"}]},"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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":10,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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/uniworld-v1-high-resolution-semantic-encoders","slug":"uniworld-v1-high-resolution-semantic-encoders","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","date":"2025-06-03","arxiv_id":"2506.03147","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/emerging-properties-in-unified-multimodal","slug":"emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","arxiv_id":"2505.14683","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emerging-properties-in-unified-multimodal#ran","syntology_url":"https://syntology.ai/paper/2505.14683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14683"}}}},{"paper":"/paper/mindomni-unleashing-reasoning-generation-in","slug":"mindomni-unleashing-reasoning-generation-in","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","date":"2025-05-19","arxiv_id":"2505.13031","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/transfer-between-modalities-with-metaqueries","slug":"transfer-between-modalities-with-metaqueries","title":"Transfer between Modalities with MetaQueries","date":"2025-04-08","arxiv_id":"2504.06256","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/janus-pro-unified-multimodal-understanding","slug":"janus-pro-unified-multimodal-understanding","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","date":"2025-01-29","arxiv_id":"2501.17811","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/janus-decoupling-visual-encoding-for-unified","slug":"janus-decoupling-visual-encoding-for-unified","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","date":"2024-10-17","arxiv_id":"2410.13848","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/emu3-next-token-prediction-is-all-you-need","slug":"emu3-next-token-prediction-is-all-you-need","title":"Emu3: Next-Token Prediction is All You Need","date":"2024-09-27","arxiv_id":"2409.18869","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emu3-next-token-prediction-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2409.18869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18869"}}}},{"paper":"/paper/show-o-one-single-transformer-to-unify","slug":"show-o-one-single-transformer-to-unify","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","date":"2024-08-22","arxiv_id":"2408.12528","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scaling-rectified-flow-transformers-for-high","slug":"scaling-rectified-flow-transformers-for-high","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","date":"2024-03-05","arxiv_id":"2403.03206","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-rectified-flow-transformers-for-high#ran","syntology_url":"https://syntology.ai/paper/2403.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03206"}}}},{"paper":"/paper/playground-v2-5-three-insights-towards","slug":"playground-v2-5-three-insights-towards","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","date":"2024-02-27","arxiv_id":"2402.17245","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pixart-a-fast-training-of-diffusion","slug":"pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","arxiv_id":"2310.00426","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["PixArt-alpha/PixArt-alpha"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pixart-a-fast-training-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2310.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00426"}}}},{"paper":"/paper/sdxl-improving-latent-diffusion-models-for","slug":"sdxl-improving-latent-diffusion-models-for","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","date":"2023-07-04","arxiv_id":"2307.01952","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":13,"pointer_only_for_licence":0,"official":{"repos":["stability-ai/generative-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sdxl-improving-latent-diffusion-models-for#ran","syntology_url":"https://syntology.ai/paper/2307.01952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01952"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/uniworld-v1-high-resolution-semantic-encoders","slug":"uniworld-v1-high-resolution-semantic-encoders","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","date":"2025-06-03","arxiv_id":"2506.03147","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/emerging-properties-in-unified-multimodal","slug":"emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","arxiv_id":"2505.14683","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emerging-properties-in-unified-multimodal#ran","syntology_url":"https://syntology.ai/paper/2505.14683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14683"}}}},{"paper":"/paper/mindomni-unleashing-reasoning-generation-in","slug":"mindomni-unleashing-reasoning-generation-in","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","date":"2025-05-19","arxiv_id":"2505.13031","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/transfer-between-modalities-with-metaqueries","slug":"transfer-between-modalities-with-metaqueries","title":"Transfer between Modalities with MetaQueries","date":"2025-04-08","arxiv_id":"2504.06256","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/janus-pro-unified-multimodal-understanding","slug":"janus-pro-unified-multimodal-understanding","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","date":"2025-01-29","arxiv_id":"2501.17811","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/janus-decoupling-visual-encoding-for-unified","slug":"janus-decoupling-visual-encoding-for-unified","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","date":"2024-10-17","arxiv_id":"2410.13848","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/emu3-next-token-prediction-is-all-you-need","slug":"emu3-next-token-prediction-is-all-you-need","title":"Emu3: Next-Token Prediction is All You Need","date":"2024-09-27","arxiv_id":"2409.18869","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/emu3-next-token-prediction-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2409.18869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18869"}}}},{"paper":"/paper/show-o-one-single-transformer-to-unify","slug":"show-o-one-single-transformer-to-unify","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","date":"2024-08-22","arxiv_id":"2408.12528","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scaling-rectified-flow-transformers-for-high","slug":"scaling-rectified-flow-transformers-for-high","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","date":"2024-03-05","arxiv_id":"2403.03206","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-rectified-flow-transformers-for-high#ran","syntology_url":"https://syntology.ai/paper/2403.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03206"}}}},{"paper":"/paper/playground-v2-5-three-insights-towards","slug":"playground-v2-5-three-insights-towards","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","date":"2024-02-27","arxiv_id":"2402.17245","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pixart-a-fast-training-of-diffusion","slug":"pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","arxiv_id":"2310.00426","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["PixArt-alpha/PixArt-alpha"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pixart-a-fast-training-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2310.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00426"}}}},{"paper":"/paper/sdxl-improving-latent-diffusion-models-for","slug":"sdxl-improving-latent-diffusion-models-for","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","date":"2023-07-04","arxiv_id":"2307.01952","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":13,"pointer_only_for_licence":0,"official":{"repos":["stability-ai/generative-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sdxl-improving-latent-diffusion-models-for#ran","syntology_url":"https://syntology.ai/paper/2307.01952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01952"}}}}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/wise/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/wise/papers/ran/1","json":"/dataset/wise/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":68,"samples_ran":51,"samples_constructed":0,"samples_ran_checked":40,"samples_ran_instrument_failed":11,"samples_unverified":17,"pointer_only_for_licence":16,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":5,"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":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/image-generation-on-wise","since_archive":"/sota/image-generation-on-wise#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/on-wise","since_archive":"/sota/on-wise#since-judged","papers_judged":4,"placed":0}]},"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":"d4a2747e13d7e85b649b65ab02fcdd9df45fcb62cd53648ba3773dc70e7ac6a0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}