{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B3YCUTGB7KMOL77OVLCKDQJ74X","short_pith_number":"pith:B3YCUTGB","schema_version":"1.0","canonical_sha256":"0ef02a4cc1fa98e5ffeeaac4a1c13fe5d3bc7e34b56bed9eb4bc87905b978de5","source":{"kind":"arxiv","id":"2107.10030","version":1},"attestation_state":"computed","paper":{"title":"Differentiable Feature Selection, a Reparameterization Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\'er\\'emie Dona (MLIA), Patrick Gallinari (MLIA)","submitted_at":"2021-07-21T11:52:34Z","abstract_excerpt":"We consider the task of feature selection for reconstruction which consists in choosing a small subset of features from which whole data instances can be reconstructed. This is of particular importance in several contexts involving for example costly physical measurements, sensor placement or information compression. To break the intrinsic combinatorial nature of this problem, we formulate the task as optimizing a binary mask distribution enabling an accurate reconstruction. We then face two main challenges. One concerns differentiability issues due to the binary distribution. The second one c"},"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":"2107.10030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T11:52:34Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"9d694f179b1d19c08905e84cb21f98f907997d8ede96bb17ec2f4f20701e29e4","abstract_canon_sha256":"57a2559d935d5fc0de51782fec81c353698bc7a4ccd3bd54ab5270762e7adc26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:42.042759Z","signature_b64":"UKBbb1KDGQkrraRlHJidSRDcusNovZPNxDfy5iwp2FS5zGZ+Kd1caWPmzoO8nwRAsuocdCY2wt7Fo4h353zlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ef02a4cc1fa98e5ffeeaac4a1c13fe5d3bc7e34b56bed9eb4bc87905b978de5","last_reissued_at":"2026-07-05T02:59:42.042417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:42.042417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Feature Selection, a Reparameterization Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\'er\\'emie Dona (MLIA), Patrick Gallinari (MLIA)","submitted_at":"2021-07-21T11:52:34Z","abstract_excerpt":"We consider the task of feature selection for reconstruction which consists in choosing a small subset of features from which whole data instances can be reconstructed. This is of particular importance in several contexts involving for example costly physical measurements, sensor placement or information compression. To break the intrinsic combinatorial nature of this problem, we formulate the task as optimizing a binary mask distribution enabling an accurate reconstruction. We then face two main challenges. One concerns differentiability issues due to the binary distribution. The second one c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10030","kind":"arxiv","version":1},"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/2107.10030/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":"2107.10030","created_at":"2026-07-05T02:59:42.042475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10030v1","created_at":"2026-07-05T02:59:42.042475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10030","created_at":"2026-07-05T02:59:42.042475+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3YCUTGB7KMO","created_at":"2026-07-05T02:59:42.042475+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3YCUTGB7KMOL77O","created_at":"2026-07-05T02:59:42.042475+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3YCUTGB","created_at":"2026-07-05T02:59:42.042475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X","json":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X.json","graph_json":"https://pith.science/api/pith-number/B3YCUTGB7KMOL77OVLCKDQJ74X/graph.json","events_json":"https://pith.science/api/pith-number/B3YCUTGB7KMOL77OVLCKDQJ74X/events.json","paper":"https://pith.science/paper/B3YCUTGB"},"agent_actions":{"view_html":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X","download_json":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X.json","view_paper":"https://pith.science/paper/B3YCUTGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10030&json=true","fetch_graph":"https://pith.science/api/pith-number/B3YCUTGB7KMOL77OVLCKDQJ74X/graph.json","fetch_events":"https://pith.science/api/pith-number/B3YCUTGB7KMOL77OVLCKDQJ74X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X/action/storage_attestation","attest_author":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X/action/author_attestation","sign_citation":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X/action/citation_signature","submit_replication":"https://pith.science/pith/B3YCUTGB7KMOL77OVLCKDQJ74X/action/replication_record"}},"created_at":"2026-07-05T02:59:42.042475+00:00","updated_at":"2026-07-05T02:59:42.042475+00:00"}