{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NS4LKHJY4D6FE35P332E5ATXXS","short_pith_number":"pith:NS4LKHJY","schema_version":"1.0","canonical_sha256":"6cb8b51d38e0fc526fafdef44e8277bc992ab191fda89e7eeb90916e77c0f5b6","source":{"kind":"arxiv","id":"2110.14812","version":1},"attestation_state":"computed","paper":{"title":"Differentiable NAS Framework and Application to Ads CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Aravind Kalaiah, Bichen Wu, Dheevatsa Mudigere, Kurt Keutzer, Maxim Naumov, Misha Smelyanskiy, Ravi Krishna","submitted_at":"2021-10-25T05:46:27Z","abstract_excerpt":"Neural architecture search (NAS) methods aim to automatically find the optimal deep neural network (DNN) architecture as measured by a given objective function, typically some combination of task accuracy and inference efficiency. For many areas, such as computer vision and natural language processing, this is a critical, yet still time consuming process. New NAS methods have recently made progress in improving the efficiency of this process. We implement an extensible and modular framework for Differentiable Neural Architecture Search (DNAS) to help solve this problem. We include an overview "},"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":"2110.14812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T05:46:27Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"92e020c059bd91247c17bcda66c11ace8e21869d9e28314b565413eafe25d53b","abstract_canon_sha256":"cc162eac687efcdd453a3c2dde9288be7e18f53184cb67d2ac3f36b8de93677e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:47.545916Z","signature_b64":"5e3K6Lbpxzm6DSheyE664YugFhQC3mEGJSLkCNN3EsOuuViT6LUrk9EY+JcBHHgQNOxEmc+oXG3BlBNk0uglCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb8b51d38e0fc526fafdef44e8277bc992ab191fda89e7eeb90916e77c0f5b6","last_reissued_at":"2026-07-05T03:26:47.545506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:47.545506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable NAS Framework and Application to Ads CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Aravind Kalaiah, Bichen Wu, Dheevatsa Mudigere, Kurt Keutzer, Maxim Naumov, Misha Smelyanskiy, Ravi Krishna","submitted_at":"2021-10-25T05:46:27Z","abstract_excerpt":"Neural architecture search (NAS) methods aim to automatically find the optimal deep neural network (DNN) architecture as measured by a given objective function, typically some combination of task accuracy and inference efficiency. For many areas, such as computer vision and natural language processing, this is a critical, yet still time consuming process. New NAS methods have recently made progress in improving the efficiency of this process. We implement an extensible and modular framework for Differentiable Neural Architecture Search (DNAS) to help solve this problem. We include an overview "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14812","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/2110.14812/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":"2110.14812","created_at":"2026-07-05T03:26:47.545561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14812v1","created_at":"2026-07-05T03:26:47.545561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14812","created_at":"2026-07-05T03:26:47.545561+00:00"},{"alias_kind":"pith_short_12","alias_value":"NS4LKHJY4D6F","created_at":"2026-07-05T03:26:47.545561+00:00"},{"alias_kind":"pith_short_16","alias_value":"NS4LKHJY4D6FE35P","created_at":"2026-07-05T03:26:47.545561+00:00"},{"alias_kind":"pith_short_8","alias_value":"NS4LKHJY","created_at":"2026-07-05T03:26:47.545561+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29119","citing_title":"Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS","json":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS.json","graph_json":"https://pith.science/api/pith-number/NS4LKHJY4D6FE35P332E5ATXXS/graph.json","events_json":"https://pith.science/api/pith-number/NS4LKHJY4D6FE35P332E5ATXXS/events.json","paper":"https://pith.science/paper/NS4LKHJY"},"agent_actions":{"view_html":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS","download_json":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS.json","view_paper":"https://pith.science/paper/NS4LKHJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14812&json=true","fetch_graph":"https://pith.science/api/pith-number/NS4LKHJY4D6FE35P332E5ATXXS/graph.json","fetch_events":"https://pith.science/api/pith-number/NS4LKHJY4D6FE35P332E5ATXXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS/action/storage_attestation","attest_author":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS/action/author_attestation","sign_citation":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS/action/citation_signature","submit_replication":"https://pith.science/pith/NS4LKHJY4D6FE35P332E5ATXXS/action/replication_record"}},"created_at":"2026-07-05T03:26:47.545561+00:00","updated_at":"2026-07-05T03:26:47.545561+00:00"}