{"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/prospector-heads-generalized-feature","title":"Prospector Heads: Generalized Feature Attribution for Large Models & Data","arxiv_id":"2402.11729","date":"2024-02-18","proceeding":null,"authors":["Gautam Machiraju","Alexander Derry","Arjun Desai","Neel Guha","Amir-Hossein Karimi","James Zou","Russ Altman","Christopher Ré","Parag Mallick"],"abstract":"Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on \"explaining\" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.","url_abs":"https://arxiv.org/abs/2402.11729v2","url_pdf":"https://arxiv.org/pdf/2402.11729v2.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":"prospector-heads-generalized-feature","repo_url":"https://github.com/gmachiraju/k2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11729"}},"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/gmachiraju/k2","reach":null}],"summary":{"ran":2,"ran_draft_wrong":3,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":10,"samples":[{"code_sha256_prefix":"2fbbd3736d73afc8","entry":"construct_sprite","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fbbd3736d73afc8"}},{"code_sha256_prefix":"c21dcb7a74fed6c8","entry":"convert_graph2arr","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c21dcb7a74fed6c8"}},{"code_sha256_prefix":"4151128d19e2a9ac","entry":"deserialize","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4151128d19e2a9ac"}},{"code_sha256_prefix":"be2dc6ef9bc23fe5","entry":"get_prospect_range","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be2dc6ef9bc23fe5"}},{"code_sha256_prefix":"bcb28698ac4fb0d4","entry":"set_graph_emb","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bcb28698ac4fb0d4"}},{"code_sha256_prefix":"c3ba13f40abe6ee1","entry":"visualize_cell_graph","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3ba13f40abe6ee1"}},{"code_sha256_prefix":"bd9d46ed18fef7e9","entry":"K2Model","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd9d46ed18fef7e9"}},{"code_sha256_prefix":"d147647e3fdc860d","entry":"dotdict","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d147647e3fdc860d"}},{"code_sha256_prefix":"714dab283815345e","entry":"visualize_quantizedZ","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"714dab283815345e"}},{"code_sha256_prefix":"2fd8ef05fa8aa404","entry":"visualize_sprite","repo":"gmachiraju/k2","repo_kind":"official","path":"src/k2.py","file_url":"https://github.com/gmachiraju/k2/blob/HEAD/src/k2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fd8ef05fa8aa404"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}