{"url":"/sota/video-retrieval-on-activitynet","task":{"name":"Video Retrieval","url":"/task/video-retrieval","note":null},"dataset":{"name":"ActivityNet","url":"/dataset/activitynet"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query.  Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video R@50","text-to-video Mean Rank","text-to-video Median Rank","video-to-text R@1","video-to-text R@5","video-to-text Mean Rank","video-to-text Median Rank","video-to-text R@10","video-to-text R@50"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"text-to-video R@1":null,"text-to-video R@5":null,"text-to-video R@10":null,"text-to-video R@50":null,"text-to-video Mean Rank":null,"text-to-video Median Rank":null,"video-to-text R@1":null,"video-to-text R@5":null,"video-to-text Mean Rank":null,"video-to-text Median Rank":null,"video-to-text R@10":null,"video-to-text R@50":null}},"counts":{"rows":31,"rows_with_code":28,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":18},"rows":[{"rank_in_archive_order":1,"model":"InternVideo2-6B","metrics":{"text-to-video R@1":"74.1","video-to-text R@1":"69.7"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"VAST","metrics":{"text-to-video R@1":"70.5","text-to-video R@10":"95.5","text-to-video R@5":"90.9"},"uses_additional_data":true,"paper_date":"2023-05-29","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_url":"https://arxiv.org/abs/2305.18500v2","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","code":"https://github.com/TXH-mercury/VALOR","n_code_links":2,"syntology":{"n_ran":15,"n_unverified":27,"n_samples":42,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"VALOR","metrics":{"text-to-video R@1":"70.1","text-to-video R@10":"95.3","text-to-video R@5":"90.8"},"uses_additional_data":true,"paper_date":"2023-04-17","paper":"/paper/valor-vision-audio-language-omni-perception","paper_url":"https://arxiv.org/abs/2304.08345v2","paper_title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","code":"https://github.com/TXH-mercury/VALOR","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"GRAM","metrics":{"text-to-video R@1":"69.9","text-to-video R@10":"96.1","video-to-text R@1":"66.9","video-to-text R@10":"95.4"},"uses_additional_data":true,"paper_date":"2024-12-16","paper":"/paper/gramian-multimodal-representation-learning","paper_url":"https://arxiv.org/abs/2412.11959v1","paper_title":"Gramian Multimodal Representation Learning and Alignment","code":"https://github.com/ispamm/GRAM","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"COSA","metrics":{"text-to-video R@1":"67.3"},"uses_additional_data":true,"paper_date":"2023-06-15","paper":"/paper/cosa-concatenated-sample-pretrained-vision","paper_url":"https://arxiv.org/abs/2306.09085v1","paper_title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","code":"https://github.com/txh-mercury/cosa","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"UMT-L (ViT-L/16)","metrics":{"text-to-video R@1":"66.8","text-to-video R@10":"94.9","text-to-video R@5":"89.1","video-to-text R@1":"64.4","video-to-text R@10":"94.8","video-to-text R@5":"89.1"},"uses_additional_data":true,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"vid-TLDR (UMT-L)","metrics":{"text-to-video R@1":"66.7","text-to-video R@10":"94.4","text-to-video R@5":"88.6","video-to-text R@1":"63.9","video-to-text R@10":"94.5","video-to-text R@5":"88.7"},"uses_additional_data":true,"paper_date":"2024-03-20","paper":"/paper/vid-tldr-training-free-token-merging-for","paper_url":"https://arxiv.org/abs/2403.13347v2","paper_title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","code":"https://github.com/mlvlab/vid-tldr","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"InternVideo","metrics":{"text-to-video R@1":"62.2","video-to-text R@1":"62.8"},"uses_additional_data":true,"paper_date":"2022-12-06","paper":"/paper/internvideo-general-video-foundation-models","paper_url":"https://arxiv.org/abs/2212.03191v2","paper_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"CLIP-ViP","metrics":{"text-to-video Median Rank":"1","text-to-video R@1":"61.4","text-to-video R@10":"92.6","text-to-video R@5":"85.7"},"uses_additional_data":true,"paper_date":"2022-09-14","paper":"/paper/clip-vip-adapting-pre-trained-image-text","paper_url":"https://arxiv.org/abs/2209.06430v4","paper_title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","code":"https://github.com/microsoft/xpretrain","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":10,"model":"HunYuan_tvr","metrics":{"text-to-video Mean Rank":"4.0","text-to-video Median Rank":"1","text-to-video R@1":"57.3","text-to-video R@10":"93.1","text-to-video R@5":"84.8","video-to-text Mean Rank":"3.4","video-to-text Median Rank":"1","video-to-text R@1":"57.7","video-to-text R@10":"93.9","video-to-text R@5":"85.7"},"uses_additional_data":true,"paper_date":"2022-04-07","paper":"/paper/hunyuan-tvr-for-text-video-retrivial","paper_url":"https://arxiv.org/abs/2204.03382v8","paper_title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"VindLU","metrics":{"text-to-video R@1":"55.0","text-to-video R@10":" 89.7","text-to-video R@5":" 