{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OQWPZWGD5N6OZ6IPEWQKTCACJD","short_pith_number":"pith:OQWPZWGD","schema_version":"1.0","canonical_sha256":"742cfcd8c3eb7cecf90f25a0a9880248e4efc6d06a8b1c7aaddd6c29b5796bbd","source":{"kind":"arxiv","id":"2206.00267","version":2},"attestation_state":"computed","paper":{"title":"LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chao Liao, Dongying Kong, Jianchao Tan, Ji Liu, Lei Yuan, Sen Yang, Yi Guo, Zhaocheng Liu, Zhi Chen","submitted_at":"2022-06-01T06:50:44Z","abstract_excerpt":"In industry, feature selection is a standard but necessary step to search for an optimal set of informative feature fields for efficient and effective training of deep Click-Through Rate (CTR) models. Most previous works measure the importance of feature fields by using their corresponding continuous weights from the model, then remove the feature fields with small weight values. However, removing many features that correspond to small but not exact zero weights will inevitably hurt model performance and not be friendly to hot-start model training. There is also no theoretical guarantee that t"},"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":"2206.00267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-01T06:50:44Z","cross_cats_sorted":[],"title_canon_sha256":"1b62a6663336394412e7f8961790d74180b032e5fdc40d4b3234d546dc1f703f","abstract_canon_sha256":"6a6912a3b90f55c3fe293bd629d8b9187da8beee809266602bcc908722184e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:21.261734Z","signature_b64":"FTHCIHJlH5sYikPfBdaH2sKj0b80aC7zzPVV7y+Qte4prV0Ffk1bN0UIuBfBB8D2/uleGYL/0wEplE1UXcxdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742cfcd8c3eb7cecf90f25a0a9880248e4efc6d06a8b1c7aaddd6c29b5796bbd","last_reissued_at":"2026-07-05T04:54:21.261243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:21.261243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chao Liao, Dongying Kong, Jianchao Tan, Ji Liu, Lei Yuan, Sen Yang, Yi Guo, Zhaocheng Liu, Zhi Chen","submitted_at":"2022-06-01T06:50:44Z","abstract_excerpt":"In industry, feature selection is a standard but necessary step to search for an optimal set of informative feature fields for efficient and effective training of deep Click-Through Rate (CTR) models. Most previous works measure the importance of feature fields by using their corresponding continuous weights from the model, then remove the feature fields with small weight values. However, removing many features that correspond to small but not exact zero weights will inevitably hurt model performance and not be friendly to hot-start model training. There is also no theoretical guarantee that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00267","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/2206.00267/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":"2206.00267","created_at":"2026-07-05T04:54:21.261301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00267v2","created_at":"2026-07-05T04:54:21.261301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00267","created_at":"2026-07-05T04:54:21.261301+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQWPZWGD5N6O","created_at":"2026-07-05T04:54:21.261301+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQWPZWGD5N6OZ6IP","created_at":"2026-07-05T04:54:21.261301+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQWPZWGD","created_at":"2026-07-05T04:54:21.261301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01111","citing_title":"LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2410.15272","citing_title":"Performance-Driven QUBO for Recommender Systems on Quantum Annealers","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09315","citing_title":"ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03419","citing_title":"Beyond Distributive Justice: Hermeneutical Fairness in Ad Delivery","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06441","citing_title":"Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD","json":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD.json","graph_json":"https://pith.science/api/pith-number/OQWPZWGD5N6OZ6IPEWQKTCACJD/graph.json","events_json":"https://pith.science/api/pith-number/OQWPZWGD5N6OZ6IPEWQKTCACJD/events.json","paper":"https://pith.science/paper/OQWPZWGD"},"agent_actions":{"view_html":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD","download_json":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD.json","view_paper":"https://pith.science/paper/OQWPZWGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00267&json=true","fetch_graph":"https://pith.science/api/pith-number/OQWPZWGD5N6OZ6IPEWQKTCACJD/graph.json","fetch_events":"https://pith.science/api/pith-number/OQWPZWGD5N6OZ6IPEWQKTCACJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD/action/storage_attestation","attest_author":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD/action/author_attestation","sign_citation":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD/action/citation_signature","submit_replication":"https://pith.science/pith/OQWPZWGD5N6OZ6IPEWQKTCACJD/action/replication_record"}},"created_at":"2026-07-05T04:54:21.261301+00:00","updated_at":"2026-07-05T04:54:21.261301+00:00"}