{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GVVLM6244G7ZBL2ZCV6BWMUTKR","short_pith_number":"pith:GVVLM624","schema_version":"1.0","canonical_sha256":"356ab67b5ce1bf90af59157c1b3293546e044c6245f9e8c06f71a11cc1ea47c6","source":{"kind":"arxiv","id":"2312.14254","version":2},"attestation_state":"computed","paper":{"title":"Contextual Feature Selection with Conditional Stochastic Gates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Gal Mishne, Hadas Benisty, Jackie Schiller, Maria Lavzin, Ofir Lindenbaum, Ram Dyuthi Sristi, Shira Lifshitz","submitted_at":"2023-12-21T19:12:59Z","abstract_excerpt":"Feature selection is a crucial tool in machine learning and is widely applied across various scientific disciplines. Traditional supervised methods generally identify a universal set of informative features for the entire population. However, feature relevance often varies with context, while the context itself may not directly affect the outcome variable. Here, we propose a novel architecture for contextual feature selection where the subset of selected features is conditioned on the value of context variables. Our new approach, Conditional Stochastic Gates (c-STG), models the importance of f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.14254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T19:12:59Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"13a8ddd1c5917dd7ec6dc1d9a28142f0722602ce7b8db615076b59ee13d1fb09","abstract_canon_sha256":"3b36e3489b65376b754e6d64d0c7f422d35fea5eed3a1eb9b486ccec22044715"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:58.356335Z","signature_b64":"1xJE4THKBtooHqXOZX63U1xYe4NPxZhKY4+shrnfHu9ZD99mFZQelk4OrdPzCPYAtmgKt9KbSWmgJNt53jh9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"356ab67b5ce1bf90af59157c1b3293546e044c6245f9e8c06f71a11cc1ea47c6","last_reissued_at":"2026-07-05T08:28:58.355818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:58.355818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Feature Selection with Conditional Stochastic Gates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Gal Mishne, Hadas Benisty, Jackie Schiller, Maria Lavzin, Ofir Lindenbaum, Ram Dyuthi Sristi, Shira Lifshitz","submitted_at":"2023-12-21T19:12:59Z","abstract_excerpt":"Feature selection is a crucial tool in machine learning and is widely applied across various scientific disciplines. Traditional supervised methods generally identify a universal set of informative features for the entire population. However, feature relevance often varies with context, while the context itself may not directly affect the outcome variable. Here, we propose a novel architecture for contextual feature selection where the subset of selected features is conditioned on the value of context variables. Our new approach, Conditional Stochastic Gates (c-STG), models the importance of f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14254","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.14254/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.14254","created_at":"2026-07-05T08:28:58.355882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14254v2","created_at":"2026-07-05T08:28:58.355882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14254","created_at":"2026-07-05T08:28:58.355882+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVVLM6244G7Z","created_at":"2026-07-05T08:28:58.355882+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVVLM6244G7ZBL2Z","created_at":"2026-07-05T08:28:58.355882+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVVLM624","created_at":"2026-07-05T08:28:58.355882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.23304","citing_title":"Context-Adaptive Inference: A Unified Statistical and Foundation-Model View","ref_index":112,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR","json":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR.json","graph_json":"https://pith.science/api/pith-number/GVVLM6244G7ZBL2ZCV6BWMUTKR/graph.json","events_json":"https://pith.science/api/pith-number/GVVLM6244G7ZBL2ZCV6BWMUTKR/events.json","paper":"https://pith.science/paper/GVVLM624"},"agent_actions":{"view_html":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR","download_json":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR.json","view_paper":"https://pith.science/paper/GVVLM624","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14254&json=true","fetch_graph":"https://pith.science/api/pith-number/GVVLM6244G7ZBL2ZCV6BWMUTKR/graph.json","fetch_events":"https://pith.science/api/pith-number/GVVLM6244G7ZBL2ZCV6BWMUTKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR/action/storage_attestation","attest_author":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR/action/author_attestation","sign_citation":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR/action/citation_signature","submit_replication":"https://pith.science/pith/GVVLM6244G7ZBL2ZCV6BWMUTKR/action/replication_record"}},"created_at":"2026-07-05T08:28:58.355882+00:00","updated_at":"2026-07-05T08:28:58.355882+00:00"}