{"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":"/paper/on-the-concept-trustworthiness-in-concept","title":"On the Concept Trustworthiness in Concept Bottleneck Models","arxiv_id":"2403.14349","date":"2024-03-21","proceeding":null,"authors":["Qihan Huang","Jie Song","Jingwen Hu","Haofei Zhang","Yong Wang","Mingli Song"],"abstract":"Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention due to their remarkable interpretability achieved by the interpretable concept bottleneck. However, despite the transparency of the concept-to-label prediction, the mapping from the input to the intermediate concept remains a black box, giving rise to concerns about the trustworthiness of the learned concepts (i.e., these concepts may be predicted based on spurious cues). The issue of concept untrustworthiness greatly hampers the interpretability of CBMs, thereby hindering their further advancement. To conduct a comprehensive analysis on this issue, in this study we establish a benchmark to assess the trustworthiness of concepts in CBMs. A pioneering metric, referred to as concept trustworthiness score, is proposed to gauge whether the concepts are derived from relevant regions. Additionally, an enhanced CBM is introduced, enabling concept predictions to be made specifically from distinct parts of the feature map, thereby facilitating the exploration of their related regions. Besides, we introduce three modules, namely the cross-layer alignment (CLA) module, the cross-image alignment (CIA) module, and the prediction alignment (PA) module, to further enhance the concept trustworthiness within the elaborated CBM. The experiments on five datasets across ten architectures demonstrate that without using any concept localization annotations during training, our model improves the concept trustworthiness by a large margin, meanwhile achieving superior accuracy to the state-of-the-arts. Our code is available at https://github.com/hqhQAQ/ProtoCBM.","url_abs":"https://arxiv.org/abs/2403.14349v1","url_pdf":"https://arxiv.org/pdf/2403.14349v1.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":"on-the-concept-trustworthiness-in-concept","repo_url":"https://github.com/hqhqaq/protocbm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.14349","atlas_url":"https://app.syntology.ai/?focus=2403.14349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14349"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.14349"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.14349"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.14349\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2403.14349"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2403.14349\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2403.14349"},"call":"get_concepts_for_paper(arxiv_id=\"2403.14349\")"}],"by_repo":[{"repo":"hqhqaq/protocbm","kind":"official","samples":8,"ran":6,"instrument":5,"unverified":2}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2403.14349.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2403.14349.svg"},"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":"deterministic:regex_extraction","url":"https://github.com/hqhQAQ/ProtoCBM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hqhqaq/protocbm","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"ran":1,"ran_fixture":1,"unverified":2},"n_samples":8,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_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'","n_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)"},"by_repo_kind":{"official":{"samples":8,"ran":6,"n_ran_checked":1,"n_instrument":5,"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":8,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"d9def42110729a85","code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"models/resnet_features_all.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/models/resnet_features_all.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int","fixture_out_type":"Conv2d","code_page":"/code/conv1x1","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256":"fac5364e2f53c6db","code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"models/resnet_features_all.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/models/resnet_features_all.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int","fixture_out_type":"Conv2d","code_page":"/code/conv3x3","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256":"d8a0333d5ea69eda","code_sha256_prefix":"d8a0333d5ea69eda","entry":"draw_point","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"util/local_parts.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/util/local_parts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"img:ndarray/3/int, point:tuple/1/int, bbox_size:int/0/int, color:tuple/1/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"d8a0333d5ea69eda"}},{"code_sha256":"a717d760b8847ead","code_sha256_prefix":"a717d760b8847ead","entry":"in_bbox","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"util/local_parts.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/util/local_parts.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"loc:list/1/int, bbox:list/1/int","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"a717d760b8847ead"}},{"code_sha256":"ce13279979f0c4cb","code_sha256_prefix":"ce13279979f0c4cb","entry":"vgg11_bn_features","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"models/vgg_features_all.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/models/vgg_features_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pretrained:bool/0/bool","fixture_out_type":"VGG_features","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"ce13279979f0c4cb"}},{"code_sha256":"9cdccaaee8e9f50a","code_sha256_prefix":"9cdccaaee8e9f50a","entry":"vgg13_features","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"models/vgg_features_all.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/models/vgg_features_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pretrained:bool/0/bool","fixture_out_type":"VGG_features","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"9cdccaaee8e9f50a"}},{"code_sha256":"54e03270e0c8586c","code_sha256_prefix":"54e03270e0c8586c","entry":"resnet18_features","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"models/resnet_features_all.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/models/resnet_features_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/resnet18-features","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"54e03270e0c8586c"}},{"code_sha256":"6a70e95b9dde024e","code_sha256_prefix":"6a70e95b9dde024e","entry":"vgg11_features","repo":"hqhQAQ/ProtoCBM","repo_kind":"official","path":"models/vgg_features_all.py","file_url":"https://github.com/hqhQAQ/ProtoCBM/blob/HEAD/models/vgg_features_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hqhQAQ/ProtoCBM when it was checked","mcp_get_code":{"code_sha256":"6a70e95b9dde024e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"38979ad63fc424d97445fd2b75a3cb606063396e8ef1d18c8238cd99cf4a8cc9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}