81.4"},"uses_additional_data":true,"paper_date":"2022-12-09","paper":"/paper/vindlu-a-recipe-for-effective-video-and","paper_url":"https://arxiv.org/abs/2212.05051v2","paper_title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","code":"https://github.com/klauscc/vindlu","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"TESTA (ViT-B/16)","metrics":{"text-to-video R@1":"54.8","text-to-video R@10":"89.6","text-to-video R@5":"80.8"},"uses_additional_data":true,"paper_date":"2023-10-29","paper":"/paper/testa-temporal-spatial-token-aggregation-for","paper_url":"https://arxiv.org/abs/2310.19060v1","paper_title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","code":"https://github.com/renshuhuai-andy/testa","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"RTQ","metrics":{"text-to-video R@1":"53.5","text-to-video R@10":"91.9","text-to-video R@5":"81.4"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/rtq-rethinking-video-language-understanding","paper_url":"https://arxiv.org/abs/2312.00347v2","paper_title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","code":"https://github.com/SCZwangxiao/RTQ-MM2023","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"DMAE\n(ViT-B/32)","metrics":{"text-to-video Mean Rank":"5.3","text-to-video Median Rank":"1.0","text-to-video R@1":"53.4","text-to-video R@10":"89.2","text-to-video R@5":"80.7"},"uses_additional_data":false,"paper_date":"2023-09-20","paper":"/paper/dual-modal-attention-enhanced-text-video","paper_url":"https://arxiv.org/abs/2309.11082v3","paper_title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","code":"https://github.com/alipay/Ant-Multi-Modal-Framework","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"CAMoE","metrics":{"text-to-video Mean Rank":"6.3","text-to-video Median Rank":"1","text-to-video R@1":"51.0","text-to-video R@10":"87.6","text-to-video R@5":"77.7"},"uses_additional_data":true,"paper_date":"2021-09-09","paper":"/paper/improving-video-text-retrieval-by-multi","paper_url":"https://arxiv.org/abs/2109.04290v3","paper_title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","code":"https://github.com/starmemda/camow","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"EMCL-Net++","metrics":{"text-to-video Mean Rank":"1","text-to-video R@1":"50.6","text-to-video R@5":"78.7","text-to-video R@50":"98.1","video-to-text Mean Rank":"1","video-to-text R@1":"50.6","video-to-text R@5":"78.9","video-to-text R@50":"98.4"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/expectation-maximization-contrastive-learning","paper_url":"https://arxiv.org/abs/2211.11427v1","paper_title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"HiTeA","metrics":{"text-to-video R@1":"49.7","text-to-video R@10":"86.7","text-to-video R@5":"77.1"},"uses_additional_data":true,"paper_date":"2022-12-30","paper":"/paper/hitea-hierarchical-temporal-aware-video","paper_url":"https://arxiv.org/abs/2212.14546v1","paper_title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"DiffusionRet+QB-Norm","metrics":{"text-to-video Mean Rank":"6.8","text-to-video Median Rank":"2.0","text-to-video R@1":"48.1","text-to-video R@10":"85.7","video-to-text Mean Rank":"6.7","video-to-text Median Rank":"2.0","video-to-text R@1":"47.4","video-to-text R@10":"86.7","video-to-text R@5":"76.3"},"uses_additional_data":false,"paper_date":"2023-03-17","paper":"/paper/diffusionret-generative-text-video-retrieval","paper_url":"https://arxiv.org/abs/2303.09867v2","paper_title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"Singularity","metrics":{"text-to-video R@1":"47.1","text-to-video R@10":"85.5","text-to-video R@5":"75.5"},"uses_additional_data":true,"paper_date":"2022-06-07","paper":"/paper/revealing-single-frame-bias-for-video-and","paper_url":"https://arxiv.org/abs/2206.03428v1","paper_title":"Revealing Single Frame Bias for Video-and-Language Learning","code":"https://github.com/jayleicn/ClipBERT","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"CenterCLIP (ViT-B/16)","metrics":{"text-to-video Mean Rank":"5.7","text-to-video Median Rank":"2","text-to-video R@1":"46.2","text-to-video R@10":"87.6","text-to-video R@5":"77.0","video-to-text Mean Rank":"5.5","video-to-text Median Rank":"2","video-to-text R@1":"46.7","video-to-text R@10":"88.0","video-to-text R@5":"77.1"},"uses_additional_data":true,"paper_date":"2022-05-02","paper":"/paper/centerclip-token-clustering-for-efficient","paper_url":"https://arxiv.org/abs/2205.00823v1","paper_title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","code":"https://github.com/mzhaoshuai/CenterCLIP","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":21,"model":"X-CLIP","metrics":{"text-to-video Mean Rank":"6.8","text-to-video R@1":"46.2","text-to-video R@5":"75.5","video-to-text Mean Rank":"6.4","video-to-text R@1":"46.4","video-to-text R@5":"75.9"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/x-clip-end-to-end-multi-grained-contrastive","paper_url":"https://arxiv.org/abs/2207.07285v2","paper_title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","code":"https://github.com/xuguohai/X-CLIP","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":22,"model":"DiffusionRet","metrics":{"text-to-video Mean Rank":"6.5","text-to-video Median