{"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/causal-triplet-an-open-challenge-for","title":"Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning","arxiv_id":"2301.05169","date":"2023-01-12","proceeding":null,"authors":["Yuejiang Liu","Alexandre Alahi","Chris Russell","Max Horn","Dominik Zietlow","Bernhard Schölkopf","Francesco Locatello"],"abstract":"Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work. Our code and datasets will be available at https://sites.google.com/view/causaltriplet.","url_abs":"https://arxiv.org/abs/2301.05169v2","url_pdf":"https://arxiv.org/pdf/2301.05169v2.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":"causal-triplet-an-open-challenge-for","repo_url":"https://github.com/CausalTriplet/causaltriplet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[{"slug":"causal-triplet","name":"Causal Triplet","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.05169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05169"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/CausalTriplet/causaltriplet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1,"unverified":11},"by_repo_kind":{"official":{"samples":12,"ran":1,"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":"863fc64cd51264f0","entry":"reparametrize","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"model/slotpair.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/model/slotpair.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"863fc64cd51264f0"}},{"code_sha256_prefix":"9da0bea29037001a","entry":"analyze_log","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"analysis/common.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/analysis/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9da0bea29037001a"}},{"code_sha256_prefix":"3e53111511bb1304","entry":"build_grid","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"model/slotpair.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/model/slotpair.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e53111511bb1304"}},{"code_sha256_prefix":"91e6bfc2eccdd5b5","entry":"count_param","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"util.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91e6bfc2eccdd5b5"}},{"code_sha256_prefix":"b330034564283acc","entry":"df_to_dict","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b330034564283acc"}},{"code_sha256_prefix":"c4fa1be5e27bafd8","entry":"extract_csv","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"analysis/common.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/analysis/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c4fa1be5e27bafd8"}},{"code_sha256_prefix":"cdfac8247641f7cf","entry":"extract_pair","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cdfac8247641f7cf"}},{"code_sha256_prefix":"f5669e360fe43efa","entry":"extract_setting","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"analysis/common.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/analysis/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f5669e360fe43efa"}},{"code_sha256_prefix":"cb7ac709b70d901a","entry":"group_to_map","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"model/grouppair.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/model/grouppair.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb7ac709b70d901a"}},{"code_sha256_prefix":"cfc85dbaaf297834","entry":"resize_attn_map","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"model/grouppair.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/model/grouppair.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfc85dbaaf297834"}},{"code_sha256_prefix":"3bc01008287f02c5","entry":"split_df","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3bc01008287f02c5"}},{"code_sha256_prefix":"55fe5a20a8c9e4f0","entry":"unstack_and_split","repo":"CausalTriplet/causaltriplet","repo_kind":"official","path":"model/slotpair.py","file_url":"https://github.com/CausalTriplet/causaltriplet/blob/HEAD/model/slotpair.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55fe5a20a8c9e4f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}