{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/vidore-benchmark-v2-raising-the-bar-for","title":"ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval","arxiv_id":"2505.17166","date":"2025-05-22","proceeding":null,"authors":["Quentin Macé","António Loison","Manuel Faysse"],"abstract":"The ViDoRe Benchmark V1 was approaching saturation with top models exceeding 90% nDCG@5, limiting its ability to discern improvements. ViDoRe Benchmark V2 introduces realistic, challenging retrieval scenarios via blind contextual querying, long and cross-document queries, and a hybrid synthetic and human-in-the-loop query generation process. It comprises four diverse, multilingual datasets and provides clear evaluation instructions. Initial results demonstrate substantial room for advancement and highlight insights on model generalization and multilingual capability. This benchmark is designed as a living resource, inviting community contributions to maintain relevance through future evaluations.","url_abs":"https://arxiv.org/abs/2505.17166v1","url_pdf":"https://arxiv.org/pdf/2505.17166v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"vidore-benchmark-v2-raising-the-bar-for","repo_url":"https://github.com/illuin-tech/vidore-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vidore-benchmark-v2-raising-the-bar-for","repo_url":"https://github.com/illuin-tech/colpali","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.17166","atlas_url":"https://app.syntology.ai/?focus=2505.17166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17166"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/illuin-tech/vidore-benchmark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/illuin-tech/colpali","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bde3923a8fec6850","entry":"aggregate_results","repo":"illuin-tech/vidore-benchmark","repo_kind":"official","path":"src/vidore_benchmark/pipeline_evaluation/evaluator.py","file_url":"https://github.com/illuin-tech/vidore-benchmark/blob/HEAD/src/vidore_benchmark/pipeline_evaluation/evaluator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bde3923a8fec6850"}},{"code_sha256_prefix":"1ffacc9d032eaa50","entry":"score_multi_vector","repo":"illuin-tech/vidore-benchmark","repo_kind":"official","path":"src/vidore_benchmark/evaluation/scoring.py","file_url":"https://github.com/illuin-tech/vidore-benchmark/blob/HEAD/src/vidore_benchmark/evaluation/scoring.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ffacc9d032eaa50"}},{"code_sha256_prefix":"4014d55a46ee32b1","entry":"load_vidore_dataset","repo":"illuin-tech/vidore-benchmark","repo_kind":"official","path":"src/vidore_benchmark/pipeline_evaluation/dataset_loader.py","file_url":"https://github.com/illuin-tech/vidore-benchmark/blob/HEAD/src/vidore_benchmark/pipeline_evaluation/dataset_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4014d55a46ee32b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}