Rank":"2.0","text-to-video R@1":"45.8","text-to-video R@10":"86.3","text-to-video R@5":"75.6","video-to-text Mean Rank":"6.3","video-to-text Median Rank":"2.0","video-to-text R@1":"43.8","video-to-text R@10":"86.7","video-to-text R@5":"75.3"},"uses_additional_data":false,"paper_date":"2023-03-17","paper":"/paper/diffusionret-generative-text-video-retrieval","paper_url":"https://arxiv.org/abs/2303.09867v2","paper_title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"HBI","metrics":{"text-to-video Mean Rank":"6.6","text-to-video Median Rank":"2.0","text-to-video R@1":"42.2","text-to-video R@10":"84.6","text-to-video R@5":"73.0","video-to-text Mean Rank":"6.5","video-to-text Median Rank":"2.0","video-to-text R@1":"42.4","video-to-text R@10":"86.0","video-to-text R@5":"73.0"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/video-text-as-game-players-hierarchical","paper_url":"https://arxiv.org/abs/2303.14369v1","paper_title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":11,"n_unverified":5,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"EMCL-Net","metrics":{"text-to-video Mean Rank":"2","text-to-video R@1":"41.2","text-to-video R@5":"72.7","video-to-text Mean Rank":"2","video-to-text R@1":"42.7","video-to-text R@5":"74","video-to-text R@50":"98.3"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/expectation-maximization-contrastive-learning","paper_url":"https://arxiv.org/abs/2211.11427v1","paper_title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"CLIP4Clip","metrics":{"text-to-video Mean Rank":"7.5","text-to-video Median Rank":"2","text-to-video R@1":"40.5","text-to-video R@5":"73.4","text-to-video R@50":"98.2"},"uses_additional_data":false,"paper_date":"2021-04-18","paper":"/paper/clip4clip-an-empirical-study-of-clip-for-end","paper_url":"https://arxiv.org/abs/2104.08860v2","paper_title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","code":"https://github.com/towhee-io/towhee","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":26,"model":"TACo","metrics":{"text-to-video Median Rank":"3.0","text-to-video R@1":"30.4","text-to-video R@5":"61.2","text-to-video R@50":"93.4"},"uses_additional_data":true,"paper_date":"2021-08-23","paper":"/paper/taco-token-aware-cascade-contrastive-learning","paper_url":"https://arxiv.org/abs/2108.09980v1","paper_title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"MMT-Pretrained","metrics":{"text-to-video Mean Rank":"16","text-to-video Median Rank":"3.3","text-to-video R@1":"28.7","text-to-video R@5":"61.4","text-to-video R@50":"94.5"},"uses_additional_data":true,"paper_date":"2020-07-21","paper":"/paper/multi-modal-transformer-for-video-retrieval","paper_url":"https://arxiv.org/abs/2007.10639v1","paper_title":"Multi-modal Transformer for Video Retrieval","code":"https://github.com/gabeur/mmt","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"HD-VILA","metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"28.5","text-to-video R@5":"57.4","text-to-video R@50":"94"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/advancing-high-resolution-video-language","paper_url":"https://arxiv.org/abs/2111.10337v2","paper_title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","code":"https://github.com/microsoft/xpretrain","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"Ours","metrics":{"text-to-video R@1":"25.4","text-to-video R@5":"59.1","video-to-text R@1":"26.1","video-to-text R@5":"60"},"uses_additional_data":false,"paper_date":"2021-10-21","paper":"/paper/video-and-text-matching-with-conditioned","paper_url":"https://arxiv.org/abs/2110.11298v1","paper_title":"Video and Text Matching with Conditioned Embeddings","code":"https://github.com/ameenali/videomatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"MMT","metrics":{"text-to-video Mean Rank":"20.8","text-to-video Median Rank":"5","text-to-video R@1":"22.7","text-to-video R@5":"54.2","text-to-video R@50":"93.2"},"uses_additional_data":false,"paper_date":"2020-07-21","paper":"/paper/multi-modal-transformer-for-video-retrieval","paper_url":"https://arxiv.org/abs/2007.10639v1","paper_title":"Multi-modal Transformer for Video Retrieval","code":"https://github.com/gabeur/mmt","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"Collaborative Experts","metrics":{"text-to-video Mean Rank":"23.1","text-to-video Median Rank":"6","text-to-video R@1":"20.5","text-to-video R@10":"63.9","text-to-video R@5":"47.7","text-to-video R@50":"91.4"},"uses_additional_data":false,"paper_date":"2019-07-31","paper":"/paper/use-what-you-have-video-retrieval-using","paper_url":"https://arxiv.org/abs/1907.13487v2","paper_title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","code":"https://github.com/albanie/collaborative-experts","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":1}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":19,"rows_with_any_sample_ran":17,"distinct_papers_with_graph_line":16,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":69,"n_unverified":76,"n_samples":145,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":78,"n_unverified":84,"n_samples":162,"n_pointer_only_licence":10,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}